WO2022091400A1 - 他車挙動予測診断装置および他車挙動予測診断方法 - Google Patents
他車挙動予測診断装置および他車挙動予測診断方法 Download PDFInfo
- Publication number
- WO2022091400A1 WO2022091400A1 PCT/JP2020/041010 JP2020041010W WO2022091400A1 WO 2022091400 A1 WO2022091400 A1 WO 2022091400A1 JP 2020041010 W JP2020041010 W JP 2020041010W WO 2022091400 A1 WO2022091400 A1 WO 2022091400A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- behavior prediction
- lane
- road
- traveling
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 23
- 230000006399 behavior Effects 0.000 title abstract description 104
- 238000003745 diagnosis Methods 0.000 claims description 23
- 230000001133 acceleration Effects 0.000 claims description 7
- 238000002405 diagnostic procedure Methods 0.000 claims 2
- 230000006870 function Effects 0.000 description 32
- 230000005856 abnormality Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- 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
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/04—Monitoring the functioning of the control system
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/04—Traffic conditions
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4041—Position
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4042—Longitudinal speed
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4045—Intention, e.g. lane change or imminent movement
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4046—Behavior, e.g. aggressive or erratic
-
- 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
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- 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
- B60W2556/00—Input parameters relating to data
- B60W2556/20—Data confidence level
Definitions
- the present application relates to another vehicle behavior prediction diagnosis device and another vehicle behavior prediction diagnosis method.
- Japanese Unexamined Patent Publication No. 2015-215873 paragraphs 0045 to 0063, FIGS. 3 to 5, paragraphs 0065 to 0119
- Japanese Patent No. 6074553 paragraphs 0184-0220, FIGS. 16-22
- the prediction is mainly based on a lot of information including the position, speed, and acceleration of the preceding vehicle and the vehicle running in the adjacent lane.
- the judgment of a person who changes lanes is wide-ranging, such as branching to a desired road, changing lanes to enter a service area, and changing lanes due to the behavior of giving way to a vehicle behind, which is complicated with a lot of information.
- behavior prediction by artificial intelligence is generally more accurate than an algorithm that makes judgments based on certain rules, and can be predicted with an accuracy equal to or higher than that of human judgments.
- learning requires the accumulation of driving data for each driver, the prediction accuracy is lowered depending on the state of the driver, and the prediction accuracy is extremely lowered especially for an unknown driver. That is, even in this case, there is a problem in terms of prediction accuracy in spite of the large amount of information and complicated operations involved.
- the present application discloses a technique for solving the above-mentioned problems, and an object thereof is to easily diagnose whether or not the behavior prediction of another vehicle is operating normally.
- the other vehicle behavior prediction diagnostic device disclosed in the present application is a device for diagnosing the soundness of the other vehicle behavior prediction function that predicts the future behavior of another vehicle, and is the road information during traveling obtained from the sensor and the locator.
- the other vehicle condition estimation unit that estimates the driving condition for each of the other vehicles traveling in front of the own vehicle from the information on the positions of the surrounding vehicles and objects, or the estimated driving condition is an object on the road or
- a warning state determination unit that determines that the vehicle is in a warning state when decelerating or changing lanes to the lane in which the own vehicle is traveling in order to avoid a collision with another vehicle, and the above-mentioned Whether or not the other vehicle behavior prediction function is sound depending on whether or not the other vehicle behavior prediction corresponding to the warning state can be received from the other vehicle behavior prediction function when the determination result of being in the alert state is received. It is characterized by having a predictive function diagnostic unit for diagnosing.
- the other vehicle behavior prediction diagnosis method disclosed in the present application is a method for diagnosing the soundness of the other vehicle behavior prediction function for predicting the future behavior of another vehicle, and is the road information during traveling obtained from the sensor and the locator.
- One of the other vehicle driving condition estimation step for estimating the driving condition for each of the other vehicles traveling in front of the own vehicle from the information on the positions of surrounding vehicles and objects, or the estimated driving condition on the road is A warning state determination step that determines that the vehicle is in a warning state when it is in a state where it should decelerate or change lanes to the lane in which the own vehicle is traveling in order to avoid a collision with an object or another vehicle.
- the other vehicle behavior prediction diagnostic device disclosed in the present application or the other vehicle behavior prediction diagnosis method when the other vehicle needs to decelerate or change lanes, the prediction corresponding to the situation is made. Since the soundness of the other vehicle behavior prediction function is judged depending on whether or not it is present, the purpose is to easily diagnose whether or not the other vehicle behavior prediction is operating normally.
