CN110834631A - Pedestrian avoiding method and device, vehicle and storage medium - Google Patents
Pedestrian avoiding method and device, vehicle and storage medium Download PDFInfo
- Publication number
- CN110834631A CN110834631A CN201911061095.7A CN201911061095A CN110834631A CN 110834631 A CN110834631 A CN 110834631A CN 201911061095 A CN201911061095 A CN 201911061095A CN 110834631 A CN110834631 A CN 110834631A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- pedestrian
- target pedestrian
- target
- driving area
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000003068 static effect Effects 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 8
- 238000013459 approach Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 239000011159 matrix material Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 230000007704 transition 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
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention discloses a pedestrian avoiding method, a pedestrian avoiding device, a vehicle and a storage medium. Wherein the method comprises the following steps: determining the current safe driving area of the vehicle according to the driving track of the vehicle planned by the vehicle route planning system; when a target pedestrian is monitored to be on a pedestrian crossing in front of the running of the vehicle, determining the motion position attribute of the target pedestrian relative to the safe running area; predicting a convergence result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute; and when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian. The invention solves the problem that the pedestrian is not given a gift or the vehicle and the pedestrian are scratched when some pedestrians are about to enter the driving track area or the distance between the pedestrians and the pedestrian is not accurately identified, and realizes the effect that the pedestrian can be given a gift by automatically driving the vehicle.
Description
Technical Field
The embodiment of the invention relates to the field of automobile design, in particular to a pedestrian avoiding method, a pedestrian avoiding device, a vehicle and a storage medium.
Background
The automatic driving function is increasingly developed, more and more companies put forward an automatic driving system in an urban road environment, but from the current development, the urban road automatic driving system still has a large gap in the aspect of functional integrity.
At present, most automatic driving systems can plan tracks and identify pedestrians according to system decision requirements, judge whether pedestrians exist in a driving area of the tracks, and carry out avoidance or wait for the pedestrians to drive after passing.
By adopting the method, the courtesy of the pedestrian can be realized, but the problems that the pedestrian cannot be avoided in time by the vehicle or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle is avoided by the pedestrian can occur under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians and the pedestrian is identified inaccurately.
Disclosure of Invention
The invention provides a pedestrian avoiding method, a pedestrian avoiding device, a vehicle and a storage medium, so that automatic driving of the vehicle can accurately give way to pedestrians.
In a first aspect, an embodiment of the present invention provides a pedestrian avoidance method, including:
determining the current safe driving area of the vehicle according to the driving track of the vehicle planned by the vehicle route planning system;
when monitoring that a target pedestrian exists on a pedestrian crossing in front of the vehicle, determining the motion position attribute of the target pedestrian relative to the safe driving area, wherein the motion position attribute comprises: the safety driving area is in a safety driving area, the safety driving area is out of a static state, the safety driving area is out of a close range, and the safety driving area is out of a far range;
predicting a convergence result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute;
and when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian.
In a second aspect, an embodiment of the present invention further provides a pedestrian avoidance apparatus, including:
the route planning module is used for planning the running track of the vehicle and determining the current safe running area of the vehicle;
the monitoring module is used for monitoring a target pedestrian on a pedestrian crossing in front of the running of the vehicle;
an attribute determination module, configured to determine, when a target pedestrian exists on a pedestrian crossing, a movement position attribute of the target pedestrian with respect to the safe driving area, where the movement position attribute includes: the safety driving area is in a safety driving area, the safety driving area is out of a static state, the safety driving area is out of a close range, and the safety driving area is out of a far range;
the prediction module is used for predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute;
and the avoidance control module is used for controlling the vehicle to avoid the target pedestrian when the intersection result is that the vehicle intersects with the target pedestrian.
In a third aspect, an embodiment of the present invention further provides a vehicle, including:
the vehicle route planning system is used for planning a vehicle running track;
the position sensor is used for sensing the driving position of the vehicle and the position of an obstacle in front of the vehicle, wherein the obstacle in front of the vehicle at least comprises a pedestrian;
the speed sensor is used for sensing the current running speed of the vehicle and the relative speed of an obstacle in front of the vehicle and the vehicle;
a memory for storing executable instructions;
a controller for implementing a pedestrian avoidance method according to any of the embodiments of the present invention when executing executable instructions stored in the memory.
In a fourth aspect, the embodiment of the present invention further provides a readable storage medium, on which executable instructions are stored, where the executable instructions are executed by a processor to implement the pedestrian avoidance method according to any embodiment of the present invention.
According to the invention, whether the target pedestrian and the vehicle are intersected or not is predicted by judging the position relation of the target pedestrian and the safe driving area of the vehicle, and a decision is made as to whether the vehicle avoids the pedestrian or not, so that the problems that the vehicle cannot avoid the pedestrian in time or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle avoids under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians is not accurately identified are solved, and the effect that the pedestrian can be correctly given a gift by automatically driving the vehicle is realized.
Drawings
Fig. 1 is a flowchart of a pedestrian avoidance method according to an embodiment of the present invention;
fig. 2 is a flowchart of a pedestrian avoidance method according to a second embodiment of the present invention;
fig. 3 is a flowchart of a pedestrian avoidance method according to a third embodiment of the present invention;
fig. 4 is a flowchart of a pedestrian avoidance method according to a third embodiment of the present invention;
fig. 5 is a block diagram of a pedestrian avoidance apparatus according to a fourth embodiment of the present invention;
fig. 6 is a block diagram of a vehicle according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a pedestrian avoidance method according to an embodiment of the present invention, where the embodiment is applicable to a situation where a vehicle avoids a pedestrian, and the method may be executed by a pedestrian avoidance device, which may be implemented by software and/or hardware, and the device may be installed on the vehicle.
As shown in fig. 1, the method may specifically include the following steps:
and step 110, determining the current safe driving area of the vehicle according to the driving track planned by the vehicle route planning system.
