US20090037088A1 - Running plan creating apparatus - Google Patents
Running plan creating apparatus Download PDFInfo
- Publication number
- US20090037088A1 US20090037088A1 US12/182,401 US18240108A US2009037088A1 US 20090037088 A1 US20090037088 A1 US 20090037088A1 US 18240108 A US18240108 A US 18240108A US 2009037088 A1 US2009037088 A1 US 2009037088A1
- Authority
- US
- United States
- Prior art keywords
- vehicle
- running
- degree
- risk
- running plan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
Definitions
- the present invention relates to a running plan creating apparatus which creates a safer running plan of a running vehicle by estimating the degree of risk of another vehicle thereabout.
- an apparatus which predicts positions from the present to T seconds thereafter, computes respective degrees of risk at the positions on the road, creates the risk-minimized running track where the sum of degrees of risk along the running path is minimized as the running path of the own vehicle, and presents it to the driver (e.g., Japanese Patent Application Laid-Open No. 2006-154967).
- This apparatus sets areas occupied by the obstacles and blind spot areas formed by the obstacles as locations with a degree of risk.
- the above-mentioned conventional apparatus provides the areas occupied by the obstacles and blind spot areas formed by the obstacles with only a fixed degree of risk corresponding to the reliability of detection, but does not take account of respective kinetic energies, unstableness in running, blind spot areas, and the like of the other vehicles thereabout, thus failing to calculate the respective degrees of risk of the other vehicles. Therefore, thus created risk-minimized running track does not always yield high safety.
- the characteristic information acquiring means may acquire a relative relationship between the other vehicle and a vehicle thereabout as the characteristic information. This allows the degree of risk to be estimated according to what characteristic the other vehicle has in terms of the relationship to the vehicle thereabout.
- the characteristic information may include at least a desirable headway time or time to collision of the other vehicle with respect to a vehicle thereabout, while the risk degree estimating means may estimate the degree of risk to be higher as the desirable headway time or time to collision is shorter. Since a vehicle more likely to approach a vehicle thereabout has a higher possibility of coming into contact therewith, creating such a running plan as to evade running near such a vehicle can lower potential risks.
- the characteristic information acquiring means may acquire a blind spot to become a blind spot for the driver of the other vehicle as the characteristic information, while the risk degree estimating means may estimate the degree of risk of each of the other vehicles by providing the blind spot area with a predetermined value. This can create such a running plan as to evade the blind spot for the driver of the other vehicle, so as to reduce the risk of accidents being caused by oversight of the drivers of the other vehicles.
- the running plan creating apparatus further comprises threshold selecting means for selecting a higher threshold as the degree of urgency is higher, while the running plan creating means creates such a running plan as to reduce the integrated value of the degree of risk when the integrated value exceeds the threshold.
- This can create such a running plan as to give a higher priority to the running condition as the degree of urgency is higher.
- FIG. 4 is a schematic view showing a hardware structural example of a vehicle mounting the running plan creating apparatus of FIG. 1 ;
- FIG. 7 is a view showing an unsafety degree distribution
- FIG. 11 is a view showing a blind spot determination value distribution
- FIG. 1 is a block diagram showing the structure of the running plan creating apparatus in accordance with the first embodiment.
- the running plan creating apparatus 1 comprises a running plan creating ECU (Electric Control Unit) 10 constructed by utilizing hardware such as a CPU (central processing unit), a memory, and the like and software, while being mounted to a vehicle (hereinafter also referred to as own vehicle) to be controlled which is under automatic driving control.
- ECU Electronic Control Unit
- the own vehicle sensor 20 is a sensor for detecting the own vehicle state quantity, e.g., a vehicle speed sensor 22 , acceleration sensor, yaw rate sensor, or steering angle sensor.
- the value detected by the own vehicle sensor 20 is used for computing an estimated value of state quantity of the own vehicle (e.g., vehicle speed, acceleration, yaw rate, or steering angle) at present from a vehicle model built in as software within the ECU 10 .
- the perimeter sensor 30 is a sensor for monitoring thereabout, such as a camera 32 or millimeter-wave radar 34 .
- the value detected by the perimeter sensor 30 is used for recognizing other vehicles running about the own vehicle and compute other vehicle information such as relative distances, angles, and speeds with respect to the own vehicle.
- the navigation unit (road information acquiring means) 40 is a device which guides the driver of the own vehicle in running.
- the navigation unit 40 has a position detecting part 42 and a map information database (DB) 44 .
- the position detecting part 42 detects the position (positional coordinates) of the own vehicle by receiving a signal from a GPS satellite.
- the map information DB 44 stores road information such as road forms and road attributes. This can display the current position of the own vehicle on a map and guide the vehicle in running to a destination.
- the running plan creating ECU 10 has a data storage part 11 , a characteristic learning part 12 , an action predicting part 13 , a weight estimating part 14 , a kinetic energy distribution setting part 15 , a running plan creating part 16 , and a safety evaluating part 17 .
- the data storage part 11 stores the data detected by the own vehicle sensor 20 and perimeter sensor 30 . Also, the data storage part 11 stores a table which indicates the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) for each kind of vehicles (e.g., vehicle type and size) as performances of the vehicles as shown in FIG. 2 .
- the characteristic learning part 12 learns acceleration and deceleration characteristics of the other vehicles. More specifically, the characteristic learning part 12 acquires the estimated value of state quantity of the own vehicle obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 . The position information history of the own vehicle, the relative speeds and position information histories of the other vehicles, and the like are computed from thus acquired information, and the acceleration/deceleration histories of the other vehicles are estimated from these kinds of information. Then, the maximum acceleration G in the past is held as an acceleration characteristic. When determining the acceleration characteristic, the acceleration component due to downhills is eliminated for the sake of accuracy. The maximum deceleration G in the past is held as a deceleration characteristic. When determining the deceleration characteristic, the deceleration component due to uphills is eliminated for the sake of accuracy.
- the action predicting part (action predicting means) 13 predicts actions of the other vehicles running about the own vehicle. More specifically, the action predicting part 13 acquires the estimated value of state quantity of the own vehicle obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 .
- the position information history of the own vehicle, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes).
- the action predicting part 13 also acquires information about the running road (such as increases/decreases in lanes, merging, branching, alignments, and curves) from infrastructures and the like through the navigation unit 40 and communication unit 50 .
- the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at each time (at predetermined time intervals)) of the other vehicles in future (e.g., in the range of about several hundreds of meters).
- the weight estimating part (characteristic information acquiring means) 14 estimates the weights of the other vehicles running about the own vehicle. This weight estimation detects the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles from the detected data from the millimeter-wave radar 34 and camera 32 . Subsequently, in the table shown in FIG. 2 stored in the data storage part 11 , capability information is extracted from the relevant column of size and vehicle type. Namely, the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) are extracted from the relevant column.
- an accelerated estimated weight of the other vehicle is computed by linear interpolation.
- a decelerated estimated weight of the other vehicle is computed by linear interpolation. The smaller of the accelerated estimated weight and decelerated estimated weight is taken as an estimated weight. The greater of them or their average may be taken as the estimated weight as well.
- the kinetic energy distribution setting part (risk degree estimating means and risk degree distribution setting means) 15 computes the kinetic energy (estimated weight ⁇ speed ⁇ speed) of the other vehicle at each time. This allows the kinetic energy to act as an index representing the degree of risk of the other vehicle, whereby the degree of risk can be estimated higher as the kinetic energy is higher.
- the kinetic energy distribution setting part 15 acquires road information, sets a running path memory, and adds the computed kinetic energy to the running path memory in the area occupied by the other vehicle.
- a substantially circular energy distribution attenuating the kinetic energy by using a specified attenuation coefficient (which attenuates the kinetic energy by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown in FIG. 3 , this adds the kinetic energy to the running path memory for each of other vehicles N 1 to N 4 running about the own vehicle M, thereby setting a kinetic energy distribution as a whole.
- a specified attenuation coefficient which attenuates the kinetic energy by 1% per 1 m, for example
- the kinetic energy distribution for each of the other vehicles N 1 to N 4 has such an image as to attain the highest energy in an area which is substantially the same as the outer shape occupied by the vehicle and attenuate the kinetic energy as it is distanced farther from this area.
- Such a kinetic energy distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds).
- the running plan creating part (running plan creating means) 16 creates a running plan of the own vehicle M. Namely, the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower. This will be explained later.
- the safety evaluating part 17 finally evaluates the safety of the running plan created by the running plan creating part 16 . More specifically, utilizing the information about the positions and speeds of the other vehicles N 1 to N 4 and the running plan including the position and speed of the own vehicle M created by the running plan creating part 16 , the headway and relative vehicle speed are computed at predetermined time intervals. Then, TTC (Time To Collision) is computed by dividing thus determined headway by the relative speed. As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed. When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the running plan creating part 16 corrects the running plan. Then, the safety evaluating part 17 reevaluates the safety of the corrected running plan.
- TTC Time To Collision
- a running control ECU 60 is connected to the running plan creating ECU 10 . While taking account of the estimated value of state quantity of the own vehicle M, the running control ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan.
- FIG. 4 is a schematic view showing a hardware structural example of the own vehicle M mounting the running plan creating apparatus 1 constructed as above.
- the running plan creating ECU 10 and running control ECU 60 are included in a control unit C.
- the millimeter-wave radar 34 and camera 32 acting as the perimeter sensor 30 are connected to the control unit C.
- the vehicle speed sensor 22 acting as the own vehicle sensor 20 is connected to the control unit C.
- the navigation unit 40 and communication unit 50 are connected to the control unit C.
- control unit C running plan creating ECU 10
- the control unit C controls a throttle actuator 71 and a brake actuator 72 , so as to regulate an engine 73 and brake units 74 , thereby controlling acceleration/deceleration.
- a steering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed.
- the table shown in FIG. 2 is prepared and stored in the data storage part 11 of the running plan creating ECU 10 .
- This table is one indicating the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) for each kind of vehicles (e.g., vehicle type and size) as performances of the vehicles.
- the fully loaded state is a realistic value which covers illegal overloading.
- the own vehicle sensor 20 and perimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while the data storage part 11 is assumed to store data for this period.
- the creating of the running plan begins from this state.
- the characteristic learning part 12 acquires the estimated value of state quantity of the own vehicle M obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 .
- the position information history of the own vehicle M, the relative speeds and position information histories of the other vehicles, and the like are computed from thus acquired information, and the acceleration/deceleration histories of the other vehicles are estimated from these kinds of information.
- the maximum acceleration G in the past is held as an acceleration characteristic, while the maximum deceleration G in the past is held as a deceleration characteristic.
- step S 502 road information concerning the running path is acquired from infrastructures through the navigation unit 40 and communication unit 50 (step S 502 ). Then, a running path memory (e.g., for several hundreds of meters) for setting a kinetic energy distribution which will be explained later is secured and initialized (to zero) (step S 503 ).
- a running path memory e.g., for several hundreds of meters
- actions of the other vehicles are predicted in the action predicting part 13 (step S 504 ). More specifically, the action predicting part 13 acquires the estimated value of state quantity of the own vehicle M obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 .
- the position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes).
- the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles are detected in the weight estimating part 14 from the detected data from the millimeter-wave radar 34 and camera 32 (step S 505 ).
- capability information is extracted from the relevant column of size and vehicle type. Namely, the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) are extracted from the relevant column.
- an accelerated estimated weight of the other vehicle is computed by linear interpolation.
- a decelerated estimated weight of the other vehicle is computed by linear interpolation. Then, the smaller of the accelerated estimated weight and decelerated estimated weight is taken as an estimated weight of the other vehicle (step S 506 ).
- the kinetic energy (estimated weight ⁇ speed ⁇ speed) of the other vehicle at each time is computed in the kinetic energy distribution setting part 15 .
- the kinetic energy distribution setting part 15 adds the computed kinetic energy to the running path memory in the area occupied by the other vehicle.
- a substantially circular energy distribution attenuating the kinetic energy by using a specified attenuation coefficient (which attenuates the kinetic energy by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory.
- the kinetic energy is added to the running path memory for each of other vehicles N 1 to N 4 running about the own vehicle M, whereby a kinetic energy distribution is set as a whole.
- a kinetic energy distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds) (step S 507 ).
- a running plan of the own vehicle M is created in the running plan creating part 16 (step S 508 ).
- the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower.
- the running plan creating part 16 creates such a running plan as to perform a lane change between the other vehicles N 3 , N 4 .
- a running plan including the position and speed of the own vehicle M is created so as to reduce the degree of potential risk.
- the safety of the running plan created by the running plan creating part 16 is finally evaluated in the safety evaluating part 17 (step S 509 ). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by the action predicting part 13 and the running plan including the position and speed of the own vehicle M created by the running plan creating part 16 , the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S 510 ). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the running plan creating part 16 corrects the running plan. Then, the safety evaluating part 17 reevaluates the safety of the corrected running plan.
- TTC Time To Collision
- the running control ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan, while taking account of the estimated value of state quantity of the own vehicle M. Then, the throttle actuator 71 and brake actuator 72 are controlled, so as to regulate the engine 73 and brake units 74 , thereby controlling acceleration/deceleration. Also, the steering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed.
- the running plan creating apparatus 1 in accordance with this embodiment can estimate and acquire the vehicle weight as characteristic information in each of the other vehicles running about the own vehicle M, and can estimate a kinetic energy as the degree of risk of each of the other vehicle by utilizing the vehicle weight, so as set a risk degree distribution, whereby a safer running plan can be obtained when created according to the risk degree distribution.
- a safer running plan can be obtained when created according to the risk degree distribution.
- the running plan creating apparatus 101 in accordance with this embodiment differs from the running plan creating apparatus 1 in accordance with the first embodiment in the structure of its running plan creating ECU 110 as shown in FIG. 6 .
- the running plan creating ECU 110 has a data storage part 111 , a characteristic learning part 112 , an action predicting part 113 , an unsafety degree computing part 114 , an unsafety degree distribution setting part 115 , a running plan creating part 116 , and a safety evaluating part 117 .