- FIG. 2A to 2D are for explaining typical examples of the warning pattern to be determined whether or not the vehicle is in the warning state in the other vehicle behavior prediction device according to the first embodiment or the other vehicle behavior prediction method, respectively.
- Embodiment 1. 1 to 3 are for explaining the other vehicle behavior prediction device or the other vehicle behavior prediction method according to the first embodiment, and FIG. 1 is another vehicle for exchanging information with the other vehicle behavior prediction device.
- the block diagram shown together with the in-vehicle device, FIGS. 2A to 2D, are generated while driving on a two-lane road that is a target for determining whether or not the vehicle is in a warning state in the other vehicle behavior prediction device or the other vehicle behavior prediction method. It is a schematic diagram which shows the typical concrete example of the alert pattern to be obtained.
- FIG. 3 is a flowchart showing the operation of the other vehicle behavior prediction diagnostic device or the other vehicle behavior prediction method.
- the other vehicle behavior prediction diagnosis device 1 is a other vehicle as shown in FIG. 1 when the traveling of the mounted vehicle (own vehicle) is obstructed by the other vehicle. It diagnoses whether or not the prediction information Ip corresponding to the prediction information Ip can be output from the behavior prediction device 12. Therefore, the prediction from the other vehicle condition determination unit 3 that determines whether or not the other vehicle is in a caution state that may interfere with the running of the own vehicle, and the other vehicle behavior prediction device 12 when the warning state is required.
- the prediction function diagnosis unit 2 for diagnosing whether or not the prediction function is sound depending on whether or not there is information Ip output is provided.
- the other vehicle situation determination unit 3 includes a situation estimation unit 31 that estimates the situation of another vehicle, and a warning pattern database 33 (abbreviated as DB in the figure) that stores a state to be watched or a situation pattern (warning pattern). It has a collating unit 32 for collating whether or not the estimated situation matches the alert pattern.
- DB warning pattern database
- the situation estimation unit 31 estimates the traveling status of the other vehicle located in front of the own vehicle based on the other vehicle position information Pv and the object position information Pe obtained from the sensor 13 and the road information Ir obtained from the locator 14. It is configured to do.
- the other vehicle position information Pv is information regarding the positions of other vehicles in front of and around the own vehicle
- the object position information Pe is information regarding the positions of objects including obstacles.
- the road information Ir is information on the measured self-position and the position and shape (particularly, the route) of the road traveling from the map.
- the sensor 13 is assumed to be either a millimeter-wave radar, a camera, or a laser radar that can recognize objects in front or around, or a sensor that is configured by combining these sensors and outputs an integrated recognition result.
- the locator 14 is assumed to recognize the position and shape of a traveling road using a road map from the self-position measured by using a self-positioning technique such as a global positioning satellite system.
- the warning pattern database 33 stores a warning pattern that is a situation that should be watched with a collision unless another vehicle traveling around the vehicle changes lanes or decelerates to its own lane.
- the alert pattern is not limited to the one stored in advance, and may be configured to be updated by version upgrade, machine learning, or the like via a communication path (not shown).
- the collation unit 32 collates the traveling status of the other vehicle estimated by the situation estimation unit 31 with the warning pattern stored in the warning pattern database 33, and determines whether or not the other vehicle is in the above-mentioned (detailed later) warning situation. Is determined. Then, when it is determined that caution is required, the warning signal Sd is configured to be output to the prediction function diagnosis unit 2.
- the prediction function diagnosis unit 2 receives the warning signal Sd from the other vehicle status determination unit 3, it depends on whether or not the prediction information Ip of the content corresponding to the warning signal Sd is output from the other vehicle behavior prediction device 12. , Diagnose whether the other vehicle behavior prediction device or the prediction function is sound. If the prediction information Ip corresponding to the warning signal Sd is not output, it is diagnosed that an abnormality has occurred in the other vehicle behavior prediction device 12, the prediction function, or the transmission path, and the warning signal Wa indicating that there is an abnormality is output to the ECU 11. Notify the control device of the own vehicle such as (Electronic Control Unit). As a result, it is possible to notify the driver, the system administrator, or the like that an abnormality has occurred in the other vehicle behavior prediction device 12, the prediction function, or the transmission path in the own vehicle.
- the control device of the own vehicle such as (Electronic Control Unit).