The route planning system is a vehicle system for automatically planning the running track and navigation of the vehicle according to the origin and the destination by an automatic driving vehicle. The travel track is a motion track of the vehicle during travel. In the embodiment of the invention, the driving track planned by the vehicle route planning system is the driving route of the vehicle. The current safe driving area of the vehicle can be understood as an area where the vehicle is likely to collide with an obstacle during driving, and if no obstacle is present in the area, it can be considered that the vehicle is safe in normal driving.
Specifically, when the driving track of the vehicle is a straight line, the safe driving area of the vehicle may be a rectangular area, the width of the rectangular area may be the sum of the vehicle width and a predetermined width, and the length of the rectangular area may be the sum of the vehicle length and a predetermined length, in a specific example, the vehicle width is 2m and the length is 4m, and the safe driving area of the vehicle may be a rectangular area with the vehicle center as the center, the width is 4m, and the length is 20 m; when the travel locus of the vehicle is a curved line, for example, when the vehicle turns, the safe travel region of the vehicle may be a closed region surrounded by the curved line and a straight line.
And 120, when a target pedestrian is monitored to be on the pedestrian crossing in front of the running of the vehicle, determining the motion position attribute of the target pedestrian relative to the safe running area.
The pedestrian crossing monitoring system comprises a pedestrian crossing monitoring device, a vehicle-mounted position sensor, a vehicle-mounted device and a vehicle-mounted device, wherein the vehicle-mounted position sensor is used for sensing the pedestrian and the position of the pedestrian crossing, the vehicle-mounted device is used for calculating and judging the relative position relation between the pedestrian and the pedestrian crossing, if the position of the pedestrian is located in the area of the pedestrian crossing, the pedestrian is located on the pedestrian crossing, and the pedestrian located on the pedestrian crossing is a target pedestrian. The position sensor may be a camera, radar device, laser device, or other device that can sense the position of the road and obstacles ahead, and combinations thereof.
The motion position attribute can be understood as a motion state and a motion direction of the target pedestrian relative to a safe driving area of the vehicle, the motion state can be static and moving, the motion direction can be approaching and departing, and the motion position attribute can be divided into an area inside the safe driving area, an area outside the safe driving area and an area outside the safe driving area.
And step 130, predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute.
Whether the target pedestrian and the vehicle are intersected or not can be understood as judging whether the target pedestrian is in a safe driving area or not, when the target pedestrian is in the safe driving area of the vehicle, the target pedestrian and the vehicle are considered to be intersected, and when the target pedestrian moves relative to the safe driving area of the vehicle, whether the target pedestrian tends to enter the safe driving area of the vehicle or not needs to be further analyzed. The movement position attribute reflects the movement state and the movement direction of the target pedestrian relative to the safe driving area of the vehicle, so that the intersection result of the target pedestrian and the vehicle in the safe driving area can be predicted by analyzing the movement position attribute.
Specifically, if the attribute of the movement position is in the safe driving area, the target pedestrian and the vehicle are considered to be intersected in the safe driving area;
if the moving position attribute is that the safe driving area is out of the static state, the target pedestrian and the vehicle are considered not to be intersected in the safe driving area;
the moving position attribute is that the moving position is close outside the safe driving area, the intersection result of the target pedestrian and the vehicle in the safe driving area is determined according to the predicted intersection time of the intersection of the vehicle and the target pedestrian, when the predicted intersection time is that the target pedestrian walks into the safe driving area, the target pedestrian and the vehicle are considered to be intersected in the safe driving area, otherwise, the target pedestrian and the vehicle are considered not to be intersected in the safe driving area;
and if the motion position attribute is that the vehicle is far away from the safe driving area, the target pedestrian and the vehicle are considered not to be intersected in the safe driving area.
And 140, controlling the vehicle to avoid the target pedestrian when the intersection result is that the vehicle and the target pedestrian intersect.
If the predicted intersection result is that the vehicle and the target pedestrian intersect, the possibility that the vehicle and the target pedestrian collide or are scratched is very high, and therefore the vehicle needs to give a gift to the target pedestrian.
According to the embodiment of the invention, whether the target pedestrian and the vehicle are intersected or not is predicted by judging the position relation of the target pedestrian and the safe driving area of the vehicle, and a decision is made whether the vehicle avoids the pedestrian or not, so that the problems that the vehicle cannot avoid the pedestrian in time or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle avoids under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians and the pedestrian is not accurately identified are solved, and the effect that the pedestrian can be accurately given a good gift by automatically driving the vehicle is realized.
Example two
Fig. 2 is a flowchart of a pedestrian avoidance method according to a second embodiment of the present invention. On the basis of the above embodiments, the present embodiment further optimizes the pedestrian avoidance method. Correspondingly, as shown in fig. 2, the method of the embodiment specifically includes:
The grid image refers to an image which is discretized in both space and brightness, a grid image can be considered as a matrix, any element in the matrix corresponds to a point in the image, the corresponding value of the element corresponds to the gray value of the point, and the grid map divides the environment into a series of grids, wherein each grid is given a possible value to represent the probability that the grid is occupied.
In the embodiment of the invention, the vehicle center can select the vehicle center of mass position, a grid map is constructed by taking the global coordinate position corresponding to the center point as the center, and the area where the pedestrian crossing is located is projected into the grid map, wherein the global coordinate position is the coordinate position in the coordinate system adopted when the position sensor acquires the position information.
Projecting the global coordinate positions of four vertexes of a parallelogram where a pedestrian crossing is located, which are acquired by a position sensor, to a grid map with a vehicle as a central coordinate system, wherein a coordinate transformation formula is as follows:
wherein (X)V，YV) The coordinate position of the pedestrian crosswalk vertex is the global coordinate position of the vehicle, (X, Y) is the global coordinate position of the pedestrian crosswalk vertex, (X, Y) is the coordinate position of the pedestrian crosswalk vertex under the grid map, and theta is the included angle between the grid coordinate system and the global coordinate system.