- the data storage part 111 stores the data detected by the own vehicle sensor 20 and perimeter sensor 30 .
- the data storage part 111 in this embodiment stores no table such as the one shown in FIG. 2 .
- the characteristic learning part 112 learns relative relationships between each of the other vehicles and its nearby vehicles. More specifically, the characteristic learning part 112 learns at least one of the desirable headway time, permissible shortest time to collision, and desirable acceleration/deceleration for the other vehicle with respect to its nearby vehicle. All of them are learned in this embodiment.
- the action predicting part (action predicting means) 113 is the same as the action predicting part 13 in the above-mentioned first embodiment.
- the unsafety degree computing part (risk degree estimating means) 114 computes the degree of unsafety D of the other vehicle.
- the degree of unsafety D of the other vehicle is represented by the following expression (1):
- a, b, and c are predetermined coefficients.
- the unsafety degree distribution setting part (risk degree distribution setting means) 115 acquires road information, sets a running path memory, and adds the computed degree of unsafety D to the running path memory in the area occupied by the other vehicle.
- a substantially circular unsafety degree distribution attenuating the degree of unsafety D by using a specified attenuation coefficient (which attenuates the degree of unsafety by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown in FIG. 7 , this adds the degree of unsafety to the running path memory for each of other vehicles running about the own vehicle, thereby setting an unsafety degree distribution as a whole.
- a specified attenuation coefficient which attenuates the degree of unsafety by 1% per 1 m, for example
- the unsafety degree distribution for each of the other vehicles N 1 to N 3 has such an image as to attain the highest energy in an area which is substantially the same as the outer shape occupied by the vehicle and attenuate the kinetic energy as it is distanced farther from this area.
- Such an unsafety degree distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds).
- the running plan creating part (running plan creating means) 116 creates a running plan of the own vehicle M. Namely, the creating of the running plan in the running plan creating part 116 is the same as that in the running plan in the running plan creating part 16 in accordance with the first embodiment except that the distribution utilized is the unsafety degree distribution.
- the safety evaluating part 117 is the same as the safety evaluating part 17 in the first embodiment.
- the own vehicle sensor 20 , perimeter sensor 30 , navigation unit 40 , communication unit 50 , and running control ECU 60 are the same as those in the first embodiment.
- the own vehicle sensor 20 and perimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while the data storage part 111 is assumed to store data for this period.
- the creating of the running plan begins from this state.
- the characteristic learning part 112 acquires the estimated value of state quantity of the own vehicle M obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 .
- the position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and acceleration/deceleration histories of the other vehicles are estimated from these kinds of information. Then, from thus obtained information, the desirable headway times, permissible shortest times to collision, and desirable accelerations/decelerations are computed and learned.
- step S 802 road information concerning the running path is acquired from infrastructures through the navigation unit 40 and communication unit 50 (step S 802 ). Then, a running path memory (e.g., for several hundreds of meters) for setting an unsafety degree distribution which will be explained later is secured and initialized (to zero) (step S 803 ).
- a running path memory e.g., for several hundreds of meters
- actions of the other vehicles are predicted in the action predicting part 113 (step S 804 ). More specifically, the action predicting part 113 acquires the estimated value of state quantity of the own vehicle M obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 . Then, the position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information.
- the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at predetermined time intervals) of the other vehicles in future (e.g., in the range of about several hundreds of meters).
- the degree of unsafety for each of the other vehicles is computed by using the above-mentioned expression (1) in the unsafety degree computing part 114 (step S 805 ).
- the unsafety degree distribution setting part thus computed degree of unsafety is added to the running path memory of the area occupied by the other vehicle. Also, a substantially circular unsafety degree distribution attenuating the degree of unsafety by using a specified attenuation coefficient (which attenuates the degree of unsafety by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown in FIG. 7 , the degree of unsafety is thus added to the running path memory for each of the other vehicles running about the own vehicle, whereby an unsafety degree distribution is set as a whole.
- Such an unsafety degree distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds) (step S 806 ).
- a running plan of the own vehicle is created in the running plan creating part 116 (step S 807 ).
- the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower.
- the running plan creating part 116 creates a running plan including the position and speed of the own vehicle M by which the own vehicle M is accelerated away from the other vehicle N 3 having the higher degree of unsafety, so as to go ahead by passing through the other vehicles N 1 , N 2 in front thereof.
- the safety of the running plan created by the running plan creating part 116 is finally evaluated in the safety evaluating part 117 (step S 808 ). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by the action predicting part 113 and the running plan including the position and speed of the own vehicle M created by the running plan creating part 116 , the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S 809 ). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the running plan creating part 116 corrects the running plan. Then, the safety evaluating part 117 reevaluates the safety of the corrected running plan.
- TTC Time To Collision
- the running control ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan, while taking account of the estimated value of state quantity of the own vehicle M. Then, the throttle actuator 71 and brake actuator 72 are controlled, so as to regulate the engine 73 and brake units 74 , thereby controlling acceleration/deceleration. Also, the steering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed.
- the running plan creating apparatus 101 in accordance with this embodiment can estimate and acquire the desirable headway time, permissible shortest time to collision, and desirable acceleration/deceleration as characteristic information in each of the other vehicles running about the own vehicle M, and can estimate a degree of unsafety as the degree of risk of each of the other vehicle by utilizing the information, so as set a risk degree distribution, whereby a safer running plan can be obtained when created according to the risk degree distribution.
- the running plan creating apparatus 201 in accordance with this embodiment differs from the running plan creating apparatus 1 in accordance with the first embodiment in the structure of its running plan creating ECU 210 as shown in FIG. 9 .
- the running plan creating ECU 210 has a data storage part 211 , an action predicting part 213 , a running condition setting part 218 , a running plan creating part 216 , a safety evaluating part 217 , a dead spot determination value distribution setting part 215 , a dead spot determination value integrating part 219 , a running condition urgency determining part 220 , a threshold selecting part 221 , and an integrated value comparing part 222 .
- the data storage part 211 stores the data detected by the own vehicle sensor 20 and perimeter sensor 30 .
- the data storage part 211 stores a table as shown in FIG. 10 . Namely, a table indicating blind spot areas for each kind (e.g., vehicle type and size) of vehicles is stored.
- the action predicting part 213 is the same as the action predicting part 13 in accordance with the above-mentioned first embodiment.
- the running condition setting part (running condition setting means) 218 sets a running condition as an action policy to be taken by the own vehicle.
- Examples of the running condition include lane changes, right and left turns, and stops.
- the running plan creating part (running plan temporarily creating means/running plan creating means) 216 temporarily creates a running plan including the position and speed of the own vehicle which achieves the set running condition.
- the safety evaluating part 217 which is the same as the safety evaluating part 17 in the first embodiment, evaluates the safety of the running plan temporarily created by the running plan creating part 216 .
- the temporary running plan is employed when determined safe.
- the running plan creating part corrects it. Then, the safety evaluating part 217 reevaluates the safety of the corrected running plan.
- the blind spot determination value distribution setting part (characteristic information acquiring means/risk degree estimating means) 215 acquires dead spot areas of the other vehicles running about the own vehicle, and provides them with predetermined determination values, thereby setting a dead spot determination value distribution for each of the other vehicles. More specifically, this blind spot determination value distribution setting detects the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles from the detected data from the millimeter-wave radar 34 and camera 32 . Subsequently, in the table shown in FIG. 10 stored in the data storage part 11 , the blind spot area is extracted from the relevant column of size and vehicle type.
- vehicle type e.g., whether it is a truck, a passenger car, or the like according to its license plate
- a predetermined determination value is provided within the extracted blind spot area.
- this part is provided with a twofold determination value.
- the determination value may be increased by a specified coefficient (e.g., 50%).
- a dead spot determination value is added to a running path memory for each of the other vehicles N 1 and N 2 running about the own vehicle M, whereby a blind spot determination value is set as a whole.
- Such a blind spot determining value distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds).
- the blind spot determination value integrating part (integrated value computing means) 219 computes an integrated value of blind spot determination value of the own vehicle in the case of running in conformity to the temporarily created running plan. Namely, utilizing the blind spot determination value distribution at each time, the blind spot determination value within the area occupied by the own vehicle is acquired and then integrated with respect to time.
- the running condition urgency determining part (urgency determining means) 220 determines the degree of urgency of the running condition set by the running condition setting part 218 .
- the urgency is determined among three stages of high, middle, and low degrees in this embodiment.
- the high degree of urgency covers necessary control such as lane changes required by reductions in the number of lanes and inevitable stops such as emergency stops.
- the middle degree of urgency covers kinds of control to be performed if possible such as control for securing higher safety, e.g., by increasing the headway.
- the low degree of urgency covers the other kinds of control that may be performed or not, such as control for improving comfort.
- the threshold selecting part (threshold selecting means) 221 selects a higher threshold as the degree of urgency is higher. Specifically, since the degree of urgency is determined among three stages, while the created running plan is employed regardless of the integrated value of blind spot determination value when the degree of urgency is high, a higher threshold is selected when the higher degree of urgency is determined between the respective cases where the degree of urgency is about middle and low, i.e., when the degree of urgency is determined “middle” than when determined “low”. For example, the threshold values are selected from 100 and 50.
- the integrated value comparing part 222 compares the integrated value of blind spot determination value with the higher threshold (e.g., 100 ). When the integrated value of blind spot determination value is not greater than this threshold, the control plan is determined safe and employed. When the integrated value of blind spot determination value exceeds this threshold, on the other hand, this control plan is determined unsafe, whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example.
- the higher threshold e.g. 100
- the integrated value comparing part 222 compares the integrated value of blind spot determination value with the lower threshold (e.g., 50 ). When the integrated value of blind spot determination value is not greater than this threshold, the control plan is determined safe and employed. When the integrated value of blind spot determination value exceeds this threshold, on the other hand, this control plan is determined unsafe, whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example.
- the lower threshold e.g. 50
- the own vehicle sensor 20 , perimeter sensor 30 , navigation unit 40 , communication unit 50 , and running control ECU 60 connected to the running plan creating ECU 10 are the same as those in the first embodiment.
- the table shown in FIG. 10 is prepared and stored in the data storage part 11 of the running plan creating ECU 10 .
- This table is one indicating the blind spot area for each kind of vehicles (e.g., vehicle type and size).
- the own vehicle sensor 20 and perimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while the data storage part 11 is assumed to store data for this period.
- the creating of the running plan begins from this state.
- road information concerning a running path is acquired from infrastructures through the navigation unit 40 and communication unit 50 (step S 1201 ).
- actions of the other vehicles are predicted in the action predicting part 213 (step S 1202 ). More specifically, the action predicting part 213 acquires the estimated value of state quantity of the own vehicle M obtained by the own vehicle sensor 20 and the other vehicle information obtained by the perimeter sensor 30 .
- the position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information.
- the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at each time (at predetermined time intervals)) of the other vehicles in future (e.g., in the range of about several hundreds of meters).
- the running condition creating part 216 temporarily creates a running plan of the own vehicle (step S 1203 ).
- a running condition as an action policy to be taken by the own vehicle is initially set in the running condition setting part 218 by utilizing the predicted actions (positions and speeds) of the other vehicles and acquired road information. Examples of the running condition include lane changes, right and left turns, and stops.
- the running plan of the own vehicle is temporarily created in the running plan creating part 216 so as to achieve the running condition.
- the safety of the running plan created by the running plan creating part 216 is evaluated in the safety evaluating part 217 (step S 1204 ). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by the action predicting part 213 and the running plan including the position and speed of the own vehicle M temporarily created by the running plan creating part 216 , the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S 1205 ). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the running plan creating part 216 corrects the running plan. Then, the safety evaluating part 217 reevaluates the safety of the corrected running plan.
- TTC Time To Collision
- a running path memory (e.g., for several hundreds of meters) for setting a blind spot determination value distribution which will be explained later is secured and initialized (to zero) (step S 1206 ).
- the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles are detected from the data obtained by the millimeter-wave radar 34 and camera 32 (step S 1207 ).
- the blind spot area is extracted from the relevant column of size and vehicle type (step S 1208 ). Then, a predetermined determination value is provided within the extracted blind spot area.
- this part is provided with a twofold determination value.
- a dead spot determination value is added to a running path memory for each of the other vehicles N 1 and N 2 running about the own vehicle M, whereby a blind spot determination value is set as a whole (step S 1209 ).
- a blind spot determining value distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds).
- the integrated value of dead spot determination value in the case of running according to the temporarily created running plan is computed in the bind spot determination value integrating part 219 (step S 1210 ). Namely, utilizing the blind spot determination value distribution at each time, the blind spot determination value within the area occupied by the own vehicle is acquired and integrated with respect to time.
- the degree of urgency of the running condition set by the running condition setting part 218 is determined in the running condition urgency determining part 220 .
- the degree of urgency is “high”, it is determined that the control is necessary or inevitable, whereby the temporarily created running plan is formally employed regardless of the blind spot determination value (step S 1212 ).
- the degree of urgency is not “high”, it is determined whether the degree of urgency is “middle” or not (step S 1213 ).
- the higher threshold e.g., 100
- this threshold and the integrated value of blind spot determination value are compared with each other in the integrated value comparing part 222 (step S 1214 ).
- the temporarily created control plan is determined safe and formally employed (step S 1212 ).
- the control plan is determined unsafe, so that the flow returns to step S 1203 , where a control plan is temporarily created again so as to evade a part interfering with a blind spot, for example.
- step S 1213 When it is determined at step S 1213 that the degree of urgency is not “middle”, the degree of urgency becomes “low” as a result.
- the lower threshold e.g., 50
- this threshold and the integrated value of blind spot determination value are compared with each other in the integrated value comparing part 222 (step S 1215 ).
- this control plan is determined safe and formally employed (step S 1216 ).
- step S 1203 When the integrated value of blind spot determination value exceeds this threshold, it is determined that the control plan is unsafe, whereby the flow shifts to step S 1203 , whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example.