- the other vehicle behavior prediction device 12 to be diagnosed predicts future behavior according to the driver's judgment, as described in Patent Document 1 or Patent Document 2, for example. This is different from the situation estimation unit 31 of the present application, which determines whether or not the traveling state can be maintained based on the road condition and the traveling condition of the vehicle.
- the own vehicle 10 is traveling in the lane 41 on the two-lane road 4 of the lane 41 and the lane 42, and the judgment target for determining whether or not the traveling state can be maintained is on the adjacent lane 42. It will be described as being another vehicle 50 traveling in front of the vehicle 10.
- the warning pattern 1 is a case where vehicles 51a and 51b, which are slower than the other vehicle 50 or are stopped, are present in front of the lane 42 in which the other vehicle 50 is traveling.
- the road 4 on which the own vehicle 10 is currently traveling has a pattern (road route pattern) in which the own lane (lane 41) and the adjacent lane 42 extend in parallel in the front in the traveling direction.
- the other vehicle position information Pv the other vehicle 50 is in front of the adjacent other lane (lane 42), and further ahead, the vehicles 51a and 51b, which are slower than the other vehicle 50 or are stopped, are present.
- the pattern of existence road condition pattern
- the other vehicle 50 traveling in the lane 42 adjacent to the lane 41 in which the own vehicle 10 is traveling is in front of the vehicle unless the lane is changed to the lane 41 or the vehicle decelerates in the lane 42. It collides with the vehicle 51a. In other words, it is determined that the current running state cannot be maintained and that it matches the warning pattern. At that time, the relative speed and distance between the other vehicle 50 and the vehicle 51a are added to the criterion for determining whether or not the other vehicle 50 matches the caution pattern that requires deceleration with acceleration of a certain threshold value or more. May be good.
- the warning pattern 2 As shown in FIG. 2B, there is a confluence point 42j to the lane 41 in front of the other vehicle 50, that is, the traveling lane (lane 42) of the other vehicle 50 merges into the own lane (lane 41). This is the case when the road conditions are high.
- the road information Ir on the road 4 on which the own vehicle 10 is currently traveling, the lane 42 adjacent to the own lane (lane 41) extends forward in the traveling direction, but the adjacent lane 42 is It corresponds to a road pattern having a merging point 42j that joins the lane 41 ahead.
- the other vehicle position information Pv corresponds to the road condition pattern in which the other vehicle 50 exists in front of the adjacent lane 42.
- the other vehicle 50 matches the caution pattern in which the lane must be changed to the lane 41 or the vehicle must decelerate. Also in this case, for example, the speed of the other vehicle 50 and the distance to the confluence 42j are used as a criterion for determining whether or not the other vehicle 50 matches a caution pattern that requires deceleration with an acceleration of a certain threshold value or higher. You may add it.
- the alert pattern 3 is a case where there is a static obstacle 6 such as a person or an object on the traveling lane (lane 42) of the other vehicle 50.
- the road 4 on which the own vehicle 10 is currently traveling corresponds to a road route pattern in which the own lane (lane 41) and the adjacent lane 42 extend in parallel in the front in the traveling direction. ..
- the other vehicle position information Pv and the object position information Pe correspond to the road condition pattern in which the other vehicle 50 is in front of the adjacent lane 42 and the obstacle 6 is further ahead of the other vehicle 50.
- the road 4 on which the own vehicle 10 is currently traveling corresponds to a road route pattern in which the own lane (lane 41) and the adjacent lane 42 extend in parallel in the front in the traveling direction. ..
- the other vehicle position information Pv and the object position information Pe there is another vehicle 50 in front of the adjacent lane 42, and further ahead, a dynamic object 7 such as a bicycle jumps out so as to cross the lane 42.
- the other vehicle 50 which cannot continue the traveling state due to the forward crossing of the dynamic object 7, matches the warning pattern in which the lane is changed to the lane 41 or the vehicle is decelerated.
- the distance to the position where the other vehicle 50 and the dynamic object 7 have popped out and the speed of the other vehicle 50 are set to a caution pattern that requires deceleration with acceleration of the other vehicle 50 or more. It may be added to the criterion of whether or not it matches.
- the estimation target is a collision, contact, etc. unless the other vehicle 50 traveling in front of the own vehicle 10 decelerates or changes lane to the own lane (lane 41). It is the "situation" of whether or not the vehicle is in a alert state, and is different from the "prediction” in behavior prediction. In other words, instead of predicting future behavior, it only estimates the situation for determining whether the other vehicle 50 in front can maintain the current running, so the number of data required for calculation, hierarchical structure, etc. Is incomparably simpler than behavior prediction. Therefore, while advanced prediction such as behavior prediction cannot be made, the possibility of error is low, and the soundness of behavior prediction can be easily diagnosed.