And step 203, acquiring the walking position of the pedestrian in front of the vehicle sensed by the position sensor, and projecting the walking position to the grid position in the grid map.
The walking position can be understood as the position of the pedestrian in front of the vehicle, which is sensed by the position sensor, and the walking position of the pedestrian can be mapped into the grid map according to the grid map and the coordinate transformation method established in step 202. Specifically, the grid position of the walking position can be expressed as (x)p，yp)。
And 204, judging whether the grid where the pedestrian is located is in the grid area of the pedestrian crossing, and determining whether the pedestrian crossing in front of the vehicle has the target pedestrian.
Judging whether the grid position coordinates are in the area of the pedestrian crossing in the grid map, determining whether the pedestrian is on the pedestrian crossing, and if the pedestrian is on the pedestrian crossing, determining the pedestrian as the target pedestrian; otherwise, the crosswalk is considered to have no pedestrian.
Specifically, when (x)p，yp) Satisfies the following conditions:
the pedestrian is located in the crosswalk area. Wherein x ismin，xmax，ymin，ymaxThe maximum and minimum coordinate values of the parallelogram region where the pedestrian crosswalk is located.
If the target pedestrian exists, executing step 205; if there is no target pedestrian, step 201 is executed to monitor the road condition in front of the vehicle again until the vehicle stops running.
And step 205, judging whether the walking position of the target pedestrian is in the safe driving area.
Specifically, when the walking position of the target pedestrian is in the safe driving area of the vehicle, determining that the attribute of the movement position is in the safe driving area, and executing step 206; and when the current walking position of the target pedestrian is outside the safe driving area of the vehicle, performing the following steps to continuously judge the motion position attribute of the target pedestrian relative to the safe driving area, and executing the step 207.
And step 207, acquiring the relative speed of the vehicle and the target pedestrian sensed by the speed sensor, and determining the target walking speed of the target pedestrian according to the relative speed.
The speed sensor can be a camera, a radar device, a laser device or other devices capable of sensing the position of a road and an obstacle in front and a combination thereof, and is arranged on the vehicle. The speed sensor senses that the speed of the target pedestrian is possibly the speed of the target pedestrian relative to the vehicle, but not the real walking speed of the target pedestrian relative to the ground, so that the target walking speed of the target pedestrian needs to be calculated through the relative speed.
Specifically, the relative speed of the vehicle and the target pedestrian sensed by the speed sensor and the current running speed of the vehicle are obtained, and the difference value between the current running speed and the relative speed of the vehicle is determined as the measured running speed of the target pedestrian. The measured walking speed can be understood as the walking speed of the pedestrian obtained by simply calculating the relative speed sensed by the speed sensor, including sensing the noise during measurement. The calculation formula is as follows: :
vz＝vr-vvehicle，
wherein v isrIs the relative speed of the vehicle and the target pedestrian, vvehicleIs the current driving speed, v, of the vehiclezThe measured walking speed of the target pedestrian.
Optionally, the target walking speed of the target pedestrian is predicted by combining kalman filtering with the measured walking speed of the target pedestrian. Kalman filtering (Kalman filtering) is an algorithm that uses a linear system state equation to optimally estimate the state of a system by inputting and outputting observation data through the system. The optimal estimation can also be seen as a filtering process, since the observed data includes the effects of noise and interference in the system. The target walking speed can be understood as the walking speed of the target pedestrian obtained after the measured walking speed is filtered, and is closer to the real walking speed of the target pedestrian. The filtering process is as follows:
where A is the state transition matrix, B is the control input gain matrix, ukIs the control quantity of the system at the moment K, K is a filter gain matrix, is the intermediate calculation result of the filtering, called the kalman gain, or the kalman coefficient, H is a conversion matrix from the state variable to the measurement (observation),is the predicted speed of the target pedestrian,is the target walking speed of the target pedestrian.
And step 208, determining the movement position attribute of the target pedestrian relative to the safe driving area according to the target walking speed.
Optionally, it is first determined whether the target walking speed of the target pedestrian is zero.
And if the target walking speeds of the target pedestrians in a certain continuous period are all 0, the target pedestrians are considered to be in a static state, and if not, the target pedestrians are considered to be in a human motion state. The interval time of each cycle may be set in advance, and may be set to a reasonable value such as 20ms or 50 ms. And when the moving state of the target pedestrian is static, determining that the moving position attribute of the target pedestrian is static outside the safe driving area.
If the target walking speed of the target pedestrian is not 0, whether the walking direction of the target pedestrian is the same as the driving direction of the vehicle can be judged.
Optionally, whether the walking direction of the target pedestrian is the same as the driving direction of the vehicle is judged according to the positive and negative values of the target walking speed of the target pedestrian. When the target walking speed of the target pedestrian is a negative value, the walking direction of the target pedestrian is the same as the driving direction of the vehicle, and the movement position attribute of the target pedestrian relative to the safe driving area is considered to be that the target pedestrian is far away from the safe driving area; when the target walking speed of the target pedestrian is a positive value, the walking direction of the target pedestrian is opposite to the driving direction of the vehicle, namely the walking direction of the target pedestrian is different from the driving direction of the vehicle, and at this moment, the moving position attribute of the target pedestrian relative to the safe driving area is considered to be that the target pedestrian is close to the outside of the safe driving area. Wherein, the walking direction of the target pedestrian and the driving direction of the vehicle can form a certain included angle.
And step 209, predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute.
And step 210, when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian.