- the running control ECU 60 creates an instruction value for an actuator, while taking account of the estimated value of state quantity of the own vehicle M, so as to faithfully reproduce the position and speed at each time according to the employed running plan. Then, the throttle actuator 71 and brake actuator 74 are controlled, so as to regulate the engine 73 and brake units 74 , thereby controlling acceleration/deceleration. Also, the steering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed.
- the running plan creating apparatus 201 in accordance with this embodiment can acquire, as characteristic information in each of the other vehicles running about the own vehicle, a blind spot area which becomes a blind spot for the driver of the other vehicle, and can set a blind spot determination value distribution as a degree of risk of each of the other vehicles by utilizing thus acquired blind spot area. Therefore, a running plan can be created according to the risk degree distribution such as to evade blind spots of the drivers within an available range in conformity to the degree of urgency in the running condition, whereby the risk of accidents being caused by oversight of the drivers of the other vehicles can be reduced.
- the present invention can be modified in various ways without being restricted to the above-mentioned embodiments.
- actions of the other vehicles running about the own vehicle are estimated from past histories in the above-mentioned embodiments.
- their running plans may be acquired through the communication unit 50 , and the actions may be predicted according to thus acquired running plans.
- the weight information of the other vehicles estimated in the first embodiment may be received through the communication unit 50 .
- the running plan creating apparatus in accordance with the embodiments can create a safer running plan in consideration of the degree of risk of each of the other vehicles thereabout.
Abstract
A running plan creating apparatus for creating a running plan including position information of a vehicle at each time comprises road information acquiring means for acquiring road information concerning a running path for the vehicle to run, action predicting means for predicting positions and speeds of other vehicles running about the vehicle at each time by utilizing the road information, characteristic information acquiring means for acquiring characteristic information in each of the other vehicles, risk degree estimating means for estimating respective degrees of risk of the other vehicles by utilizing the characteristic information, risk degree distribution setting means for setting a risk degree distribution at each time on the running path by utilizing the road information and the positions and degrees of risk of the other vehicles, and running plan creating means for creating the running plan of the vehicle by utilizing the risk degree distribution.
Description
- 1. Field of the Invention
- The present invention relates to a running plan creating apparatus which creates a safer running plan of a running vehicle by estimating the degree of risk of another vehicle thereabout.
- 2. Related Background Art
- Concerning the own vehicle and obstacles on a road, an apparatus has been known which predicts positions from the present to T seconds thereafter, computes respective degrees of risk at the positions on the road, creates the risk-minimized running track where the sum of degrees of risk along the running path is minimized as the running path of the own vehicle, and presents it to the driver (e.g., Japanese Patent Application Laid-Open No. 2006-154967). This apparatus sets areas occupied by the obstacles and blind spot areas formed by the obstacles as locations with a degree of risk.
- The above-mentioned conventional apparatus provides the areas occupied by the obstacles and blind spot areas formed by the obstacles with only a fixed degree of risk corresponding to the reliability of detection, but does not take account of respective kinetic energies, unstableness in running, blind spot areas, and the like of the other vehicles thereabout, thus failing to calculate the respective degrees of risk of the other vehicles. Therefore, thus created risk-minimized running track does not always yield high safety.
- In view of circumstances mentioned above, it is an object of the present invention to provide a running plan creating apparatus which can create a safer running plan in consideration of the degree of risk of each of the other vehicles thereabout.
- The running plan creating apparatus in accordance with the present invention is a running plan creating apparatus for creating a running plan including position information of a vehicle at each time, the apparatus comprising road information acquiring means for acquiring road information concerning a running path for the vehicle to run, action predicting means for predicting positions and speeds of other vehicles running about the vehicle at each time by utilizing the road information, characteristic information acquiring means for acquiring characteristic information in each of the other vehicles, risk degree estimating means for estimating respective degrees of risk of the other vehicles by utilizing the characteristic information, risk degree distribution setting means for setting a risk degree distribution at each time on the running path by utilizing the road information and the positions and degrees of risk of the other vehicles, and running plan creating means for creating the running plan of the vehicle by utilizing the risk degree distribution.
- This running plan creating apparatus can acquire characteristic information in each of other vehicles running about the vehicle and estimate the degree of risk of each of the other vehicles by utilizing this information, so as to set a risk degree distribution. Therefore, a safer running plan can be obtained when created according to the risk degree distribution.
- The characteristic information acquiring means may acquire a weight of the other vehicle as the characteristic information, while the risk degree estimating means may estimate the degree of risk to be higher as a kinetic energy based on the weight and speed of the other vehicle is higher. Since the damage at the time of a collision becomes greater as the vehicle has a higher kinetic energy, thus estimating the degree of risk to be higher as the kinetic energy is higher can create a running plan which evades running near such a vehicle, whereby potential risks can be reduced.
- The characteristic information acquiring means may acquire a relative relationship between the other vehicle and a vehicle thereabout as the characteristic information. This allows the degree of risk to be estimated according to what characteristic the other vehicle has in terms of the relationship to the vehicle thereabout.
- The characteristic information may include at least a desirable headway time or time to collision of the other vehicle with respect to a vehicle thereabout, while the risk degree estimating means may estimate the degree of risk to be higher as the desirable headway time or time to collision is shorter. Since a vehicle more likely to approach a vehicle thereabout has a higher possibility of coming into contact therewith, creating such a running plan as to evade running near such a vehicle can lower potential risks.
- The characteristic information acquiring means may acquire a blind spot to become a blind spot for the driver of the other vehicle as the characteristic information, while the risk degree estimating means may estimate the degree of risk of each of the other vehicles by providing the blind spot area with a predetermined value. This can create such a running plan as to evade the blind spot for the driver of the other vehicle, so as to reduce the risk of accidents being caused by oversight of the drivers of the other vehicles.
- Preferably, the running plan creating apparatus further comprises running condition setting means for setting a running condition of the vehicle, running plan temporarily creating means for temporarily creating a running plan of the vehicle achieving the running condition, integrated value computing means for computing an integrated value of degree of risk of the vehicle running according to the temporarily created running plan by utilizing the risk degree distribution, and urgency degree determining means for determining a degree of urgency of the running condition, while the running plan creating means creates such a running plan as to reduce the integrated value of degree of risk according to the degree of urgency. This can create a running plan whose degree of risk is lowered according to the degree of urgency of the running condition, e.g., whether it is essential or desirable.
- Preferably, the running plan creating apparatus further comprises threshold selecting means for selecting a higher threshold as the degree of urgency is higher, while the running plan creating means creates such a running plan as to reduce the integrated value of the degree of risk when the integrated value exceeds the threshold. This can create such a running plan as to give a higher priority to the running condition as the degree of urgency is higher.
-
FIG. 1 is a block diagram showing the structure of the running plan creating apparatus in accordance with a first embodiment; -
FIG. 2 is a table showing the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) for each kind of vehicles (vehicle type and size); -
FIG. 3 is a view showing a kinetic energy distribution; -
FIG. 4 is a schematic view showing a hardware structural example of a vehicle mounting the running plan creating apparatus ofFIG. 1 ; -
FIG. 5 is a flowchart showing the running plan creating method in accordance with the first embodiment; -
FIG. 6 is a block diagram showing the structure of the running plan creating apparatus in accordance with a second embodiment; -
FIG. 7 is a view showing an unsafety degree distribution; -
FIG. 8 is a flowchart showing the running plan creating method in accordance with the second embodiment; -
FIG. 9 is a block diagram showing the structure of the running plan creating apparatus in accordance with a third embodiment; -
FIG. 10 is a table showing a blind spot area for each kind of vehicles (vehicle type and size); -
FIG. 11 is a view showing a blind spot determination value distribution; and -
FIG. 12 is a flowchart showing the running plan creating method in accordance with the third embodiment. - In the following, embodiments of the present invention will be explained in detail with reference to the accompanying drawings. In the explanation of the drawings, the same constituents will be referred to with the same numerals or letters while omitting their overlapping descriptions.
-
FIG. 1 is a block diagram showing the structure of the running plan creating apparatus in accordance with the first embodiment. As shown inFIG. 1 , the running plan creating apparatus 1 comprises a running plan creating ECU (Electric Control Unit) 10 constructed by utilizing hardware such as a CPU (central processing unit), a memory, and the like and software, while being mounted to a vehicle (hereinafter also referred to as own vehicle) to be controlled which is under automatic driving control. - Connected to the running plan creating ECU 10 are an
own vehicle sensor 20, aperimeter sensor 30, anavigation unit 40, and acommunication unit 50 which are mounted to the own vehicle. - The
own vehicle sensor 20 is a sensor for detecting the own vehicle state quantity, e.g., a vehicle speed sensor 22, acceleration sensor, yaw rate sensor, or steering angle sensor. The value detected by theown vehicle sensor 20 is used for computing an estimated value of state quantity of the own vehicle (e.g., vehicle speed, acceleration, yaw rate, or steering angle) at present from a vehicle model built in as software within theECU 10. - The
perimeter sensor 30 is a sensor for monitoring thereabout, such as acamera 32 or millimeter-wave radar 34. The value detected by theperimeter sensor 30 is used for recognizing other vehicles running about the own vehicle and compute other vehicle information such as relative distances, angles, and speeds with respect to the own vehicle. - The navigation unit (road information acquiring means) 40 is a device which guides the driver of the own vehicle in running. The
navigation unit 40 has aposition detecting part 42 and a map information database (DB) 44. Theposition detecting part 42 detects the position (positional coordinates) of the own vehicle by receiving a signal from a GPS satellite. The map information DB 44 stores road information such as road forms and road attributes. This can display the current position of the own vehicle on a map and guide the vehicle in running to a destination. - The
communication unit 50 sends and receives information through road-vehicle communication and inter-vehicle communication. For example, in collaboration with infrastructures, thecommunication unit 50 acquires information about the road to run (road information acquiring means). The road information may be acquired from one or both of the above-mentionednavigation unit 40 andcommunication unit 50. - The running plan creating ECU 10 has a
data storage part 11, acharacteristic learning part 12, anaction predicting part 13, aweight estimating part 14, a kinetic energydistribution setting part 15, a runningplan creating part 16, and asafety evaluating part 17. - For a predetermined period in the past, the
data storage part 11 stores the data detected by theown vehicle sensor 20 andperimeter sensor 30. Also, thedata storage part 11 stores a table which indicates the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) for each kind of vehicles (e.g., vehicle type and size) as performances of the vehicles as shown inFIG. 2 . - As characteristics of the other vehicles running about the own vehicle, the
characteristic learning part 12 learns acceleration and deceleration characteristics of the other vehicles. More specifically, thecharacteristic learning part 12 acquires the estimated value of state quantity of the own vehicle obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle, the relative speeds and position information histories of the other vehicles, and the like are computed from thus acquired information, and the acceleration/deceleration histories of the other vehicles are estimated from these kinds of information. Then, the maximum acceleration G in the past is held as an acceleration characteristic. When determining the acceleration characteristic, the acceleration component due to downhills is eliminated for the sake of accuracy. The maximum deceleration G in the past is held as a deceleration characteristic. When determining the deceleration characteristic, the deceleration component due to uphills is eliminated for the sake of accuracy. - The action predicting part (action predicting means) 13 predicts actions of the other vehicles running about the own vehicle. More specifically, the
action predicting part 13 acquires the estimated value of state quantity of the own vehicle obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes). Theaction predicting part 13 also acquires information about the running road (such as increases/decreases in lanes, merging, branching, alignments, and curves) from infrastructures and the like through thenavigation unit 40 andcommunication unit 50. According to the position information histories and current states of the other vehicle and the road information, the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at each time (at predetermined time intervals)) of the other vehicles in future (e.g., in the range of about several hundreds of meters). - The weight estimating part (characteristic information acquiring means) 14 estimates the weights of the other vehicles running about the own vehicle. This weight estimation detects the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles from the detected data from the millimeter-
wave radar 34 andcamera 32. Subsequently, in the table shown inFIG. 2 stored in thedata storage part 11, capability information is extracted from the relevant column of size and vehicle type. Namely, the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) are extracted from the relevant column. Then, utilizing the maximum acceleration G learned in thecharacteristic learning part 12 and the extracted maximum acceleration capabilities G (in unloaded and fully loaded states), an accelerated estimated weight of the other vehicle is computed by linear interpolation. Also, utilizing the maximum deceleration G learned in thecharacteristic learning part 12 and the extracted maximum deceleration capabilities G (in unloaded and fully loaded states), a decelerated estimated weight of the other vehicle is computed by linear interpolation. The smaller of the accelerated estimated weight and decelerated estimated weight is taken as an estimated weight. The greater of them or their average may be taken as the estimated weight as well. - Utilizing the speed of the other vehicle predicted by the
action predicting part 13 and the estimated weight obtained by theweight estimating part 14, the kinetic energy distribution setting part (risk degree estimating means and risk degree distribution setting means) 15 computes the kinetic energy (estimated weight×speed×speed) of the other vehicle at each time. This allows the kinetic energy to act as an index representing the degree of risk of the other vehicle, whereby the degree of risk can be estimated higher as the kinetic energy is higher. - Also, the kinetic energy
distribution setting part 15 acquires road information, sets a running path memory, and adds the computed kinetic energy to the running path memory in the area occupied by the other vehicle. A substantially circular energy distribution attenuating the kinetic energy by using a specified attenuation coefficient (which attenuates the kinetic energy by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown inFIG. 3 , this adds the kinetic energy to the running path memory for each of other vehicles N1 to N4 running about the own vehicle M, thereby setting a kinetic energy distribution as a whole. InFIG. 3 , the kinetic energy distribution for each of the other vehicles N1 to N4 has such an image as to attain the highest energy in an area which is substantially the same as the outer shape occupied by the vehicle and attenuate the kinetic energy as it is distanced farther from this area. Such a kinetic energy distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds). - Utilizing thus set kinetic energy distribution, i.e., risk degree distribution, the running plan creating part (running plan creating means) 16 creates a running plan of the own vehicle M. Namely, the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower. This will be explained later.