- the operation of the other vehicle behavior prediction diagnosis device 1 and the other vehicle behavior prediction diagnosis method will be described with reference to the flowchart of FIG.
- the warning pattern is basically set before the other vehicle behavior prediction diagnostic device 1 is installed or installed (formed) (step S10) and started. It is assumed that it is previously stored in the alert pattern database 33. Of course, as described above, it is possible to make appropriate corrections and adjustments by learning during operation.
- the situation estimation unit 31 acquires other vehicle position information Pv and object position information Pe from the sensor 13, and acquires road information Ir from the locator 14 (step S100). Then, based on the acquired information, the traveling conditions (road route pattern and road condition pattern) of each vehicle are estimated from the positions of other vehicles, obstacles, road positions, and shapes (step S120), and the collation unit. Send to 32.
- the collating unit 32 collates the estimated driving condition with the warning pattern stored in the warning pattern database 33, and is in a warning state in which the lane must be changed or decelerated to match the pattern, that is, the estimated driving condition. It is determined whether or not (step S120).
- step S130 When it is determined that there is no match (“No” in step S130), the process returns to step S00. On the other hand, when it is determined that "there is a match" ("yes” in step S130), the process proceeds to the other vehicle behavior prediction diagnosis step after step S200.
- the prediction information Ip from the other vehicle behavior prediction device 12 is acquired (step S200). Then, it is determined whether or not the acquired prediction information Ip includes the warning behavior prediction for changing lanes or decelerating in the traveling condition of the other vehicle determined to match the warning pattern (step S210).
- step S220 If the warning behavior prediction is not included (“No” in step S220), the lane change or deceleration is not predicted even though the situation is warning, and the behavior prediction of other vehicles is abnormal. A warning signal Wa is issued to the effect that there is an abnormality in the behavior prediction of the other vehicle (step S300). If the warning behavior prediction is included (“Yes” in step S220), the lane change or deceleration corresponding to the warning pattern is predicted, and there is no abnormality in the other vehicle behavior prediction (diagnosed as normal). , Return to step S100.
- a scene in which the other vehicle behavior prediction device 12 which is the diagnosis target is assumed to be unpredictable may be used not as the diagnosis target.
- a diagnostic item is used according to the model of the other vehicle behavior prediction device or the type of prediction function. May be able to be selected.
- the prediction function diagnosis unit 2 and the other vehicle status determination unit 3 constituting the other vehicle behavior prediction diagnosis device 1 according to the first embodiment are one equipped with a processor 101 and a storage device 102 as shown in FIG. It can be represented by a configuration consisting of hardware 100.
- the storage device 102 includes a volatile storage device such as a random access memory and a non-volatile auxiliary storage device such as a flash memory. Further, the auxiliary storage device of the hard disk may be provided instead of the flash memory.
- the processor 101 executes the program input from the storage device 102. In this case, the program is input from the auxiliary storage device to the processor 101 via the volatile storage device. Further, the processor 101 may output data such as a calculation result to the volatile storage device of the storage device 102, or may store the data in the auxiliary storage device via the volatile storage device.
- the situation estimation unit 31 it is determined whether or not the other vehicle situation estimated by the situation estimation unit 31 matches the warning pattern stored in the warning pattern database 33, but it is limited to this. There is no such thing. For example, it may be possible to directly determine whether or not another vehicle is in a situation where the vehicle is decelerating or the lane should be changed to the own lane (lane 41) in the situation estimation unit 31. Since this is a situation estimation different from the future behavior prediction, it can be executed by a simple algorithm.
- the other vehicle behavior prediction diagnostic device 1 to be diagnosed does not necessarily have to be mounted on the own vehicle 10, but may be obtained from the outside such as a cloud.
- the behavior prediction is not limited to the contents described in Patent Document 1 or 2, and may have more advanced or various behavior prediction functions.
- the warning pattern is not limited to two lanes, and it goes without saying that it may be one lane, or three or more lanes, and there may be an intersection.