The embodiment of the invention constructs the grid map by taking the vehicle as the center, projects the walking position of the pedestrian into the grid map, judges whether the grid where the pedestrian is located is in the grid area of the pedestrian crossing, is the target pedestrian when the grid where the pedestrian is located is in the grid area of the pedestrian crossing, further judges whether the walking position of the target pedestrian is in the safe driving area of the vehicle, and subdivides the motion position attribute of the target pedestrian into the static state outside the safe driving area, the far away outside the safe driving area and the close outside the safe driving area when the walking position of the target pedestrian is outside the safe driving area of the vehicle.
EXAMPLE III
Fig. 3 is a flowchart of a pedestrian avoidance method according to a third embodiment of the present invention. On the basis of the above embodiments, the present embodiment further optimizes the pedestrian avoidance method. Correspondingly, as shown in fig. 3, the method of the embodiment specifically includes:
step 301, determining the current safe driving area of the vehicle according to the driving track planned by the vehicle route planning system.
Step 302, when a target pedestrian is monitored to be on a pedestrian crossing in front of the vehicle, determining the motion position attribute of the target pedestrian relative to the safe driving area.
After determining the motion location attribute, steps 303 through 305 are performed according to the different motion location attributes.
And step 303, when the motion position attribute is in the safe driving area, determining that the intersection result is that the vehicle intersects with the target pedestrian.
Specifically, when the motion position attribute is within the safe driving area, it may be understood that the target pedestrian has intersected with the driving track of the vehicle and enters the safe driving area of the vehicle, and therefore the intersection result is considered that the vehicle intersects with the target pedestrian.
And step 304, when the motion position attribute is static outside the safe driving area or far away from the safe driving area, determining that the vehicle does not intersect with the target pedestrian according to the intersection result.
Specifically, when the motion position attribute is that the vehicle is stationary outside the safe driving area or is far away from the safe driving area, it can be understood that the walking track of the pedestrian and the driving track of the vehicle do not intersect, and the pedestrian does not enter the safe driving area of the vehicle, so that the intersection result is considered that the vehicle and the target pedestrian do not intersect.
And 305, when the motion position attribute is that the vehicle approaches outside the safe driving area, determining an intersection result of the target pedestrian and the vehicle in the safe driving area according to the predicted intersection time of the vehicle and the target pedestrian.
Specifically, when the moving position attribute is that the target pedestrian approaches the safe driving area, although the target pedestrian does not enter the safe driving area, the moving trend of the target pedestrian is that the target pedestrian approaches the vehicle, and after a certain time interval, the target pedestrian may meet the vehicle, so that further analysis is required. As shown in fig. 4, the method specifically includes:
The estimated walking track can be understood as a route which is predicted by the target pedestrian according to the target walking speed and the walking direction of the target pedestrian. The estimated intersection point can be understood as an intersection point of a vehicle running track and an estimated target pedestrian running track, and if a vehicle collides with a pedestrian, the collision point is at a position near the intersection point.
And 3502, determining estimated driving time from the vehicle to the estimated junction point according to the driving track from the vehicle to the estimated junction point and the current driving speed of the vehicle.
The estimated driving time can be understood as the time taken for the vehicle to normally drive to the estimated intersection point according to the current driving speed.
Specifically, the estimated intersection point position of the vehicle running track and the target pedestrian running track is calculated in the grid map, the length from the vehicle to the estimated intersection point running track is obtained, and a track length calculation formula is as follows:
wherein (x)i，yi) And (4) planning any point on the running track for the vehicle system, wherein s is the length from the vehicle to the estimated junction running track.
Determining the estimated driving time from the vehicle to the estimated junction according to the current driving speed of the vehicle and the length of the driving track from the vehicle to the estimated junction:
t＝s/vvehicle，
and t is the estimated driving time from the vehicle to the estimated junction.
The walking predicted position can be understood as the position where the target pedestrian walks along the current walking direction according to the target walking speed and arrives after the estimated time of driving. The calculation formula is as follows:
wherein the content of the first and second substances,
the initial state of the target pedestrian occupies the grid position of the grid map, and β is the included angle between the walking direction of the target pedestrian and the driving direction of the vehicle.
When the walking predicted position of the target pedestrian is in the safe driving area, the target pedestrian and the vehicle are considered to be easy to collide, and step 3505 is executed; when the walking predicted position of the target pedestrian is not within the safe driving area, step 3506 is performed.
And step 306, when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian.
The embodiment of the invention predicts whether the target pedestrian and the vehicle are intersected or not by judging the motion position attribute of the target pedestrian, further refines and analyzes the condition that the motion position attribute is close to the outside of the safe driving area, determines the estimated intersection point of the vehicle and the target pedestrian according to the estimated driving track of the vehicle and the target pedestrian, and predicts whether the target pedestrian and the vehicle are intersected or not according to the current driving speed of the vehicle and the target driving speed of the target pedestrian, thereby solving the problems that the vehicle cannot avoid the pedestrian or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle avoids under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians and the target pedestrian is not accurately recognized, and realizing the effect that the automatic driving vehicle can correctly give the gift to the pedestrian.
Example four
An embodiment of the present invention provides a pedestrian avoidance apparatus, which is capable of executing a pedestrian avoidance method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method, and fig. 5 is a structural block diagram of the pedestrian avoidance apparatus provided in the fourth embodiment of the present invention, and as shown in fig. 5, the apparatus includes: a route planning module 410, a monitoring module 420, an attribute determination module 430, a prediction module 440, and a avoidance control module 450.
And the route planning module 410 is used for planning the running track of the vehicle and determining the current safe running area of the vehicle.
And the monitoring module 420 is used for monitoring the target pedestrian on the pedestrian crossing in front of the vehicle.
An attribute determining module 430, configured to determine, when a target pedestrian exists on the pedestrian crossing, a movement position attribute of the target pedestrian with respect to the safe driving area, where the movement position attribute includes: the driving mode is a mode including being stationary inside the safe driving area, outside the safe driving area, close outside the safe driving area and far outside the safe driving area.
And the predicting module 440 is used for predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute.