- The
safety evaluating part 17 finally evaluates the safety of the running plan created by the runningplan creating part 16. More specifically, utilizing the information about the positions and speeds of the other vehicles N1 to N4 and the running plan including the position and speed of the own vehicle M created by the runningplan creating part 16, the headway and relative vehicle speed are computed at predetermined time intervals. Then, TTC (Time To Collision) is computed by dividing thus determined headway by the relative speed. As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed. When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the runningplan creating part 16 corrects the running plan. Then, thesafety evaluating part 17 reevaluates the safety of the corrected running plan. - A running
control ECU 60 is connected to the runningplan creating ECU 10. While taking account of the estimated value of state quantity of the own vehicle M, the runningcontrol ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan. -
FIG. 4 is a schematic view showing a hardware structural example of the own vehicle M mounting the running plan creating apparatus 1 constructed as above. The runningplan creating ECU 10 and runningcontrol ECU 60 are included in a control unit C. The millimeter-wave radar 34 andcamera 32 acting as theperimeter sensor 30 are connected to the control unit C. Also, the vehicle speed sensor 22 acting as theown vehicle sensor 20 is connected to the control unit C. Further, thenavigation unit 40 andcommunication unit 50 are connected to the control unit C. - When a running plan is created in the control unit C (running plan creating ECU 10), the control unit C (running control ECU 60) controls a
throttle actuator 71 and abrake actuator 72, so as to regulate anengine 73 andbrake units 74, thereby controlling acceleration/deceleration. Also, asteering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed. - A running plan creating method by the above-mentioned running plan creating apparatus 1 will now be explained with reference to the flowchart of
FIG. 5 . - To begin with, as a basis for the control, the table shown in
FIG. 2 is prepared and stored in thedata storage part 11 of the runningplan creating ECU 10. This table is one indicating the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) for each kind of vehicles (e.g., vehicle type and size) as performances of the vehicles. Preferably, the fully loaded state is a realistic value which covers illegal overloading. - The
own vehicle sensor 20 andperimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while thedata storage part 11 is assumed to store data for this period. The creating of the running plan begins from this state. - First, as characteristics of the other vehicles running about the own vehicle M, the acceleration and deceleration characteristics of the other vehicles are learned in the characteristic learning part 12 (step S501). More specifically, the
characteristic learning part 12 acquires the estimated value of state quantity of the own vehicle M obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle M, the relative speeds and position information histories of the other vehicles, and the like are computed from thus acquired information, and the acceleration/deceleration histories of the other vehicles are estimated from these kinds of information. Then, the maximum acceleration G in the past is held as an acceleration characteristic, while the maximum deceleration G in the past is held as a deceleration characteristic. - Next, road information concerning the running path is acquired from infrastructures through the
navigation unit 40 and communication unit 50 (step S502). Then, a running path memory (e.g., for several hundreds of meters) for setting a kinetic energy distribution which will be explained later is secured and initialized (to zero) (step S503). - Next, actions of the other vehicles are predicted in the action predicting part 13 (step S504). More specifically, the
action predicting part 13 acquires the estimated value of state quantity of the own vehicle M obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes). According to the position information histories and current states of the other vehicle and the acquired road information, the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at each time (at predetermined time intervals)) of the other vehicles in future (e.g., in the range of about several hundreds of meters). - Next, the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles are detected in the
weight estimating part 14 from the detected data from the millimeter-wave radar 34 and camera 32 (step S505). Subsequently, in the table shown inFIG. 2 stored in thedata storage part 11, capability information is extracted from the relevant column of size and vehicle type. Namely, the maximum acceleration capabilities G (in unloaded and fully loaded states) and maximum deceleration capabilities G (in unloaded and fully loaded states) are extracted from the relevant column. Then, utilizing the maximum acceleration G learned in thecharacteristic learning part 12 and the extracted maximum acceleration capabilities G (in unloaded and fully loaded states), an accelerated estimated weight of the other vehicle is computed by linear interpolation. Also, utilizing the maximum deceleration G learned in thecharacteristic learning part 12 and the extracted maximum deceleration capabilities G (in unloaded and fully loaded states), a decelerated estimated weight of the other vehicle is computed by linear interpolation. Then, the smaller of the accelerated estimated weight and decelerated estimated weight is taken as an estimated weight of the other vehicle (step S506). - Utilizing the speed of the other vehicle predicted by the
action predicting part 13 and the estimated weight obtained by theweight estimating part 14, the kinetic energy (estimated weight×speed×speed) of the other vehicle at each time is computed in the kinetic energydistribution setting part 15. Then, the kinetic energydistribution setting part 15 adds the computed kinetic energy to the running path memory in the area occupied by the other vehicle. A substantially circular energy distribution attenuating the kinetic energy by using a specified attenuation coefficient (which attenuates the kinetic energy by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. Thus, as shown inFIG. 3 , the kinetic energy is added to the running path memory for each of other vehicles N1 to N4 running about the own vehicle M, whereby a kinetic energy distribution is set as a whole. Such a kinetic energy distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds) (step S507). - Using thus set kinetic energy distribution, i.e., risk degree distribution, a running plan of the own vehicle M is created in the running plan creating part 16 (step S508). Namely, the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower. When the own vehicle M runs in the center lane as shown in
FIG. 3 , for example, it is seemingly safe. Since the other vehicles N1, N2 with high kinetic energies run in the left lane of the own vehicle M, however, the energy distributions of the other vehicles N1, N2 overlap the area occupied by the own vehicle M. On the other hand, while the headway between the other vehicles N3, N4 running in the right lane of the own vehicle M is short, their kinetic energies are low, whereby the degree of risk between the other vehicles N3, N4 is the lowest. Therefore, the runningplan creating part 16 creates such a running plan as to perform a lane change between the other vehicles N3, N4. Thus, with reference to the kinetic energy distribution, a running plan including the position and speed of the own vehicle M is created so as to reduce the degree of potential risk. - Next, the safety of the running plan created by the running
plan creating part 16 is finally evaluated in the safety evaluating part 17 (step S509). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by theaction predicting part 13 and the running plan including the position and speed of the own vehicle M created by the runningplan creating part 16, the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S510). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the runningplan creating part 16 corrects the running plan. Then, thesafety evaluating part 17 reevaluates the safety of the corrected running plan. - When the running plan is thus employed, the running
control ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan, while taking account of the estimated value of state quantity of the own vehicle M. Then, thethrottle actuator 71 andbrake actuator 72 are controlled, so as to regulate theengine 73 andbrake units 74, thereby controlling acceleration/deceleration. Also, thesteering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed. - As in the foregoing, the running plan creating apparatus 1 in accordance with this embodiment can estimate and acquire the vehicle weight as characteristic information in each of the other vehicles running about the own vehicle M, and can estimate a kinetic energy as the degree of risk of each of the other vehicle by utilizing the vehicle weight, so as set a risk degree distribution, whereby a safer running plan can be obtained when created according to the risk degree distribution. Namely, since the damage at the time of a collision becomes greater as the vehicle has a higher kinetic energy, thus estimating the degree of risk to be higher as the kinetic energy is higher can create a running plan which evades running near such a vehicle, whereby potential risks can be reduced.
- The running plan creating apparatus in accordance with the second embodiment will now be explained. The same constituents as those of the above-mentioned embodiment will be referred to with the same numerals or letters while omitting their overlapping descriptions.
- The running
plan creating apparatus 101 in accordance with this embodiment differs from the running plan creating apparatus 1 in accordance with the first embodiment in the structure of its runningplan creating ECU 110 as shown inFIG. 6 . The runningplan creating ECU 110 has adata storage part 111, acharacteristic learning part 112, anaction predicting part 113, an unsafetydegree computing part 114, an unsafety degreedistribution setting part 115, a runningplan creating part 116, and asafety evaluating part 117. - For a predetermined period in the past, the
data storage part 111 stores the data detected by theown vehicle sensor 20 andperimeter sensor 30. Thedata storage part 111 in this embodiment stores no table such as the one shown inFIG. 2 . - As characteristics of the other vehicles running about the own vehicle, the characteristic learning part (characteristic information acquiring means) 112 learns relative relationships between each of the other vehicles and its nearby vehicles. More specifically, the
characteristic learning part 112 learns at least one of the desirable headway time, permissible shortest time to collision, and desirable acceleration/deceleration for the other vehicle with respect to its nearby vehicle. All of them are learned in this embodiment. - The action predicting part (action predicting means) 113 is the same as the
action predicting part 13 in the above-mentioned first embodiment. - Utilizing the desirable headway time A, permissible shortest time to collision (TTC) B, and desirable acceleration/deceleration C of the other vehicle with respect to its nearby vehicle learned by the
characteristic learning part 112, the unsafety degree computing part (risk degree estimating means) 114 computes the degree of unsafety D of the other vehicle. Specifically, the degree of unsafety D of the other vehicle is represented by the following expression (1): -
D=a/A+b/B+c·C (1) - where a, b, and c are predetermined coefficients. When the degree of unsafety D of the other vehicle is thus set as an index of the degree of risk, the degree of risk is estimated higher as desirable headway time A and time to collision B are shorter because the headway is short. The degree of risk is also estimated higher as the desirable acceleration/deceleration C is higher because the driving is rough.
- The unsafety degree distribution setting part (risk degree distribution setting means) 115 acquires road information, sets a running path memory, and adds the computed degree of unsafety D to the running path memory in the area occupied by the other vehicle. A substantially circular unsafety degree distribution attenuating the degree of unsafety D by using a specified attenuation coefficient (which attenuates the degree of unsafety by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown in
FIG. 7 , this adds the degree of unsafety to the running path memory for each of other vehicles running about the own vehicle, thereby setting an unsafety degree distribution as a whole. InFIG. 7 , the unsafety degree distribution for each of the other vehicles N1 to N3 has such an image as to attain the highest energy in an area which is substantially the same as the outer shape occupied by the vehicle and attenuate the kinetic energy as it is distanced farther from this area. Such an unsafety degree distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds). - Utilizing thus set unsafety degree distribution, i.e., risk degree distribution, the running plan creating part (running plan creating means) 116 creates a running plan of the own vehicle M. Namely, the creating of the running plan in the running
plan creating part 116 is the same as that in the running plan in the runningplan creating part 16 in accordance with the first embodiment except that the distribution utilized is the unsafety degree distribution. - The
safety evaluating part 117 is the same as thesafety evaluating part 17 in the first embodiment. Theown vehicle sensor 20,perimeter sensor 30,navigation unit 40,communication unit 50, and runningcontrol ECU 60 are the same as those in the first embodiment. - A running plan creating method using the above-mentioned running
plan creating apparatus 101 will now be explained with reference to the flowchart ofFIG. 8 . - The
own vehicle sensor 20 andperimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while thedata storage part 111 is assumed to store data for this period. The creating of the running plan begins from this state. - First, as characteristics of the other vehicles running about the own vehicle M, the desirable headway times, permissible shortest times to collision, and desirable accelerations/decelerations of the other vehicles with respect to their nearby vehicles are learned in the characteristic learning part 112 (step S801). More specifically, from the
data storage part 111, thecharacteristic learning part 112 acquires the estimated value of state quantity of the own vehicle M obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and acceleration/deceleration histories of the other vehicles are estimated from these kinds of information. Then, from thus obtained information, the desirable headway times, permissible shortest times to collision, and desirable accelerations/decelerations are computed and learned. - Next, road information concerning the running path is acquired from infrastructures through the
navigation unit 40 and communication unit 50 (step S802). Then, a running path memory (e.g., for several hundreds of meters) for setting an unsafety degree distribution which will be explained later is secured and initialized (to zero) (step S803). - Next, actions of the other vehicles are predicted in the action predicting part 113 (step S804). More specifically, the
action predicting part 113 acquires the estimated value of state quantity of the own vehicle M obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. Then, the position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes). According to the position information histories and current states of the other vehicle and the acquired road information, the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at predetermined time intervals) of the other vehicles in future (e.g., in the range of about several hundreds of meters). - Subsequently, utilizing the desirable headway times, permissible shortest times to collision, and desirable acceleration/deceleration learned in the
characteristic learning part 112, the degree of unsafety for each of the other vehicles is computed by using the above-mentioned expression (1) in the unsafety degree computing part 114 (step S805). - Next, in the unsafety degree distribution setting part, thus computed degree of unsafety is added to the running path memory of the area occupied by the other vehicle. Also, a substantially circular unsafety degree distribution attenuating the degree of unsafety by using a specified attenuation coefficient (which attenuates the degree of unsafety by 1% per 1 m, for example) about the area occupied by the other vehicle is added to the running path memory. As shown in
FIG. 7 , the degree of unsafety is thus added to the running path memory for each of the other vehicles running about the own vehicle, whereby an unsafety degree distribution is set as a whole. Such an unsafety degree distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds) (step S806). - Subsequently, utilizing thus set unsafety degree distribution, i.e., risk degree distribution, a running plan of the own vehicle is created in the running plan creating part 116 (step S807). Namely, the running plan including the position and speed of the own vehicle M is created so as to make the degree of risk lower. When the own vehicle M runs in the center lane as shown in
FIG. 7 , for example, it is seemingly safe. Since the other vehicle N3 with a higher degree of unsafety runs in the right lane in the rear of the own vehicle M, however, the unsafety degree distribution of the other vehicle N3 overlaps the area occupied by the own vehicle M. On the other hand, while the other vehicles N1, N2 in the right and left lanes in front of the vehicle run in parallel, their degrees of unsafety are low, so that the degree of unsafety between the other vehicles N1, N2 is the lowest. Therefore, the runningplan creating part 116 creates a running plan including the position and speed of the own vehicle M by which the own vehicle M is accelerated away from the other vehicle N3 having the higher degree of unsafety, so as to go ahead by passing through the other vehicles N1, N2 in front thereof. - Next, the safety of the running plan created by the running
plan creating part 116 is finally evaluated in the safety evaluating part 117 (step S808). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by theaction predicting part 113 and the running plan including the position and speed of the own vehicle M created by the runningplan creating part 116, the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S809). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the runningplan creating part 116 corrects the running plan. Then, thesafety evaluating part 117 reevaluates the safety of the corrected running plan. - When the running plan is thus employed, the running
control ECU 60 creates an instruction value for an actuator so as to faithfully reproduce the position and speed at each time according to the employed running plan, while taking account of the estimated value of state quantity of the own vehicle M. Then, thethrottle actuator 71 andbrake actuator 72 are controlled, so as to regulate theengine 73 andbrake units 74, thereby controlling acceleration/deceleration. Also, thesteering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed. - As in the foregoing, the running
plan creating apparatus 101 in accordance with this embodiment can estimate and acquire the desirable headway time, permissible shortest time to collision, and desirable acceleration/deceleration as characteristic information in each of the other vehicles running about the own vehicle M, and can estimate a degree of unsafety as the degree of risk of each of the other vehicle by utilizing the information, so as set a risk degree distribution, whereby a safer running plan can be obtained when created according to the risk degree distribution. Namely, since the other vehicle is more likely to approach and come into contact with its nearby vehicle as its desirable headway time and time to collision are shorter, while the driving becomes rougher so as to yield a higher risk of contact as the desirable acceleration/deceleration is greater, whereby the degree of unsafety is estimated higher in such a case. Since a vehicle having a higher degree of unsafety yields a higher degree of potential risk, creating such a running plan as to evade running near such a vehicle can reduce potential risks. - The running plan creating apparatus in accordance with the third embodiment will now be explained. The same constituents as those of the above-mentioned embodiments will be referred to with the same numerals or letters while omitting their overlapping descriptions.