- the soundness of the other vehicle behavior prediction function (for example, the other vehicle behavior prediction device 12) that predicts the future behavior of the other vehicle. It is a device for diagnosing, and the own vehicle 10 is obtained from the traveling road information Ir obtained from the sensor 13 and the locator 14 and the information regarding the positions of surrounding vehicles and objects (other vehicle position information Pv, object position information Pe). Either the other vehicle condition estimation unit (situation estimation unit 31) that estimates the driving condition for each of the other vehicles 50 traveling in front of the vehicle, or the estimated driving condition collides with an object or another vehicle on the road 4.
- the other vehicle condition estimation unit situation estimation unit 31
- Warning state determination unit (verification unit 32, warning pattern database) that determines that the vehicle is in a warning state when decelerating or changing lanes to the lane 41 in which the own vehicle 10 is traveling in order to avoid 33), and whether or not the other vehicle behavior prediction corresponding to the alert state can be received from the other vehicle behavior prediction function (for example, the other vehicle behavior prediction device 12) when the determination result of being in the alert state is received.
- the prediction function diagnosis unit 2 for diagnosing whether or not the other vehicle behavior prediction function (for example, the other vehicle behavior prediction device 12) is sound is provided. Therefore, whether or not the other vehicle behavior prediction is operating normally. Can be easily diagnosed.
- the second vehicle (corresponding to the other vehicle 50) running in front of the first vehicle (corresponding to the own vehicle 10) decelerates in order to avoid a collision with an object or another vehicle on the road 4.
- a warning pattern database 33 that stores a combination of the road route of the road 4 that is assumed to be in a situation where the lane to the lane 41 in which the first vehicle travels and the road condition in front is stored as a warning pattern is provided. If the other vehicle situation determination unit 3 (verification unit 32) determines whether or not the vehicle is in the alert state depending on whether or not the estimated driving condition (by the situation estimation unit 31) matches the alert pattern. , It is possible to easily diagnose whether or not the behavior prediction of another vehicle is operating normally by a simple calculation.
- the alert pattern database 33 there is a vehicle slower than the second vehicle or a stopped vehicle (for example, vehicle 51a, vehicle 51b) in front of the second vehicle (corresponding to another vehicle 50).
- a vehicle slower than the second vehicle or a stopped vehicle for example, vehicle 51a, vehicle 51b
- a stopped vehicle for example, vehicle 51a, vehicle 51b
- an obstacle is in front of the second vehicle.
- At least one of the case where there is a 6 (warning pattern 3) and the case where the intrusion of the dynamic object 7 is detected in front of the second vehicle (warning pattern 4) is stored as a warning pattern. For example, it is possible to easily and surely determine whether or not the situation is typical.
- the alert state determination unit determines whether or not the vehicle is in the alert state depending on whether or not the acceleration required for deceleration exceeds the threshold value when determining the traveling condition corresponding to the situation in which deceleration should be performed. By doing so, it is possible to judge whether or not the situation should be watched more closely according to the actual situation.
- the alert state determination unit is configured to exclude situations that are not predicted by the other vehicle behavior prediction function (for example, the other vehicle behavior prediction device 12) from the determination target of whether or not the vehicle is in the alert state. By doing so, it is possible to prevent a situation that is not predicted by the other vehicle behavior prediction function from being erroneously determined as an abnormality.
- the soundness of the other vehicle behavior prediction function for example, the other vehicle behavior prediction device 12 for predicting the future behavior of the other vehicle is determined. It is a method of diagnosing the own vehicle 10 from the traveling road information Ir obtained from the sensor 13 and the locator 14 and the information regarding the positions of surrounding vehicles and objects (other vehicle position information Pv, object position information Pe). Either the driving condition estimation step (steps S100 to S110) for estimating the driving condition for each of the other vehicles 50 traveling ahead and the estimated driving condition avoid collision with an object or another vehicle on the road 4.
- the warning state determination step (steps S120 to S130) for determining that the vehicle is in the warning state when the vehicle is in a state of decelerating or changing the lane to the lane 41 in which the own vehicle 10 is traveling, and the warning state.
- Other vehicle behavior prediction function depending on whether or not the other vehicle behavior prediction function corresponding to the alert state can be received from the other vehicle behavior prediction function (for example, the other vehicle behavior prediction device 12) when the determination result is received.
- the other vehicle behavior prediction device 12 is configured to include a prediction function diagnosis step (steps S200 to S300) for diagnosing whether or not the vehicle is sound, so whether or not the other vehicle behavior prediction is operating normally. Can be easily diagnosed.
- the second vehicle (corresponding to the other vehicle 50) running in front of the first vehicle (corresponding to the own vehicle 10) decelerates in order to avoid a collision with an object or another vehicle on the road 4.