And an avoidance control module 450, configured to control the vehicle to avoid the target pedestrian when the intersection result is that the vehicle intersects with the target pedestrian.
According to the embodiment of the invention, whether the target pedestrian and the vehicle are intersected or not is predicted by judging the position relation of the target pedestrian and the safe driving area of the vehicle, and a decision is made whether the vehicle avoids the pedestrian or not, so that the problems that the vehicle cannot avoid the pedestrian in time or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle avoids under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians and the pedestrian is not accurately identified are solved, and the effect that the pedestrian can be accurately given a good gift by automatically driving the vehicle is realized.
Optionally, the monitoring module 420 is specifically configured to:
constructing a grid map by taking a vehicle as a center, acquiring a region where a pedestrian crossing is located and sensed by a position sensor, and projecting the region where the pedestrian crossing is located into the grid map, wherein the position sensor is arranged on the vehicle;
acquiring the walking position of a pedestrian in front of the vehicle sensed by a position sensor, and projecting the walking position to a grid position in a grid map;
and if the grid position is in the projection area of the crosswalk, determining that the target pedestrian exists on the crosswalk in front of the vehicle in the driving process.
Optionally, the attribute determining module 430 includes:
a first attribute determination unit, configured to determine, when the walking position of the target pedestrian is within the safe driving area, that the attribute of the moving position of the target pedestrian relative to the safe driving area is within the safe driving area;
the speed determining unit is used for acquiring the relative speed of the vehicle and the target pedestrian sensed by the speed sensor when the walking position of the target pedestrian is not in the safe driving area, and determining the target walking speed of the target pedestrian according to the relative speed;
and the second attribute determining unit is used for determining the motion position attribute of the target pedestrian relative to the safe driving area according to the target walking speed.
Optionally, the speed determination unit is specifically configured to:
determining the difference value between the current running speed and the relative speed of the vehicle as the measured running speed of the target pedestrian;
and predicting the target walking speed of the target pedestrian by adopting Kalman filtering in combination with the measurement of the walking speed.
Optionally, the second attribute determining unit is specifically configured to:
if the target walking speed is equal to 0, determining that the attribute of the moving position of the target pedestrian relative to the safe driving area is static outside the safe driving area;
if the target walking speed is not equal to 0, determining that the moving position attribute of the target pedestrian relative to the safe driving area is far away from the safe driving area when the walking direction of the target pedestrian is the same as the driving direction of the vehicle; if not, then,
and determining the moving position attribute of the target pedestrian relative to the safe driving area as the approaching outside the safe driving area.
Optionally, the prediction module 440 includes:
the first result determining unit is used for determining that the intersection result is that the vehicle intersects with the target pedestrian when the motion position attribute is in the safe driving area;
the second result determining unit is used for determining that the vehicle does not intersect with the target pedestrian according to the intersection result when the motion position attribute is static outside the safe driving area or far away outside the safe driving area;
and the third result determining unit is used for determining the intersection result of the target pedestrian and the vehicle in the safe driving area according to the predicted intersection time of the intersection of the vehicle and the target pedestrian when the motion position attribute is that the vehicle approaches the outside of the safe driving area.
Optionally, the third result determining unit is specifically configured to:
when the motion position attribute is that the safe driving area is out of the area and is close to the safe driving area, determining the estimated walking track of the target pedestrian, and determining an estimated intersection point of the vehicle and the target pedestrian according to the walking track and the estimated walking track;
determining the estimated time of the vehicle to the estimated junction according to the driving track from the vehicle to the estimated junction and the current driving speed of the vehicle;
determining a walking predicted position of the target pedestrian according to the estimated driving time and the predetermined target walking speed of the target pedestrian;
if the walking predicted position is in the safe driving area, determining that the intersection result is that the vehicle and the target pedestrian are intersected; otherwise, determining that the vehicle does not intersect with the target pedestrian according to the intersection result.
According to the embodiment of the invention, the position, the walking speed and the walking direction of the target pedestrian are monitored, the attribute of the moving position of the target pedestrian is subjected to detailed analysis, the intersection result of the target pedestrian and the vehicle is predicted according to the attribute of the moving position according to the condition, the problems that the vehicle cannot avoid the pedestrian in time or the vehicle and the pedestrian are scratched or the pedestrian is far away from the vehicle but the vehicle avoids the pedestrian under the condition that some pedestrians are about to enter the driving track area or the distance between the pedestrians and the vehicle is not accurately recognized are solved, and the effect that the pedestrians can be given good care to the automatically driven vehicle is realized.
EXAMPLE five
Fig. 6 is a block diagram of a vehicle according to a fifth embodiment of the present invention, and as shown in fig. 6, the vehicle includes: a vehicle route planning system 510, a position sensor 520, a speed sensor 530, a memory 540, and a controller 550; the number of controllers 550 may be one or more, and one controller 550 is illustrated in fig. 6; the vehicle routing system 510, the position sensor 520, the speed sensor 530, the memory 540, and the controller 550 in the vehicle may be connected by a bus or other means, as exemplified by a bus connection in fig. 6.
And a vehicle route planning system 510 for planning a vehicle driving track.
And a position sensor 520 for sensing a driving position of the vehicle and a position of an obstacle in front of the vehicle, wherein the obstacle in front of the vehicle at least comprises a pedestrian.
A speed sensor 530 for sensing a current traveling speed of the vehicle and a relative speed of an obstacle in front of the vehicle and the vehicle.
A memory 540 for storing executable instructions.
A controller 550 for executing the executable instructions stored in the memory.
The memory 540 is a readable storage medium and can be used for storing software programs, executable programs, and modules, such as program instructions/modules corresponding to the pedestrian avoidance method in the embodiment of the present invention (for example, the route planning module 410, the monitoring module 420, the attribute determination module 430, the prediction module 440, and the avoidance control module 450 in the pedestrian avoidance apparatus). The controller 550 executes various functional applications and data processing of the vehicle by executing software programs, instructions and modules stored in the memory 540, so as to implement the pedestrian avoidance method described above.