- The running
plan creating apparatus 201 in accordance with this embodiment differs from the running plan creating apparatus 1 in accordance with the first embodiment in the structure of its runningplan creating ECU 210 as shown inFIG. 9 . The runningplan creating ECU 210 has adata storage part 211, anaction predicting part 213, a runningcondition setting part 218, a runningplan creating part 216, asafety evaluating part 217, a dead spot determination valuedistribution setting part 215, a dead spot determinationvalue integrating part 219, a running conditionurgency determining part 220, athreshold selecting part 221, and an integratedvalue comparing part 222. - For a predetermined period in the past, the
data storage part 211 stores the data detected by theown vehicle sensor 20 andperimeter sensor 30. Thedata storage part 211 stores a table as shown inFIG. 10 . Namely, a table indicating blind spot areas for each kind (e.g., vehicle type and size) of vehicles is stored. - The
action predicting part 213 is the same as theaction predicting part 13 in accordance with the above-mentioned first embodiment. - According to the actions (positions and speeds) of other vehicles predicted by the
action predicting part 213 and road information, the running condition setting part (running condition setting means) 218 sets a running condition as an action policy to be taken by the own vehicle. Examples of the running condition include lane changes, right and left turns, and stops. - The running plan creating part (running plan temporarily creating means/running plan creating means) 216 temporarily creates a running plan including the position and speed of the own vehicle which achieves the set running condition.
- The
safety evaluating part 217, which is the same as thesafety evaluating part 17 in the first embodiment, evaluates the safety of the running plan temporarily created by the runningplan creating part 216. The temporary running plan is employed when determined safe. When the temporary running plan is determined unsafe, the running plan creating part corrects it. Then, thesafety evaluating part 217 reevaluates the safety of the corrected running plan. - The blind spot determination value distribution setting part (characteristic information acquiring means/risk degree estimating means) 215 acquires dead spot areas of the other vehicles running about the own vehicle, and provides them with predetermined determination values, thereby setting a dead spot determination value distribution for each of the other vehicles. More specifically, this blind spot determination value distribution setting detects the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles from the detected data from the millimeter-
wave radar 34 andcamera 32. Subsequently, in the table shown inFIG. 10 stored in thedata storage part 11, the blind spot area is extracted from the relevant column of size and vehicle type. - A predetermined determination value is provided within the extracted blind spot area. When the dead spots of two other vehicles overlap each other, for example, this part is provided with a twofold determination value. When the other vehicle has been known to be a vehicle mounting a perimeter monitoring sensor, the probability of wrong operations by the driver of the other vehicle being prevented by an alarm and the like becomes higher, whereby the determination value may be increased by a specified coefficient (e.g., 50%). Thus, as shown in
FIG. 11 , a dead spot determination value is added to a running path memory for each of the other vehicles N1 and N2 running about the own vehicle M, whereby a blind spot determination value is set as a whole. Such a blind spot determining value distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds). - Utilizing the blind spot determined value distribution as a risk degree distribution, the blind spot determination value integrating part (integrated value computing means) 219 computes an integrated value of blind spot determination value of the own vehicle in the case of running in conformity to the temporarily created running plan. Namely, utilizing the blind spot determination value distribution at each time, the blind spot determination value within the area occupied by the own vehicle is acquired and then integrated with respect to time.
- The running condition urgency determining part (urgency determining means) 220 determines the degree of urgency of the running condition set by the running
condition setting part 218. The urgency is determined among three stages of high, middle, and low degrees in this embodiment. The high degree of urgency covers necessary control such as lane changes required by reductions in the number of lanes and inevitable stops such as emergency stops. The middle degree of urgency covers kinds of control to be performed if possible such as control for securing higher safety, e.g., by increasing the headway. The low degree of urgency covers the other kinds of control that may be performed or not, such as control for improving comfort. - As a threshold to be compared with the integrated value of blind spot determination value, the threshold selecting part (threshold selecting means) 221 selects a higher threshold as the degree of urgency is higher. Specifically, since the degree of urgency is determined among three stages, while the created running plan is employed regardless of the integrated value of blind spot determination value when the degree of urgency is high, a higher threshold is selected when the higher degree of urgency is determined between the respective cases where the degree of urgency is about middle and low, i.e., when the degree of urgency is determined “middle” than when determined “low”. For example, the threshold values are selected from 100 and 50.
- When the degree of urgency is determined “middle”, the integrated
value comparing part 222 compares the integrated value of blind spot determination value with the higher threshold (e.g., 100). When the integrated value of blind spot determination value is not greater than this threshold, the control plan is determined safe and employed. When the integrated value of blind spot determination value exceeds this threshold, on the other hand, this control plan is determined unsafe, whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example. - When the degree of urgency is determined “low”, the integrated
value comparing part 222 compares the integrated value of blind spot determination value with the lower threshold (e.g., 50). When the integrated value of blind spot determination value is not greater than this threshold, the control plan is determined safe and employed. When the integrated value of blind spot determination value exceeds this threshold, on the other hand, this control plan is determined unsafe, whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example. - The
own vehicle sensor 20,perimeter sensor 30,navigation unit 40,communication unit 50, and runningcontrol ECU 60 connected to the runningplan creating ECU 10 are the same as those in the first embodiment. - A running plan creating method using the above-mentioned running
plan creating apparatus 201 will now be explained with reference to the flowchart ofFIG. 12 . - To begin with, as a basis for the control, the table shown in
FIG. 10 is prepared and stored in thedata storage part 11 of the runningplan creating ECU 10. This table is one indicating the blind spot area for each kind of vehicles (e.g., vehicle type and size). - The
own vehicle sensor 20 andperimeter sensor 30 are supposed to have started acquiring data from a time earlier by a predetermined period than the present, while thedata storage part 11 is assumed to store data for this period. The creating of the running plan begins from this state. - First, road information concerning a running path is acquired from infrastructures through the
navigation unit 40 and communication unit 50 (step S1201). - Next, actions of the other vehicles are predicted in the action predicting part 213 (step S1202). More specifically, the
action predicting part 213 acquires the estimated value of state quantity of the own vehicle M obtained by theown vehicle sensor 20 and the other vehicle information obtained by theperimeter sensor 30. The position information history of the own vehicle M, the relative position information histories and relative speeds of the other vehicles, and the like are computed from thus acquired information, and the position information histories and current states (speeds, accelerations, yaw angles with respect to road alignments, etc.) of the other vehicles are estimated from these kinds of information. This makes it possible to estimate the positional relationship between the other vehicles and tendencies of the other vehicles (drivers' likings such as headway, vehicle speed, acceleration/deceleration, and resistance to lane changes). According to the position information histories and current states of the other vehicle and the acquired road information, the tendencies of the other vehicles are put into a driver model which has been created beforehand, so as to predict actions (position, speed, and the like at each time (at predetermined time intervals)) of the other vehicles in future (e.g., in the range of about several hundreds of meters). - Subsequently, with reference to the actions (positions and speeds) of the other vehicles predicted by the
action predicting part 213, the runningcondition creating part 216 temporarily creates a running plan of the own vehicle (step S1203). When temporarily creating the running plan, a running condition as an action policy to be taken by the own vehicle is initially set in the runningcondition setting part 218 by utilizing the predicted actions (positions and speeds) of the other vehicles and acquired road information. Examples of the running condition include lane changes, right and left turns, and stops. The running plan of the own vehicle is temporarily created in the runningplan creating part 216 so as to achieve the running condition. - Next, the safety of the running plan created by the running
plan creating part 216 is evaluated in the safety evaluating part 217 (step S1204). More specifically, utilizing the information about the positions and speeds of the other vehicles predicted by theaction predicting part 213 and the running plan including the position and speed of the own vehicle M temporarily created by the runningplan creating part 216, the headway and relative vehicle speed are computed at predetermined time intervals. Thus determined headway is divided by the relative speed, so as to compute the TTC (Time To Collision). As a consequence, the safety of the running plan is evaluated according to whether the TTC is greater than a safety reference value or not. When the TTC exceeds the safety reference value, the running plan is evaluated as safe and employed (step S1205). When the TTC is lower than the safety reference value, so that the running plan is evaluated unsafe, the runningplan creating part 216 corrects the running plan. Then, thesafety evaluating part 217 reevaluates the safety of the corrected running plan. - Subsequently, a running path memory (e.g., for several hundreds of meters) for setting a blind spot determination value distribution which will be explained later is secured and initialized (to zero) (step S1206).
- Next, in the blind spot determination
value setting part 215, the size (length and width) and vehicle type (e.g., whether it is a truck, a passenger car, or the like according to its license plate) of each of the other vehicles are detected from the data obtained by the millimeter-wave radar 34 and camera 32 (step S1207). Subsequently, in the table shown inFIG. 10 stored in thedata storage part 211, the blind spot area is extracted from the relevant column of size and vehicle type (step S1208). Then, a predetermined determination value is provided within the extracted blind spot area. When the dead spots of two other vehicles overlap each other, for example, this part is provided with a twofold determination value. When the other vehicle has been known to be a vehicle mounting a perimeter monitoring sensor, the probability of wrong operations by the driver of the other vehicle being prevented by an alarm and the like becomes higher, whereby the determination value may be increased by a specified coefficient (e.g., 50%). Thus, as shown inFIG. 11 , a dead spot determination value is added to a running path memory for each of the other vehicles N1 and N2 running about the own vehicle M, whereby a blind spot determination value is set as a whole (step S1209). Such a blind spot determining value distribution is set so as to extend to about several hundreds of meters ahead at each time at predetermined time intervals after the lapse of a predetermined time in future (e.g., after several seconds to several tens of seconds). - Subsequently, utilizing the blind spot determination value distribution as a risk degree distribution, the integrated value of dead spot determination value in the case of running according to the temporarily created running plan is computed in the bind spot determination value integrating part 219 (step S1210). Namely, utilizing the blind spot determination value distribution at each time, the blind spot determination value within the area occupied by the own vehicle is acquired and integrated with respect to time.
- Next, the degree of urgency of the running condition set by the running
condition setting part 218 is determined in the running conditionurgency determining part 220. First, it is determined whether the degree of urgency is “high” or not (step S1211). When the degree of urgency is “high”, it is determined that the control is necessary or inevitable, whereby the temporarily created running plan is formally employed regardless of the blind spot determination value (step S1212). When the degree of urgency is not “high”, it is determined whether the degree of urgency is “middle” or not (step S1213). When the degree of urgency is “middle”, the higher threshold (e.g., 100) is selected in thethreshold selecting part 221, and this threshold and the integrated value of blind spot determination value are compared with each other in the integrated value comparing part 222 (step S1214). When the integrated value of blind spot determination value is not higher than the threshold value, the temporarily created control plan is determined safe and formally employed (step S1212). When the integrated value of blind spot determination value exceeds this threshold, the control plan is determined unsafe, so that the flow returns to step S1203, where a control plan is temporarily created again so as to evade a part interfering with a blind spot, for example. - When it is determined at step S1213 that the degree of urgency is not “middle”, the degree of urgency becomes “low” as a result. In this case, the lower threshold (e.g., 50) is selected in the
threshold selecting part 221, and this threshold and the integrated value of blind spot determination value are compared with each other in the integrated value comparing part 222 (step S1215). When the integrated value of blind spot determination value is not greater than this threshold, this control plan is determined safe and formally employed (step S1216). When the integrated value of blind spot determination value exceeds this threshold, it is determined that the control plan is unsafe, whereby the flow shifts to step S1203, whereby a control plan is temporarily created again so as to evade a part interfering with a blind spot area, for example. - When the running plan is thus employed, the running
control ECU 60 creates an instruction value for an actuator, while taking account of the estimated value of state quantity of the own vehicle M, so as to faithfully reproduce the position and speed at each time according to the employed running plan. Then, thethrottle actuator 71 andbrake actuator 74 are controlled, so as to regulate theengine 73 andbrake units 74, thereby controlling acceleration/deceleration. Also, thesteering motor 75 is controlled, so as to regulate an electric power steering unit, whereby steering control is performed. - As in the foregoing, the running
plan creating apparatus 201 in accordance with this embodiment can acquire, as characteristic information in each of the other vehicles running about the own vehicle, a blind spot area which becomes a blind spot for the driver of the other vehicle, and can set a blind spot determination value distribution as a degree of risk of each of the other vehicles by utilizing thus acquired blind spot area. Therefore, a running plan can be created according to the risk degree distribution such as to evade blind spots of the drivers within an available range in conformity to the degree of urgency in the running condition, whereby the risk of accidents being caused by oversight of the drivers of the other vehicles can be reduced. - The present invention can be modified in various ways without being restricted to the above-mentioned embodiments. For example, actions of the other vehicles running about the own vehicle are estimated from past histories in the above-mentioned embodiments. When the other vehicles are automatically controlled vehicles, their running plans may be acquired through the
communication unit 50, and the actions may be predicted according to thus acquired running plans. In this case, the weight information of the other vehicles estimated in the first embodiment may be received through thecommunication unit 50. - Though the above-mentioned embodiments explain the case where the running plan creating apparatus is mounted to the own vehicle, infrastructures may be provided with the running plan creating apparatus, so that a running plan created thereby may be received through a communication unit, such as to control the running of the own vehicle.