- a combination of the road route of the road 4, which is assumed to be in a situation where the lane should be changed to the lane 41 in which the first vehicle travels, and the road condition in front of the vehicle is set as a warning pattern (step S10), and the warning pattern is set.
- the state determination step if it is determined whether or not the vehicle is in the alert state based on whether or not the estimated driving condition matches the alert pattern, whether the other vehicle behavior prediction is operating normally by a simple calculation. Whether or not it can be easily diagnosed.
- step S10 if there is a vehicle slower than the other vehicle 50 or the stopped vehicles 51a and 51b in front of the other vehicle 50, the own vehicle 10 is in front of the other vehicle 50. At least one of the following cases: when there is a merging point 42j into the traveling lane (lane 41), when there is an obstacle 6 in front of the other vehicle 50, and when an intrusion of a dynamic object 7 is detected in front of the other vehicle 50. If it is set as a warning pattern, it can be easily and surely determined whether or not it is a typical warning situation.
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
図1~図3は、実施の形態1にかかる他車挙動予測装置、あるいは他車挙動予測方法について説明するためのものであり、図1は他車挙動予測装置を情報のやり取りを行う他の車載装置とともに示すブロック図、図2A~図2Dそれぞれは、他車挙動予測装置、あるいは他車挙動予測方法における、警戒状態にあるか否かの判断対象となる2車線の道路を走行中に生じ得る警戒パターンの典型的な具体例を示す模式図である。そして、図3は他車挙動予測診断装置の動作、あるいは他車挙動予測方法を示すフローチャートである。
警戒パターン1は、図2Aに示すように、他車両50が走行する車線42の前方に他車両50よりも速度が遅い、または停車中の車両51a、51bが存在する場合である。これは、道路情報Irについては、現在自車両10が走行している道路4は、自車線(車線41)と隣接する車線42が進行方向前方において、並行して延びているパターン(道筋パターン)に該当する。そして、他車両位置情報Pvについては、隣接する他車線(車線42)の前方に他車両50があり、さらにその先に、他車両50よりも速度が遅い、または停車中の車両51a、51bが存在しているというパターン(道路状況パターン)に対応する。
警戒パターン2は、図2Bに示すように、他車両50の前方に車線41への合流点42jがある、つまり、他車両50の走行車線(車線42)が自車線(車線41)に合流する道路状況である場合である。これは、道路情報Irについては、現在自車両10が走行している道路4は、自車線(車線41)と隣接する車線42が進行方向前方に向かって延びているが、隣の車線42が前方において車線41に合流する合流点42jを有する道筋パターンに該当する。そして、他車両位置情報Pvについては、隣接する車線42の前方に他車両50が存在しているという道路状況パターンに対応する。
警戒パターン3は、図2Cに示すように、他車両50の走行車線(車線42)上に人、物体等の静的な障害物6がある場合である。これは、道路情報Irについては、現在自車両10が走行している道路4は、自車線(車線41)と隣接する車線42が進行方向前方において、並行して延びている道筋パターンに該当する。そして、他車両位置情報Pv、物***置情報Peについては、隣接する車線42の前方に他車両50があり、さらにその先に、障害物6が存在しているという道路状況パターンに対応する。
警戒パターン4は、図2Dに示すように、他車両50の走行車線(車線42)上に動的物体7(人、車両)が飛び出してきている場合に、他車両50が車線41への車線変更または減速を行わなければならない場合である。これは、道路情報Irについては、現在自車両10が走行している道路4は、自車線(車線41)と隣接する車線42が進行方向前方において、並行して延びている道筋パターンに該当する。そして、他車両位置情報Pv、物***置情報Peについては、隣接する車線42の前方に他車両50があり、さらにその先で、自転車のような動的物体7が車線42を横切るように飛び出してきた状態であることを検知した道路状況パターンに対応する。
Claims (7)
- 他車の将来の挙動を予測する他車挙動予測機能の健全性を診断する装置であって、
センサとロケータから得られた走行中の道路情報と周囲の車両と物体の位置に関する情報から、自車両の前方を走行する他車両のそれぞれについて走行状況を推定する他車状況推定部、
推定された走行状況のいずれかが、道路上の物体または別の車両への衝突を回避するために、減速、あるいは前記自車両が走行する車線への車線変更をすべき状況にあったときに、警戒状態にあると判定する警戒状態判定部、および