The memory 540 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 540 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 540 may further include memory located remotely from the controller 550, which may be connected to the vehicle over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
EXAMPLE six
An embodiment of the present invention further provides a storage medium storing executable instructions, where the executable instructions are executed by a processor to perform a pedestrian avoidance method, where the method includes:
determining the current safe driving area of the vehicle according to the driving track of the vehicle planned by the vehicle route planning system;
when a target pedestrian is monitored to exist on a pedestrian crossing in front of the running vehicle, determining the motion position attribute of the target pedestrian relative to a safe running area, wherein the motion position attribute comprises: the safety driving area is in a safety driving area, the safety driving area is out of a static state, the safety driving area is out of a close range, and the safety driving area is out of a far range;
predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute;
and when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian.
Of course, the storage medium storing the executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the pedestrian avoidance method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A pedestrian avoidance method, comprising:
determining the current safe driving area of the vehicle according to the driving track of the vehicle planned by the vehicle route planning system;
when monitoring that a target pedestrian exists on a pedestrian crossing in front of the vehicle, determining the motion position attribute of the target pedestrian relative to the safe driving area, wherein the motion position attribute comprises: the safety driving area is in a safety driving area, the safety driving area is out of a static state, the safety driving area is out of a close range, and the safety driving area is out of a far range;
predicting a convergence result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute;
and when the intersection result is that the vehicle and the target pedestrian intersect, controlling the vehicle to avoid the target pedestrian.
2. The method of claim 1, wherein said monitoring for a target pedestrian on a crosswalk ahead of the vehicle comprises:
constructing a grid map by taking the vehicle as a center, acquiring the area of the pedestrian crossing sensed by a position sensor, and projecting the area of the pedestrian crossing into the grid map, wherein the position sensor is arranged on the vehicle;
acquiring the walking position of a pedestrian in front of the vehicle sensed by the position sensor, and projecting the walking position to a grid position in the grid map;
and if the grid position is in the projection area of the pedestrian crossing, determining that the pedestrian crossing in front of the vehicle runs has the target pedestrian.
3. The method of claim 1, wherein said determining a motion location attribute of said target pedestrian relative to said safe driving area comprises:
if the walking position of the target pedestrian is in the safe driving area, determining that the attribute of the movement position of the target pedestrian relative to the safe driving area is in the safe driving area;
otherwise, acquiring the relative speed of the vehicle and the target pedestrian sensed by the speed sensor, and determining the target walking speed of the target pedestrian according to the relative speed;
and determining the motion position attribute of the target pedestrian relative to the safe driving area according to the target walking speed.
4. The method of claim 3, wherein said determining a target walking speed of said target pedestrian from said relative speed comprises:
determining a difference value between the current running speed of the vehicle and the relative speed as a measured running speed of the target pedestrian;
and predicting the target walking speed of the target pedestrian by adopting Kalman filtering and combining the measured walking speed.
5. The method of claim 3, wherein said determining said motion location attribute of said target pedestrian relative to said safe driving area based on said target walking speed comprises:
if the target walking speed is equal to 0, determining that the attribute of the moving position of the target pedestrian relative to the safe driving area is static outside the safe driving area;
if the target walking speed is not equal to 0, when the walking direction of the target pedestrian is the same as the driving direction of the vehicle, determining that the attribute of the movement position of the target pedestrian relative to the safe driving area is that the target pedestrian is far away from the safe driving area; if not, then,
and determining that the attribute of the movement position of the target pedestrian relative to the safe driving area is that the target pedestrian approaches outside the safe driving area.
6. The method according to any one of claims 1-5, wherein the predicting the result of the intersection of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute comprises:
when the motion position attribute is in a safe driving area, determining that the intersection result is that the vehicle and the target pedestrian intersect;
when the motion position attribute is static outside a safe driving area or far away from the safe driving area, determining that the intersection result is that the vehicle does not intersect with the target pedestrian;
and when the motion position attribute is that the vehicle approaches outside the safe driving area, determining the intersection result of the target pedestrian and the vehicle in the safe driving area according to the predicted intersection time of the intersection of the vehicle and the target pedestrian.
7. The method of claim 6, wherein determining the interaction result of the target pedestrian and the vehicle in the safe driving area according to the predicted intersection time of the vehicle and the target pedestrian comprises:
determining an estimated walking track of the target pedestrian, and determining an estimated intersection point of the vehicle and the target pedestrian according to the walking track and the estimated walking track;
determining the estimated driving time from the vehicle to the estimated junction point according to the driving track from the vehicle to the estimated junction point and the current driving speed of the vehicle;
determining a walking predicted position of the target pedestrian according to the estimated driving time and the predetermined target walking speed of the target pedestrian;
if the walking predicted position is in the safe driving area, determining that the intersection result is that the vehicle intersects with the target pedestrian; otherwise, determining that the vehicle does not intersect with the target pedestrian according to the intersection result.
8. A pedestrian avoidance apparatus, comprising:
the route planning module is used for planning the running track of the vehicle and determining the current safe running area of the vehicle;
the monitoring module is used for monitoring a target pedestrian on a pedestrian crossing in front of the running of the vehicle;
an attribute determination module, configured to determine, when a target pedestrian exists on a pedestrian crossing, a movement position attribute of the target pedestrian with respect to the safe driving area, where the movement position attribute includes: the safety driving area is in a safety driving area, the safety driving area is out of a static state, the safety driving area is out of a close range, and the safety driving area is out of a far range;
the prediction module is used for predicting the intersection result of the target pedestrian and the vehicle in the safe driving area according to the motion position attribute;
and the avoidance control module is used for controlling the vehicle to avoid the target pedestrian when the intersection result is that the vehicle intersects with the target pedestrian.