- As explained in the foregoing, the running plan creating apparatus in accordance with the embodiments can create a safer running plan in consideration of the degree of risk of each of the other vehicles thereabout.
Claims (14)
1. A running plan creating apparatus for creating a running plan including position information of a vehicle at each time;
the apparatus comprising:
road information acquiring means for acquiring road information concerning a running path for the vehicle to run;
action predicting means for predicting positions and speeds of other vehicles running about the vehicle at each time by utilizing the road information;
characteristic information acquiring means for acquiring characteristic information in each of the other vehicles;
risk degree estimating means for estimating respective degrees of risk of the other vehicles by utilizing the characteristic information;
risk degree distribution setting means for setting a risk degree distribution at each time on the running path by utilizing the road information and the positions and degrees of risk of the other vehicles; and
running plan creating means for creating the running plan of the vehicle by utilizing the risk degree distribution.
2. A running plan creating apparatus according to claim 1 , wherein the characteristic information acquiring means acquires a weight of the other vehicle as the characteristic information; and
wherein the risk degree estimating means estimates the degree of risk to be higher as a kinetic energy based on the weight and speed of the other vehicle is higher.
3. A running plan creating apparatus according to claim 1 , wherein the characteristic information acquiring means acquires a relative relationship between the other vehicle and a vehicle thereabout as the characteristic information.
4. A running plan creating apparatus according to claim 3 , wherein the characteristic information includes at least a desirable headway time or time to collision of the other vehicle with respect to a vehicle thereabout; and
wherein the risk degree estimating means estimates the degree of risk to be higher as the desirable headway time or time to collision is shorter.
5. A running plan creating apparatus according to claim 1 , wherein the characteristic information acquiring means acquires a blind spot area to become a blind spot for the driver of the other vehicle as the characteristic information; and
wherein the risk degree estimating means estimates the degree of risk of each of the other vehicles by providing the blind spot area with a predetermined value.
6. A running plan creating apparatus according to claim 5 , further comprising:
running condition setting means for setting a running condition of the vehicle;
running plan temporarily creating means for temporarily creating a running plan of the vehicle achieving the running condition;
integrated value computing means for computing an integrated value of degree of risk of the vehicle running according to the temporarily created running plan by utilizing the risk degree distribution; and
urgency degree determining means for determining a degree of urgency of the running condition;
wherein the running plan creating means creates such a running plan as to reduce the integrated value of degree of risk according to the degree of urgency.
7. A running plan creating apparatus according to claim 6 , further comprising threshold selecting means for selecting a higher threshold as the degree of urgency is higher;
wherein the running plan creating means creates such a running plan as to reduce the integrated value of the degree of risk when the integrated value exceeds the threshold.
8. A running plan creating apparatus for creating a running plan including position information of a vehicle at each time;
the apparatus comprising:
a road information acquiring unit adapted to acquire road information concerning a running path for the vehicle to run; and
a control unit;
wherein the control unit comprises:
an action predicting part configured to predict positions and speeds of other vehicles running about the vehicle at each time by utilizing the road information;
a characteristic information acquiring part configured to acquire characteristic information in each of the other vehicles;
a risk degree estimating part configured to estimate respective degrees of risk of the other vehicles by utilizing the characteristic information;
a risk degree distribution setting part configured to set a risk degree distribution at each time on the running path by utilizing the road information and the positions and degrees of risk of the other vehicles; and
a running plan creating part configured to create the running plan of the vehicle by utilizing the risk degree distribution.
9. A running plan creating apparatus according to claim 8 , wherein the characteristic information acquiring part acquires a weight of the other vehicle as the characteristic information; and
wherein the risk degree estimating part estimates the degree of risk to be higher as a kinetic energy based on the weight and speed of the other vehicle is higher.
10. A running plan creating apparatus according to claim 8 , wherein the characteristic information acquiring part acquires a relative relationship between the other vehicle and a vehicle thereabout as the characteristic information.
11. A running plan creating apparatus according to claim 10 , wherein the characteristic information includes at least a desirable headway time or time to collision of the other vehicle with respect to a vehicle thereabout; and
wherein the risk degree estimating part estimates the degree of risk to be higher as the desirable headway time or time to collision is shorter.
12. A running plan creating apparatus according to claim 8 , wherein the characteristic information acquiring part acquires a blind spot area to become a blind spot for the driver of the other vehicle as the characteristic information; and
wherein the risk degree estimating part estimates the degree of risk of each of the other vehicles by providing the blind spot area with a predetermined value.
13. A running plan creating apparatus according to claim 12 , wherein the control unit further comprises:
a running condition setting part configured to set a running condition of the vehicle;
a running plan temporarily creating part configured to temporarily create a running plan of the vehicle achieving the running condition;
an integrated value computing part configured to compute an integrated value of degree of risk of the vehicle running according to the temporarily created running plan by utilizing the risk degree distribution; and
an urgency degree determining part configured to determine a degree of urgency of the running condition; and
wherein the running plan creating part creates such a running plan as to reduce the integrated value of degree of risk according to the degree of urgency.
14. A running plan creating apparatus according to claim 13 , wherein the control unit further comprises a threshold selecting part configured to select a higher threshold as the degree of urgency is higher; and
wherein the running plan creating part creates such a running plan as to reduce the integrated value of the degree of risk when the integrated value exceeds the threshold.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/027,572 US8660778B2 (en) | 2007-08-03 | 2011-02-15 | Running plan creating apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2007203491A JP4416020B2 (en) | 2007-08-03 | 2007-08-03 | Travel plan generator |
JPP2007-203491 | 2007-08-03 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/027,572 Continuation US8660778B2 (en) | 2007-08-03 | 2011-02-15 | Running plan creating apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
US20090037088A1 true US20090037088A1 (en) | 2009-02-05 |
Family
ID=40338895
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/182,401 Abandoned US20090037088A1 (en) | 2007-08-03 | 2008-07-30 | Running plan creating apparatus |
US13/027,572 Active 2029-08-09 US8660778B2 (en) | 2007-08-03 | 2011-02-15 | Running plan creating apparatus |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/027,572 Active 2029-08-09 US8660778B2 (en) | 2007-08-03 | 2011-02-15 | Running plan creating apparatus |
Country Status (2)
Country | Link |
---|---|
US (2) | US20090037088A1 (en) |
JP (1) | JP4416020B2 (en) |
Cited By (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100228419A1 (en) * | 2009-03-09 | 2010-09-09 | Gm Global Technology Operations, Inc. | method to assess risk associated with operating an autonomic vehicle control system |
WO2010089661A3 (en) * | 2009-02-09 | 2010-10-14 | Toyota Jidosha Kabushiki Kaisha | Apparatus for predicting the movement of a mobile body |
US8155868B1 (en) * | 2009-03-31 | 2012-04-10 | Toyota Infotechnology Center Co., Ltd. | Managing vehicle efficiency |
US20130162791A1 (en) * | 2011-12-23 | 2013-06-27 | Automotive Research & Testing Center | Vehicular warning system and method |
JP2013186724A (en) * | 2012-03-08 | 2013-09-19 | Nissan Motor Co Ltd | Travel control apparatus and travel control method |
US20140032090A1 (en) * | 2012-07-27 | 2014-01-30 | Toyota Jidosha Kabushiki Kaisha | Vehicle behavior prediction apparatus and vehicle behavior prediction method |
US20150012207A1 (en) * | 2013-07-08 | 2015-01-08 | GM Global Technology Operations LLC | Vehicle range projection estimation |
CN104340152A (en) * | 2013-08-06 | 2015-02-11 | 通用汽车环球科技运作有限责任公司 | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks |
US20150314783A1 (en) * | 2014-04-30 | 2015-11-05 | Denso International America, Inc. | Situation Awareness Assistant For Vehicle Control |
US9180882B1 (en) * | 2012-06-20 | 2015-11-10 | Google Inc. | Avoiding blind spots of other vehicles |
US20160150070A1 (en) * | 2013-07-18 | 2016-05-26 | Secure4Drive Communication Ltd. | Method and device for assisting in safe driving of a vehicle |
JP2017130104A (en) * | 2016-01-21 | 2017-07-27 | 富士通テン株式会社 | Composure degree determination device, composure degree determination method and drive support system |
GB2553191A (en) * | 2016-06-13 | 2018-02-28 | Ford Global Tech Llc | Blind spot detection systems and methods |
US20180201192A1 (en) * | 2017-01-19 | 2018-07-19 | Toyota Jidosha Kabushiki Kaisha | Alert apparatus for vehicle |
US10204516B2 (en) * | 2014-07-23 | 2019-02-12 | Hatsumeiya Co, Ltd | Automobile and computing system |
US10262539B2 (en) * | 2016-12-15 | 2019-04-16 | Ford Global Technologies, Llc | Inter-vehicle warnings |
US10347127B2 (en) | 2013-02-21 | 2019-07-09 | Waymo Llc | Driving mode adjustment |
US20190315345A1 (en) * | 2018-04-16 | 2019-10-17 | David E. Newman | Blind spot potential-hazard avoidance system |
US10486708B1 (en) * | 2016-04-11 | 2019-11-26 | State Farm Mutual Automobile Insurance Company | System for adjusting autonomous vehicle driving behavior to mimic that of neighboring/surrounding vehicles |
US10529235B2 (en) | 2016-01-08 | 2020-01-07 | Ford Global Technologies, Llc | System and method for virtual transformation of standard or non-connected vehicles |
US10571283B1 (en) | 2016-04-11 | 2020-02-25 | State Farm Mutual Automobile Insurance Company | System for reducing vehicle collisions based on an automated segmented assessment of a collision risk |
US10593197B1 (en) | 2016-04-11 | 2020-03-17 | State Farm Mutual Automobile Insurance Company | Networked vehicle control systems to facilitate situational awareness of vehicles |
EP3614362A4 (en) * | 2017-04-19 | 2020-05-13 | Nissan Motor Co., Ltd. | Travel assistance method and travel assistance device |
CN111291916A (en) * | 2018-12-10 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Driving behavior safety prediction method and device, electronic equipment and storage medium |
US10706094B2 (en) | 2005-10-26 | 2020-07-07 | Cortica Ltd | System and method for customizing a display of a user device based on multimedia content element signatures |
US10713950B1 (en) | 2019-06-13 | 2020-07-14 | Autonomous Roadway Intelligence, Llc | Rapid wireless communication for vehicle collision mitigation |
US10748038B1 (en) | 2019-03-31 | 2020-08-18 | Cortica Ltd. | Efficient calculation of a robust signature of a media unit |
US10748022B1 (en) | 2019-12-12 | 2020-08-18 | Cartica Ai Ltd | Crowd separation |
US10776669B1 (en) | 2019-03-31 | 2020-09-15 | Cortica Ltd. | Signature generation and object detection that refer to rare scenes |
US10789535B2 (en) | 2018-11-26 | 2020-09-29 | Cartica Ai Ltd | Detection of road elements |
US10789527B1 (en) | 2019-03-31 | 2020-09-29 | Cortica Ltd. | Method for object detection using shallow neural networks |
US10796444B1 (en) | 2019-03-31 | 2020-10-06 | Cortica Ltd | Configuring spanning elements of a signature generator |
US10818113B1 (en) | 2016-04-11 | 2020-10-27 | State Farm Mutual Automobile Insuance Company | Systems and methods for providing awareness of emergency vehicles |