前記警戒状態にあるとの判定結果を受けたときに、前記警戒状態に対応する他車挙動予測を前記他車挙動予測機能から受信できたか否かにより、前記他車挙動予測機能が健全か否かを診断する予測機能診断部、
を備えたことを特徴とする他車挙動予測診断装置。 - 第一の車両の前方を走る第二の車両が、道路上の物体または別の車両への衝突を回避するために、減速、あるいは前記第一の車両が走行する車線への車線変更をすべき状況にあると想定される前記道路の道筋と、前方の道路状況の組み合わせを警戒パターンとして記憶する警戒パターンデータベースが設けられ、
前記警戒状態判定部は、前記推定された走行状況が前記警戒パターンに合致するか否かによって、前記警戒状態にあるか否かを判定することを特徴とする請求項1に記載の他車挙動予測診断装置。 - 前記警戒パターンデータベースには、
前記第二の車両の前方に前記第二の車両よりも速度が遅い車両、または停車中の車両がある場合、前記第二の車両の前方に前記第一の車両が走行する車線への合流点がある場合、前記第二の車両の前方に障害物がある場合、および前記第二の車両の前方に動的物体の侵入を検知した場合、の少なくともいずれかが、前記警戒パターンとして記憶されていることを特徴とする請求項2に記載の他車挙動予測診断装置。 - 前記警戒状態判定部は、前記減速をすべき状況に対応する走行状況を判定する際、前記減速に要する加速度が閾値を上回るか否かで前記警戒状態であるか否かを判定することを特徴とする請求項1から3のいずれか1項に記載の他車挙動予測診断装置。
- 前記警戒状態判定部は、前記他車挙動予測機能において予測対象外の状況を、前記警戒状態であるか否かの判定対象から除外することを特徴とする請求項1から4のいずれか1項に記載の他車挙動予測診断装置。
- 他車の将来の挙動を予測する他車挙動予測機能の健全性を診断する方法であって、
センサとロケータから得られた走行中の道路情報と周囲の車両と物体の位置に関する情報から、自車両の前方を走行する他車両のそれぞれについて走行状況を推定する他車走行状況推定ステップ、
前記推定された走行状況のいずれかが、道路上の物体または別の車両への衝突を回避するために、減速、あるいは前記自車両が走行する車線への車線変更をすべき状態であったときに、警戒状態にあると判定する警戒状態判定ステップ、および
前記警戒状態にあるとの判定結果を受けたときに、前記警戒状態に対応する他車挙動予測を前記他車挙動予測機能から受信できたか否かにより、前記他車挙動予測機能が健全か否かを診断する予測機能診断ステップ、
を含むことを特徴とする他車挙動予測診断方法。 - 第一の車両の前方を走る第二の車両が、道路上の物体または別の車両への衝突を回避するために、減速、あるいは前記第一の車両が走行する車線への車線変更をすべき状況にあると想定される前記道路の道筋と、前方の道路状況の組み合わせが警戒パターンとして設定されており、
前記警戒状態判定ステップでは、前記推定された走行状況が前記警戒パターンに合致するか否かによって、前記警戒状態にあるか否かを判定することを特徴とする請求項6に記載の他車挙動予測診断方法。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022558797A JP7438393B2 (ja) | 2020-11-02 | 2020-11-02 | 他車挙動予測診断装置および他車挙動予測診断方法 |
PCT/JP2020/041010 WO2022091400A1 (ja) | 2020-11-02 | 2020-11-02 | 他車挙動予測診断装置および他車挙動予測診断方法 |
CN202080104057.XA CN116157311A (zh) | 2020-11-02 | 2020-11-02 | 其它车辆行为预测诊断装置及其它车辆行为预测诊断方法 |
US18/015,751 US20230219568A1 (en) | 2020-11-02 | 2020-11-02 | Diagnostic device for other-vehicle behavior prediction and diagnostic method for other-vehicle behavior prediction |
DE112020007753.5T DE112020007753T5 (de) | 2020-11-02 | 2020-11-02 | Diagnosevorrichtung für Andere-Fahrzeug-Verhaltensvorhersage und Diagnoseverfahren für die Andere-Fahrzeug-Verhaltensvorhersage |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2020/041010 WO2022091400A1 (ja) | 2020-11-02 | 2020-11-02 | 他車挙動予測診断装置および他車挙動予測診断方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022091400A1 true WO2022091400A1 (ja) | 2022-05-05 |
Family
ID=81382158
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/041010 WO2022091400A1 (ja) | 2020-11-02 | 2020-11-02 | 他車挙動予測診断装置および他車挙動予測診断方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20230219568A1 (ja) |
JP (1) | JP7438393B2 (ja) |
CN (1) | CN116157311A (ja) |
DE (1) | DE112020007753T5 (ja) |
WO (1) | WO2022091400A1 (ja) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011221734A (ja) * | 2010-04-08 | 2011-11-04 | Toshiba Corp | 車両周辺監視装置及び車両周辺監視方法 |
JP2019137321A (ja) * | 2018-02-14 | 2019-08-22 | 日立オートモティブシステムズ株式会社 | 運転制御装置 |