9. A vehicle, characterized by comprising:
the vehicle route planning system is used for planning a vehicle running track;
the position sensor is used for sensing the driving position of the vehicle and the position of an obstacle in front of the vehicle, wherein the obstacle in front of the vehicle at least comprises a pedestrian;
the speed sensor is used for sensing the current running speed of the vehicle and the relative speed of an obstacle in front of the vehicle and the vehicle;
a memory for storing executable instructions;
a controller for implementing the method of any one of claims 1 to 7 when executing executable instructions stored in the memory.
10. A readable storage medium having stored thereon executable instructions, which when executed by a processor, implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911061095.7A CN110834631A (en) | 2019-11-01 | 2019-11-01 | Pedestrian avoiding method and device, vehicle and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911061095.7A CN110834631A (en) | 2019-11-01 | 2019-11-01 | Pedestrian avoiding method and device, vehicle and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110834631A true CN110834631A (en) | 2020-02-25 |
Family
ID=69575991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911061095.7A Pending CN110834631A (en) | 2019-11-01 | 2019-11-01 | Pedestrian avoiding method and device, vehicle and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110834631A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111391828A (en) * | 2020-03-13 | 2020-07-10 | 南京航空航天大学 | Method for planning vehicle collision avoidance track under pedestrian crossing working condition |
| CN111409631A (en) * | 2020-04-10 | 2020-07-14 | 新石器慧通（北京）科技有限公司 | Vehicle running control method and device, vehicle and storage medium |
| CN111497840A (en) * | 2020-04-27 | 2020-08-07 | 清华大学 | Calculation method and safety evaluation system for vehicle-pedestrian collision risk domain |
| CN111572542A (en) * | 2020-04-30 | 2020-08-25 | 汉腾新能源汽车科技有限公司 | Intelligent control system and method for avoiding pedestrians |
| CN112498342A (en) * | 2020-11-26 | 2021-03-16 | 潍柴动力股份有限公司 | Pedestrian collision prediction method and system |
| CN112729320A (en) * | 2020-12-22 | 2021-04-30 | 中国第一汽车股份有限公司 | Method, device and equipment for constructing obstacle map and storage medium |
| CN113341941A (en) * | 2021-08-04 | 2021-09-03 | 北京三快在线科技有限公司 | Control method and device of unmanned equipment |
| CN114312836A (en) * | 2021-12-24 | 2022-04-12 | 阿波罗智联(北京)科技有限公司 | Method, device, equipment and storage medium for automatically driving vehicle to give way to pedestrians |
| CN114379587A (en) * | 2021-12-28 | 2022-04-22 | 阿波罗智联(北京)科技有限公司 | Method and device for avoiding pedestrian in automatic driving |
| CN114771514A (en) * | 2022-06-14 | 2022-07-22 | 小米汽车科技有限公司 | Vehicle running control method, device, equipment, medium, chip and vehicle |
| CN115206111A (en) * | 2022-06-23 | 2022-10-18 | 北京顺捷通畅交通设施工程有限公司 | Traffic signal lamp control method, system and storage medium |
| CN115331436A (en) * | 2022-08-04 | 2022-11-11 | 西安理工大学 | Road section automatic driving automobile movement planning method considering pedestrian safety |
| CN115329126A (en) * | 2022-10-14 | 2022-11-11 | 南通启锦智能科技有限公司 | Intelligent data storage method of vehicle event data recorder |
| WO2023082850A1 (en) * | 2021-11-11 | 2023-05-19 | 中国第一汽车股份有限公司 | Pedestrian trajectory prediction method and apparatus, and storage medium |
| CN116223056A (en) * | 2022-12-14 | 2023-06-06 | 清华大学 | Virtual collision test method, apparatus, device, storage medium, and program product |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014204383A1 (en) * | 2014-03-11 | 2015-09-17 | Conti Temic Microelectronic Gmbh | Driver assistance system for object recognition and procedures |
| CN107226088A (en) * | 2016-03-25 | 2017-10-03 | 松下电器（美国）知识产权公司 | Controller, driving control method and program |
| DE102016124157A1 (en) * | 2016-12-13 | 2018-06-14 | Valeo Schalter Und Sensoren Gmbh | Determining a braking necessity for avoiding a collision of a motor vehicle with a pedestrian |
| US20190118810A1 (en) * | 2016-11-28 | 2019-04-25 | drive.ai Inc. | Method for influencing entities at a roadway intersection |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110293968A (en) * | 2019-06-18 | 2019-10-01 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
-
2019
- 2019-11-01 CN CN201911061095.7A patent/CN110834631A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014204383A1 (en) * | 2014-03-11 | 2015-09-17 | Conti Temic Microelectronic Gmbh | Driver assistance system for object recognition and procedures |
| CN107226088A (en) * | 2016-03-25 | 2017-10-03 | 松下电器（美国）知识产权公司 | Controller, driving control method and program |
| US20190118810A1 (en) * | 2016-11-28 | 2019-04-25 | drive.ai Inc. | Method for influencing entities at a roadway intersection |
| DE102016124157A1 (en) * | 2016-12-13 | 2018-06-14 | Valeo Schalter Und Sensoren Gmbh | Determining a braking necessity for avoiding a collision of a motor vehicle with a pedestrian |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110293968A (en) * | 2019-06-18 | 2019-10-01 | 百度在线网络技术（北京）有限公司 | Control method, device, equipment and the readable storage medium storing program for executing of automatic driving vehicle |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111391828A (en) * | 2020-03-13 | 2020-07-10 | 南京航空航天大学 | Method for planning vehicle collision avoidance track under pedestrian crossing working condition |