US10816636B2 (en) | 2018-12-20 | 2020-10-27 | Autonomous Roadway Intelligence, Llc | Autonomous vehicle localization system |
US10839694B2 (en) * | 2018-10-18 | 2020-11-17 | Cartica Ai Ltd | Blind spot alert |
US10872379B1 (en) | 2016-04-11 | 2020-12-22 | State Farm Mutual Automobile Insurance Company | Collision risk-based engagement and disengagement of autonomous control of a vehicle |
US10877482B2 (en) | 2017-04-06 | 2020-12-29 | Toyota Jidosha Kabushiki Kaisha | Trajectory setting device and trajectory setting method |
US10895471B1 (en) | 2016-04-11 | 2021-01-19 | State Farm Mutual Automobile Insurance Company | System for driver's education |
US10930158B1 (en) | 2016-04-11 | 2021-02-23 | State Farm Mutual Automobile Insurance Company | System for identifying high risk parking lots |
US10989556B1 (en) | 2016-04-11 | 2021-04-27 | State Farm Mutual Automobile Insurance Company | Traffic risk a avoidance for a route selection system |
US11029685B2 (en) | 2018-10-18 | 2021-06-08 | Cartica Ai Ltd. | Autonomous risk assessment for fallen cargo |
US20210200235A1 (en) * | 2018-08-14 | 2021-07-01 | Mobileye Vision Technologies Ltd. | Navigation with a safe longitudinal distance |
US11126869B2 (en) | 2018-10-26 | 2021-09-21 | Cartica Ai Ltd. | Tracking after objects |
US11126870B2 (en) | 2018-10-18 | 2021-09-21 | Cartica Ai Ltd. | Method and system for obstacle detection |
US11132548B2 (en) | 2019-03-20 | 2021-09-28 | Cortica Ltd. | Determining object information that does not explicitly appear in a media unit signature |
US11175662B2 (en) | 2017-02-20 | 2021-11-16 | Mitsubishi Electric Corporation | Travel plan correction device and travel plan correction method |
US11181911B2 (en) | 2018-10-18 | 2021-11-23 | Cartica Ai Ltd | Control transfer of a vehicle |
CN113815613A (en) * | 2020-06-18 | 2021-12-21 | 现代摩比斯株式会社 | Vehicle sight blind area avoiding system and method using accident history information |
CN113815614A (en) * | 2020-06-18 | 2021-12-21 | 现代摩比斯株式会社 | Vehicle blind area avoiding device and method thereof |
US11209284B2 (en) * | 2017-12-18 | 2021-12-28 | Hyundai Motor Company | System and method for creating driving route of vehicle |
US11222069B2 (en) | 2019-03-31 | 2022-01-11 | Cortica Ltd. | Low-power calculation of a signature of a media unit |
US11285963B2 (en) | 2019-03-10 | 2022-03-29 | Cartica Ai Ltd. | Driver-based prediction of dangerous events |
US11347224B2 (en) * | 2017-06-01 | 2022-05-31 | Mitsubishi Electric Corporation | System and method to control a target object based on a traveling state of a peripheral object |
US11498537B1 (en) | 2016-04-11 | 2022-11-15 | State Farm Mutual Automobile Insurance Company | System for determining road slipperiness in bad weather conditions |
US11593662B2 (en) | 2019-12-12 | 2023-02-28 | Autobrains Technologies Ltd | Unsupervised cluster generation |
US11590988B2 (en) | 2020-03-19 | 2023-02-28 | Autobrains Technologies Ltd | Predictive turning assistant |
US11643005B2 (en) | 2019-02-27 | 2023-05-09 | Autobrains Technologies Ltd | Adjusting adjustable headlights of a vehicle |
US11694088B2 (en) | 2019-03-13 | 2023-07-04 | Cortica Ltd. | Method for object detection using knowledge distillation |
US11756424B2 (en) | 2020-07-24 | 2023-09-12 | AutoBrains Technologies Ltd. | Parking assist |
US11760387B2 (en) | 2017-07-05 | 2023-09-19 | AutoBrains Technologies Ltd. | Driving policies determination |
US11827215B2 (en) | 2020-03-31 | 2023-11-28 | AutoBrains Technologies Ltd. | Method for training a driving related object detector |
US11899707B2 (en) | 2017-07-09 | 2024-02-13 | Cortica Ltd. | Driving policies determination |
Families Citing this family (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5336800B2 (en) * | 2008-09-24 | 2013-11-06 | 富士重工業株式会社 | Vehicle driving support device |
JP5316186B2 (en) * | 2009-04-10 | 2013-10-16 | トヨタ自動車株式会社 | Vehicle control apparatus and vehicle control method |
JP2011048470A (en) * | 2009-08-25 | 2011-03-10 | Toyota Motor Corp | Environment prediction device |
JP5482323B2 (en) * | 2010-03-12 | 2014-05-07 | 株式会社豊田中央研究所 | Driving support device and program |
JP5533157B2 (en) * | 2010-04-07 | 2014-06-25 | トヨタ自動車株式会社 | Future behavior prediction device |
JP5593800B2 (en) * | 2010-04-14 | 2014-09-24 | トヨタ自動車株式会社 | Travel control device |
JP5565359B2 (en) * | 2011-03-29 | 2014-08-06 | 株式会社デンソー | In-vehicle control device |
JP2014049075A (en) * | 2012-09-04 | 2014-03-17 | Toyota Motor Corp | Travel support device |
JP6357737B2 (en) * | 2013-07-24 | 2018-07-18 | 富士通株式会社 | Vehicle flow measuring device, method and program |
JP6155973B2 (en) * | 2013-08-27 | 2017-07-05 | 株式会社デンソー | Driving support device and driving support method |
JP6308032B2 (en) * | 2014-06-04 | 2018-04-11 | 株式会社デンソー | System and method for generating driving maneuvers |
WO2016110999A1 (en) * | 2015-01-09 | 2016-07-14 | 三菱電機株式会社 | Operation control device |
KR101730321B1 (en) | 2015-08-03 | 2017-04-27 | 엘지전자 주식회사 | Driver assistance apparatus and control method for the same |
US9568915B1 (en) * | 2016-02-11 | 2017-02-14 | Mitsubishi Electric Research Laboratories, Inc. | System and method for controlling autonomous or semi-autonomous vehicle |
CN105785977B (en) * | 2016-05-03 | 2018-09-11 | 北京新能源汽车股份有限公司 | The date storage method and electric-control system of the electric-control system of vehicle |
US10042362B2 (en) * | 2016-11-18 | 2018-08-07 | Waymo Llc | Dynamic routing for autonomous vehicles |
KR101934731B1 (en) * | 2016-11-22 | 2019-01-03 | 엘지전자 주식회사 | Communication device for vehicle and vehicle |
JP6596047B2 (en) * | 2017-09-01 | 2019-10-23 | 本田技研工業株式会社 | Vehicle control device, vehicle, and method |
JP6907896B2 (en) | 2017-11-17 | 2021-07-21 | トヨタ自動車株式会社 | Autonomous driving system |
KR102035922B1 (en) * | 2018-01-25 | 2019-10-24 | 주식회사 에프에스솔루션 | Apparatus and method for predicting degree of risk by forward vehicle |
JP6689337B2 (en) * | 2018-09-12 | 2020-04-28 | 三菱電機株式会社 | Automatic operation control device and automatic operation control method |
KR102637599B1 (en) * | 2018-10-08 | 2024-02-19 | 주식회사 에이치엘클레무브 | Apparatus and Method for Controlling Lane Changing using Vehicle-to-Vehicle Communication and Tendency Information Calculation Apparatus therefor |
JP7086217B2 (en) * | 2018-11-28 | 2022-06-17 | 三菱電機株式会社 | Collision avoidance learning device and collision avoidance learning method |
JP2020095594A (en) | 2018-12-14 | 2020-06-18 | トヨタ自動車株式会社 | Vehicle control device and vehicle control method |
KR102247168B1 (en) * | 2018-12-26 | 2021-05-03 | 바이두닷컴 타임즈 테크놀로지(베이징) 컴퍼니 리미티드 | Obstacle filtering method of non-avoidance planning system in autonomous vehicle |
JP7258077B2 (en) * | 2021-05-13 | 2023-04-14 | 三菱電機株式会社 | Other vehicle behavior prediction device |
WO2023085469A1 (en) * | 2021-11-12 | 2023-05-19 | 충북대학교 산학협력단 | Vehicle traveling hybrid control method and traveling hybrid control apparatus supporting same |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040011582A1 (en) * | 2002-04-03 | 2004-01-22 | Takata Corporation | Collision detecting device and passive safety system |
US20050143911A1 (en) * | 2003-12-24 | 2005-06-30 | Noboru Ishibashi | Navigation apparatus, navigation system and navigation method providing guidance for lane changes |
US20060031015A1 (en) * | 2004-08-09 | 2006-02-09 | M/A-Com, Inc. | Imminent-collision detection system and process |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001294116A (en) | 2000-04-12 | 2001-10-23 | Keihin Corp | Vehicular collision determination device |
JP4045811B2 (en) | 2002-02-13 | 2008-02-13 | 株式会社豊田中央研究所 | Vehicle speed control device |
JP4578795B2 (en) * | 2003-03-26 | 2010-11-10 | 富士通テン株式会社 | Vehicle control device, vehicle control method, and vehicle control program |
JP2005263026A (en) * | 2004-03-18 | 2005-09-29 | Toyota Motor Corp | Method and device for optimizing pre-crash safety control |
JP4604683B2 (en) | 2004-11-25 | 2011-01-05 | 日産自動車株式会社 | Hazardous situation warning device |
JP4760715B2 (en) | 2004-12-28 | 2011-08-31 | 株式会社豊田中央研究所 | Vehicle motion control device |
JP2006277058A (en) | 2005-03-28 | 2006-10-12 | Fujitsu Ten Ltd | Safety device |
JP4770488B2 (en) | 2006-01-31 | 2011-09-14 | コニカミノルタホールディングス株式会社 | Inkjet printer |
JP2008108086A (en) | 2006-10-26 | 2008-05-08 | Kyocera Corp | Traffic information providing system, traffic information providing device and traffic information providing method |
-
2007
- 2007-08-03 JP JP2007203491A patent/JP4416020B2/en not_active Expired - Fee Related
-
2008
- 2008-07-30 US US12/182,401 patent/US20090037088A1/en not_active Abandoned
-
2011
- 2011-02-15 US US13/027,572 patent/US8660778B2/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040011582A1 (en) * | 2002-04-03 | 2004-01-22 | Takata Corporation | Collision detecting device and passive safety system |
US20050143911A1 (en) * | 2003-12-24 | 2005-06-30 | Noboru Ishibashi | Navigation apparatus, navigation system and navigation method providing guidance for lane changes |
US20060031015A1 (en) * | 2004-08-09 | 2006-02-09 | M/A-Com, Inc. | Imminent-collision detection system and process |
Cited By (107)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10706094B2 (en) | 2005-10-26 | 2020-07-07 | Cortica Ltd | System and method for customizing a display of a user device based on multimedia content element signatures |
WO2010089661A3 (en) * | 2009-02-09 | 2010-10-14 | Toyota Jidosha Kabushiki Kaisha | Apparatus for predicting the movement of a mobile body |
US8676487B2 (en) | 2009-02-09 | 2014-03-18 | Toyota Jidosha Kabushiki Kaisha | Apparatus for predicting the movement of a mobile body |
US8244408B2 (en) * | 2009-03-09 | 2012-08-14 | GM Global Technology Operations LLC | Method to assess risk associated with operating an autonomic vehicle control system |
US20100228419A1 (en) * | 2009-03-09 | 2010-09-09 | Gm Global Technology Operations, Inc. | method to assess risk associated with operating an autonomic vehicle control system |
US8155868B1 (en) * | 2009-03-31 | 2012-04-10 | Toyota Infotechnology Center Co., Ltd. | Managing vehicle efficiency |
US9283846B2 (en) * | 2011-12-23 | 2016-03-15 | Automotive Research & Testing Center | Vehicular warning system and method |
US20130162791A1 (en) * | 2011-12-23 | 2013-06-27 | Automotive Research & Testing Center | Vehicular warning system and method |
JP2013186724A (en) * | 2012-03-08 | 2013-09-19 | Nissan Motor Co Ltd | Travel control apparatus and travel control method |
US9180882B1 (en) * | 2012-06-20 | 2015-11-10 | Google Inc. | Avoiding blind spots of other vehicles |
US9690296B1 (en) | 2012-06-20 | 2017-06-27 | Waymo Llc | Avoiding blind spots of other vehicles |
US11868133B1 (en) * | 2012-06-20 | 2024-01-09 | Waymo Llc | Avoiding blind spots of other vehicles |
US10591919B1 (en) | 2012-06-20 | 2020-03-17 | Waymo Llc | Avoiding blind spots of other vehicles |
US20140032090A1 (en) * | 2012-07-27 | 2014-01-30 | Toyota Jidosha Kabushiki Kaisha | Vehicle behavior prediction apparatus and vehicle behavior prediction method |
US9052997B2 (en) * | 2012-07-27 | 2015-06-09 | Toyota Jidosha Kabushiki Kaisha | Vehicle behavior prediction apparatus and vehicle behavior prediction method |
US10347127B2 (en) | 2013-02-21 | 2019-07-09 | Waymo Llc | Driving mode adjustment |
US9074894B2 (en) * | 2013-07-08 | 2015-07-07 | GM Global Technology Operations LLC | Vehicle range projection estimation |
US20150012207A1 (en) * | 2013-07-08 | 2015-01-08 | GM Global Technology Operations LLC | Vehicle range projection estimation |
US20160150070A1 (en) * | 2013-07-18 | 2016-05-26 | Secure4Drive Communication Ltd. | Method and device for assisting in safe driving of a vehicle |
US10298741B2 (en) * | 2013-07-18 | 2019-05-21 | Secure4Drive Communication Ltd. | Method and device for assisting in safe driving of a vehicle |
US9280899B2 (en) * | 2013-08-06 | 2016-03-08 | GM Global Technology Operations LLC | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks |
CN104340152A (en) * | 2013-08-06 | 2015-02-11 | 通用汽车环球科技运作有限责任公司 | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks |
US20150046078A1 (en) * | 2013-08-06 | 2015-02-12 | GM Global Technology Operations LLC | Dynamic safety shields for situation assessment and decision making in collision avoidance tasks |
US9522676B2 (en) * | 2014-04-30 | 2016-12-20 | Denso International America, Inc. | Situation awareness assistant for vehicle control |
US20150314783A1 (en) * | 2014-04-30 | 2015-11-05 | Denso International America, Inc. | Situation Awareness Assistant For Vehicle Control |
US10204516B2 (en) * | 2014-07-23 | 2019-02-12 | Hatsumeiya Co, Ltd | Automobile and computing system |
US10529235B2 (en) | 2016-01-08 | 2020-01-07 | Ford Global Technologies, Llc | System and method for virtual transformation of standard or non-connected vehicles |
JP2017130104A (en) * | 2016-01-21 | 2017-07-27 | 富士通テン株式会社 | Composure degree determination device, composure degree determination method and drive support system |