JP2019175492A (ja) * | 2019-06-04 | 2019-10-10 | パイオニア株式会社 | 予測装置、予測システム、予測方法および予測プログラム |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6074553U (ja) | 1983-10-31 | 1985-05-25 | 森 弘喜 | 通気性向上植木鉢 |
EP2942765B1 (en) | 2014-05-07 | 2018-12-26 | Honda Research Institute Europe GmbH | Method and system for predictive lane change assistance, program software product and vehicle |
-
2020
- 2020-11-02 WO PCT/JP2020/041010 patent/WO2022091400A1/ja active Application Filing
- 2020-11-02 CN CN202080104057.XA patent/CN116157311A/zh active Pending
- 2020-11-02 JP JP2022558797A patent/JP7438393B2/ja active Active
- 2020-11-02 US US18/015,751 patent/US20230219568A1/en active Pending
- 2020-11-02 DE DE112020007753.5T patent/DE112020007753T5/de active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011221734A (ja) * | 2010-04-08 | 2011-11-04 | Toshiba Corp | 車両周辺監視装置及び車両周辺監視方法 |
JP2019137321A (ja) * | 2018-02-14 | 2019-08-22 | 日立オートモティブシステムズ株式会社 | 運転制御装置 |
JP2019175492A (ja) * | 2019-06-04 | 2019-10-10 | パイオニア株式会社 | 予測装置、予測システム、予測方法および予測プログラム |
Also Published As
Publication number | Publication date |
---|---|
JP7438393B2 (ja) | 2024-02-26 |
DE112020007753T5 (de) | 2023-09-21 |
JPWO2022091400A1 (ja) | 2022-05-05 |
CN116157311A (zh) | 2023-05-23 |
US20230219568A1 (en) | 2023-07-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10037036B2 (en) | Method and arrangement for determining safe vehicle trajectories | |
JP6524144B2 (ja) | 車両制御システム及び方法、並びに走行支援サーバ | |
JP6375221B2 (ja) | 対象とする交通物体の移動挙動を予測するための方法及びシステム | |
CN110709303B (zh) | 车辆控制装置 | |
JP6985203B2 (ja) | 挙動予測装置 | |
CN106985780B (zh) | 车辆安全辅助*** | |
US11724708B2 (en) | Fail-safe handling system for autonomous driving vehicle | |
CN108137054B (zh) | 传感器测量数据的替换 | |
CN106240565B (zh) | 碰撞减轻和躲避 | |
JP4416020B2 (ja) | 走行計画生成装置 | |
CN109844843B (zh) | 用于检查超车可能性条件的方法 | |
JP4957747B2 (ja) | 車両環境推定装置 | |
JP6838241B2 (ja) | 移動体挙動予測装置 | |
KR20190124119A (ko) | 차량의 안전 전략 제공 장치 및 방법 | |
JP2016212872A (ja) | 対象物体の将来状態を計算により予測する方法の性能を向上するための方法、運転者支援システム、そのような運転者支援システムを備える車両、並びに対応するプログラムの記憶媒体及びプログラム | |
CN113853640B (zh) | 电子控制装置 | |
US11731661B2 (en) | Systems and methods for imminent collision avoidance | |
CN112660156B (zh) | 车辆控制*** | |
JP2007272412A (ja) | 車両の走行安全装置 | |
CN108367752A (zh) | 安全性优化的导航 | |
CN107458337B (zh) | 机动车保护装置的控制 | |
JP7356892B2 (ja) | 車両の走行環境推定方法、及び、走行環境推定システム | |
WO2022091400A1 (ja) | 他車挙動予測診断装置および他車挙動予測診断方法 | |
CN114834477A (zh) | 用于自主车辆的恶意事件检测 | |
WO2024043011A1 (ja) | 車両予測機能の検証 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20959915 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022558797 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 112020007753 Country of ref document: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20959915 Country of ref document: EP Kind code of ref document: A1 |