| CN111409631A (en) * | 2020-04-10 | 2020-07-14 | 新石器慧通（北京）科技有限公司 | Vehicle running control method and device, vehicle and storage medium |
| WO2021217752A1 (en) * | 2020-04-27 | 2021-11-04 | 清华大学 | Vehicle-pedestrian collision risk region calculation method and safety evaluation system |
| CN111497840A (en) * | 2020-04-27 | 2020-08-07 | 清华大学 | Calculation method and safety evaluation system for vehicle-pedestrian collision risk domain |
| CN111572542A (en) * | 2020-04-30 | 2020-08-25 | 汉腾新能源汽车科技有限公司 | Intelligent control system and method for avoiding pedestrians |
| CN112498342A (en) * | 2020-11-26 | 2021-03-16 | 潍柴动力股份有限公司 | Pedestrian collision prediction method and system |
| CN112729320B (en) * | 2020-12-22 | 2022-05-17 | 中国第一汽车股份有限公司 | Method, device and equipment for constructing obstacle map and storage medium |
| CN112729320A (en) * | 2020-12-22 | 2021-04-30 | 中国第一汽车股份有限公司 | Method, device and equipment for constructing obstacle map and storage medium |
| CN113341941A (en) * | 2021-08-04 | 2021-09-03 | 北京三快在线科技有限公司 | Control method and device of unmanned equipment |
| WO2023082850A1 (en) * | 2021-11-11 | 2023-05-19 | 中国第一汽车股份有限公司 | Pedestrian trajectory prediction method and apparatus, and storage medium |
| CN114312836A (en) * | 2021-12-24 | 2022-04-12 | 阿波罗智联(北京)科技有限公司 | Method, device, equipment and storage medium for automatically driving vehicle to give way to pedestrians |
| CN114379587A (en) * | 2021-12-28 | 2022-04-22 | 阿波罗智联(北京)科技有限公司 | Method and device for avoiding pedestrian in automatic driving |
| CN114379587B (en) * | 2021-12-28 | 2024-05-24 | 阿波罗智联(北京)科技有限公司 | Method and device for avoiding pedestrians in automatic driving |
| CN114771514A (en) * | 2022-06-14 | 2022-07-22 | 小米汽车科技有限公司 | Vehicle running control method, device, equipment, medium, chip and vehicle |
| CN114771514B (en) * | 2022-06-14 | 2022-09-02 | 小米汽车科技有限公司 | Vehicle running control method, device, equipment, medium, chip and vehicle |
| CN115206111B (en) * | 2022-06-23 | 2024-02-20 | 北京顺捷通畅交通设施工程有限公司 | Traffic signal lamp control method, system and storage medium |
| CN115206111A (en) * | 2022-06-23 | 2022-10-18 | 北京顺捷通畅交通设施工程有限公司 | Traffic signal lamp control method, system and storage medium |
| CN115331436A (en) * | 2022-08-04 | 2022-11-11 | 西安理工大学 | Road section automatic driving automobile movement planning method considering pedestrian safety |
| CN115331436B (en) * | 2022-08-04 | 2024-04-30 | 西安理工大学 | Road section automatic driving automobile motion planning method considering pedestrian safety |
| CN115329126B (en) * | 2022-10-14 | 2022-12-27 | 南通启锦智能科技有限公司 | Intelligent data storage method of vehicle event data recorder |
| CN115329126A (en) * | 2022-10-14 | 2022-11-11 | 南通启锦智能科技有限公司 | Intelligent data storage method of vehicle event data recorder |
| CN116223056A (en) * | 2022-12-14 | 2023-06-06 | 清华大学 | Virtual collision test method, apparatus, device, storage medium, and program product |
| CN116223056B (en) * | 2022-12-14 | 2024-03-12 | 清华大学 | Virtual collision test method, apparatus, device, storage medium, and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110834631A (en) | Pedestrian avoiding method and device, vehicle and storage medium | |
| US11465619B2 (en) | Vehicle collision avoidance based on perturbed object trajectories | |
| CN111670468B (en) | Moving body behavior prediction device and moving body behavior prediction method | |
| US11574089B2 (en) | Synthetic scenario generator based on attributes | |
| US11568100B2 (en) | Synthetic scenario simulator based on events | |
| US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
| WO2020245654A1 (en) | Systems and methods for vehicle navigation | |
| KR20210074366A (en) | Autonomous vehicle planning and forecasting | |
| JP2018152056A (en) | Risk-based driver assistance for approaching intersections with limited visibility | |
| CN112639849A (en) | Route selection method and route selection device | |
| JP2022549763A (en) | SAFETY MODULE, AUTOMATED DRIVING SYSTEM AND METHOD THEREOF | |
| JP7193656B2 (en) | Control unit and method for recognizing intruding or exiting vehicles | |
| US20240174221A1 (en) | Vehicle decision-making planning method and apparatus, device and medium | |
| US11814072B2 (en) | Method and system for conditional operation of an autonomous agent | |
| WO2020264276A1 (en) | Synthetic scenario generator based on attributes | |
| CN111707258B (en) | External vehicle monitoring method, device, equipment and storage medium | |
| US11745762B2 (en) | System and methods of adaptive trajectory prediction for autonomous driving | |
| CN116225026A (en) | Automatic driving vehicle operation method, electronic device, and computer-readable medium | |
| US20230053243A1 (en) | Hybrid Performance Critic for Planning Module's Parameter Tuning in Autonomous Driving Vehicles | |
| US11724717B2 (en) | Implementation of dynamic cost function of self-driving vehicles | |
| CN114030483A (en) | Vehicle control method, device, electronic apparatus, and medium | |
| Yoshihira et al. | Developing an autonomous vehicle control system for intersections using obstacle/blind spot detection frames | |
| US20230418291A1 (en) | Testing reuse across protolane families | |
| US20230415773A1 (en) | Validating protolanes with actor behavior flowcharts | |
| US20230415767A1 (en) | Protolanes for testing autonomous vehicle intent |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200225 |