US10933881B1 (en) * | 2016-04-11 | 2021-03-02 | State Farm Mutual Automobile Insurance Company | System for adjusting autonomous vehicle driving behavior to mimic that of neighboring/surrounding vehicles |
US11205340B2 (en) | 2016-04-11 | 2021-12-21 | State Farm Mutual Automobile Insurance Company | Networked vehicle control systems to facilitate situational awareness of vehicles |
US10571283B1 (en) | 2016-04-11 | 2020-02-25 | State Farm Mutual Automobile Insurance Company | System for reducing vehicle collisions based on an automated segmented assessment of a collision risk |
US10895471B1 (en) | 2016-04-11 | 2021-01-19 | State Farm Mutual Automobile Insurance Company | System for driver's education |
US10593197B1 (en) | 2016-04-11 | 2020-03-17 | State Farm Mutual Automobile Insurance Company | Networked vehicle control systems to facilitate situational awareness of vehicles |
US11851041B1 (en) | 2016-04-11 | 2023-12-26 | State Farm Mutual Automobile Insurance Company | System for determining road slipperiness in bad weather conditions |
US11727495B1 (en) | 2016-04-11 | 2023-08-15 | State Farm Mutual Automobile Insurance Company | Collision risk-based engagement and disengagement of autonomous control of a vehicle |
US10872379B1 (en) | 2016-04-11 | 2020-12-22 | State Farm Mutual Automobile Insurance Company | Collision risk-based engagement and disengagement of autonomous control of a vehicle |
US11656094B1 (en) | 2016-04-11 | 2023-05-23 | State Farm Mutual Automobile Insurance Company | System for driver's education |
US11498537B1 (en) | 2016-04-11 | 2022-11-15 | State Farm Mutual Automobile Insurance Company | System for determining road slipperiness in bad weather conditions |
US11257377B1 (en) | 2016-04-11 | 2022-02-22 | State Farm Mutual Automobile Insurance Company | System for identifying high risk parking lots |
US10930158B1 (en) | 2016-04-11 | 2021-02-23 | State Farm Mutual Automobile Insurance Company | System for identifying high risk parking lots |
US10486708B1 (en) * | 2016-04-11 | 2019-11-26 | State Farm Mutual Automobile Insurance Company | System for adjusting autonomous vehicle driving behavior to mimic that of neighboring/surrounding vehicles |
US10989556B1 (en) | 2016-04-11 | 2021-04-27 | State Farm Mutual Automobile Insurance Company | Traffic risk a avoidance for a route selection system |
US11024157B1 (en) | 2016-04-11 | 2021-06-01 | State Farm Mutual Automobile Insurance Company | Networked vehicle control systems to facilitate situational awareness of vehicles |
US10818113B1 (en) | 2016-04-11 | 2020-10-27 | State Farm Mutual Automobile Insuance Company | Systems and methods for providing awareness of emergency vehicles |
US10988960B1 (en) | 2016-04-11 | 2021-04-27 | State Farm Mutual Automobile Insurance Company | Systems and methods for providing awareness of emergency vehicles |
US10829966B1 (en) | 2016-04-11 | 2020-11-10 | State Farm Mutual Automobile Insurance Company | Systems and methods for control systems to facilitate situational awareness of a vehicle |
US10991181B1 (en) | 2016-04-11 | 2021-04-27 | State Farm Mutual Automobile Insurance Company | Systems and method for providing awareness of emergency vehicles |
GB2553191A (en) * | 2016-06-13 | 2018-02-28 | Ford Global Tech Llc | Blind spot detection systems and methods |
US10262539B2 (en) * | 2016-12-15 | 2019-04-16 | Ford Global Technologies, Llc | Inter-vehicle warnings |
US20180201192A1 (en) * | 2017-01-19 | 2018-07-19 | Toyota Jidosha Kabushiki Kaisha | Alert apparatus for vehicle |
US11175662B2 (en) | 2017-02-20 | 2021-11-16 | Mitsubishi Electric Corporation | Travel plan correction device and travel plan correction method |
US11204607B2 (en) | 2017-04-06 | 2021-12-21 | Toyota Jidosha Kabushiki Kaisha | Trajectory setting device and trajectory setting method |
US11932284B2 (en) | 2017-04-06 | 2024-03-19 | Toyota Jidosha Kabushiki Kaisha | Trajectory setting device and trajectory setting method |
US11662733B2 (en) | 2017-04-06 | 2023-05-30 | Toyota Jidosha Kabushiki Kaisha | Trajectory setting device and trajectory setting method |
US10877482B2 (en) | 2017-04-06 | 2020-12-29 | Toyota Jidosha Kabushiki Kaisha | Trajectory setting device and trajectory setting method |
US10994730B2 (en) | 2017-04-19 | 2021-05-04 | Nissan Motor Co., Ltd. | Traveling assistance method and traveling assistance device |
EP3614362A4 (en) * | 2017-04-19 | 2020-05-13 | Nissan Motor Co., Ltd. | Travel assistance method and travel assistance device |
US11347224B2 (en) * | 2017-06-01 | 2022-05-31 | Mitsubishi Electric Corporation | System and method to control a target object based on a traveling state of a peripheral object |
US11760387B2 (en) | 2017-07-05 | 2023-09-19 | AutoBrains Technologies Ltd. | Driving policies determination |
US11899707B2 (en) | 2017-07-09 | 2024-02-13 | Cortica Ltd. | Driving policies determination |
US11209284B2 (en) * | 2017-12-18 | 2021-12-28 | Hyundai Motor Company | System and method for creating driving route of vehicle |
US20190315345A1 (en) * | 2018-04-16 | 2019-10-17 | David E. Newman | Blind spot potential-hazard avoidance system |
US20210200235A1 (en) * | 2018-08-14 | 2021-07-01 | Mobileye Vision Technologies Ltd. | Navigation with a safe longitudinal distance |
US11126870B2 (en) | 2018-10-18 | 2021-09-21 | Cartica Ai Ltd. | Method and system for obstacle detection |
US11087628B2 (en) | 2018-10-18 | 2021-08-10 | Cartica Al Ltd. | Using rear sensor for wrong-way driving warning |
US11718322B2 (en) | 2018-10-18 | 2023-08-08 | Autobrains Technologies Ltd | Risk based assessment |
US11181911B2 (en) | 2018-10-18 | 2021-11-23 | Cartica Ai Ltd | Control transfer of a vehicle |
US11685400B2 (en) | 2018-10-18 | 2023-06-27 | Autobrains Technologies Ltd | Estimating danger from future falling cargo |
US11673583B2 (en) | 2018-10-18 | 2023-06-13 | AutoBrains Technologies Ltd. | Wrong-way driving warning |
US11029685B2 (en) | 2018-10-18 | 2021-06-08 | Cartica Ai Ltd. | Autonomous risk assessment for fallen cargo |
US10839694B2 (en) * | 2018-10-18 | 2020-11-17 | Cartica Ai Ltd | Blind spot alert |
US11282391B2 (en) | 2018-10-18 | 2022-03-22 | Cartica Ai Ltd. | Object detection at different illumination conditions |
US11170233B2 (en) | 2018-10-26 | 2021-11-09 | Cartica Ai Ltd. | Locating a vehicle based on multimedia content |
US11700356B2 (en) | 2018-10-26 | 2023-07-11 | AutoBrains Technologies Ltd. | Control transfer of a vehicle |
US11244176B2 (en) | 2018-10-26 | 2022-02-08 | Cartica Ai Ltd | Obstacle detection and mapping |
US11373413B2 (en) | 2018-10-26 | 2022-06-28 | Autobrains Technologies Ltd | Concept update and vehicle to vehicle communication |
US11270132B2 (en) | 2018-10-26 | 2022-03-08 | Cartica Ai Ltd | Vehicle to vehicle communication and signatures |
US11126869B2 (en) | 2018-10-26 | 2021-09-21 | Cartica Ai Ltd. | Tracking after objects |
US10789535B2 (en) | 2018-11-26 | 2020-09-29 | Cartica Ai Ltd | Detection of road elements |
CN111291916A (en) * | 2018-12-10 | 2020-06-16 | 北京嘀嘀无限科技发展有限公司 | Driving behavior safety prediction method and device, electronic equipment and storage medium |
US10816636B2 (en) | 2018-12-20 | 2020-10-27 | Autonomous Roadway Intelligence, Llc | Autonomous vehicle localization system |
US11643005B2 (en) | 2019-02-27 | 2023-05-09 | Autobrains Technologies Ltd | Adjusting adjustable headlights of a vehicle |
US11285963B2 (en) | 2019-03-10 | 2022-03-29 | Cartica Ai Ltd. | Driver-based prediction of dangerous events |
US11694088B2 (en) | 2019-03-13 | 2023-07-04 | Cortica Ltd. | Method for object detection using knowledge distillation |
US11755920B2 (en) | 2019-03-13 | 2023-09-12 | Cortica Ltd. | Method for object detection using knowledge distillation |
US11132548B2 (en) | 2019-03-20 | 2021-09-28 | Cortica Ltd. | Determining object information that does not explicitly appear in a media unit signature |
US11275971B2 (en) | 2019-03-31 | 2022-03-15 | Cortica Ltd. | Bootstrap unsupervised learning |
US10748038B1 (en) | 2019-03-31 | 2020-08-18 | Cortica Ltd. | Efficient calculation of a robust signature of a media unit |
US11488290B2 (en) | 2019-03-31 | 2022-11-01 | Cortica Ltd. | Hybrid representation of a media unit |
US11481582B2 (en) | 2019-03-31 | 2022-10-25 | Cortica Ltd. | Dynamic matching a sensed signal to a concept structure |
US11741687B2 (en) | 2019-03-31 | 2023-08-29 | Cortica Ltd. | Configuring spanning elements of a signature generator |
US10776669B1 (en) | 2019-03-31 | 2020-09-15 | Cortica Ltd. | Signature generation and object detection that refer to rare scenes |
US10796444B1 (en) | 2019-03-31 | 2020-10-06 | Cortica Ltd | Configuring spanning elements of a signature generator |
US10846570B2 (en) | 2019-03-31 | 2020-11-24 | Cortica Ltd. | Scale inveriant object detection |
US11222069B2 (en) | 2019-03-31 | 2022-01-11 | Cortica Ltd. | Low-power calculation of a signature of a media unit |
US10789527B1 (en) | 2019-03-31 | 2020-09-29 | Cortica Ltd. | Method for object detection using shallow neural networks |
US10713950B1 (en) | 2019-06-13 | 2020-07-14 | Autonomous Roadway Intelligence, Llc | Rapid wireless communication for vehicle collision mitigation |
US11593662B2 (en) | 2019-12-12 | 2023-02-28 | Autobrains Technologies Ltd | Unsupervised cluster generation |
US10748022B1 (en) | 2019-12-12 | 2020-08-18 | Cartica Ai Ltd | Crowd separation |
US11590988B2 (en) | 2020-03-19 | 2023-02-28 | Autobrains Technologies Ltd | Predictive turning assistant |
US11827215B2 (en) | 2020-03-31 | 2023-11-28 | AutoBrains Technologies Ltd. | Method for training a driving related object detector |
CN113815613A (en) * | 2020-06-18 | 2021-12-21 | 现代摩比斯株式会社 | Vehicle sight blind area avoiding system and method using accident history information |
US20210394753A1 (en) * | 2020-06-18 | 2021-12-23 | Hyundai Mobis Co., Ltd. | System for avoiding blind spot of vehicle and method thereof |
CN113815614A (en) * | 2020-06-18 | 2021-12-21 | 现代摩比斯株式会社 | Vehicle blind area avoiding device and method thereof |
US11884267B2 (en) * | 2020-06-18 | 2024-01-30 | Hyundai Mobis Co., Ltd. | System for avoiding blind spot of vehicle using accident history information and method thereof |
US20210394750A1 (en) * | 2020-06-18 | 2021-12-23 | Hyundai Mobis Co., Ltd. | System for avoiding blind spot of vehicle using accident history information and method thereof |
US11756424B2 (en) | 2020-07-24 | 2023-09-12 | AutoBrains Technologies Ltd. | Parking assist |
Also Published As
Publication number | Publication date |
---|---|
US20110137562A1 (en) | 2011-06-09 |
JP2009037561A (en) | 2009-02-19 |
US8660778B2 (en) | 2014-02-25 |
JP4416020B2 (en) | 2010-02-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8660778B2 (en) | Running plan creating apparatus | |
US20190016339A1 (en) | Vehicle control device, vehicle control method, and vehicle control program | |
CN111547053B (en) | Automatic driving control method and system based on vehicle-road cooperation | |
CN101529486B (en) | Cruise control plan evaluation device and method | |
US10532736B2 (en) | Vehicle travel control device | |
US20140257686A1 (en) | Vehicle lane determination | |
US20220227392A1 (en) | Vehicle control device, vehicle control method, and automatic driving method | |
EP3925845B1 (en) | Other vehicle action prediction method and other vehicle action prediction device | |
CN113272196A (en) | Advanced highway auxiliary scene | |
CN110040138B (en) | Vehicle parallel auxiliary driving method and system | |
EP4074565A1 (en) | Automated lane changing device and method for vehicle | |
US11472439B2 (en) | Vehicle control system and vehicle control method | |
US11731661B2 (en) | Systems and methods for imminent collision avoidance | |
US20210107478A1 (en) | Vehicle control system | |
US20230148202A1 (en) | Vehicle control system | |
CN112874531B (en) | Vehicle curve anti-collision control method, device and system | |
US20220375349A1 (en) | Method and device for lane-changing prediction of target vehicle | |
US11548530B2 (en) | Vehicle control system | |
JP2021160714A (en) | Vehicle control device and vehicle control method | |
CN116279341B (en) | Safety braking method and device, electronic equipment and storage medium | |
CN112677976B (en) | Vehicle driving method, device, vehicle and storage medium | |
US11851088B2 (en) | Method for determining capability boundary and associated risk of a safety redundancy autonomous system in real-time | |
US11801857B2 (en) | Control method and device for driver assistance | |
CN115503715A (en) | Method and device for changing lane of automatic driving vehicle, computer equipment and storage medium | |
CN117953609A (en) | Accident data processing method, device, equipment and medium for automatic driving vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: TOYOTA JIDOSHA KABUSHIKI KAISHA, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TAGUCHI, KOJI;REEL/FRAME:021607/0649 Effective date: 20080909 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |