Vehicle-meeting control method, device, vehicle control equipment and storage medium

Abstract

The present invention discloses a vehicle-meeting control method, device, vehicle control equipment and storage medium, including: determining the width of a drivable area when a main vehicle detects an oncoming vehicle, judging whether the width satisfies the passing of the main vehicle and the oncoming vehicle, and if so, generating a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively the trajectories of the main vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is the trajectory of the main vehicle stopping to avoid, calculating the lateral meeting cost of the main vehicle according to the first trajectory and the third trajectory, and calculating the longitudinal meeting cost of the main vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with the lateral distance between the main vehicle and the oncoming vehicle when the two vehicles meet; judging whether the lateral meeting cost is less than the longitudinal meeting cost; if so, controlling the main vehicle to travel according to the first trajectory; otherwise, controlling the main vehicle to travel according to the second trajectory. In this embodiment, the main vehicle can select a more comfortable meeting method to meet the oncoming vehicle according to the meeting cost, thereby improving the comfort of the main vehicle when meeting.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving vehicles, and in particular to a vehicle-meeting control method, device, vehicle control equipment and storage medium. Background Art

[0002] As more and more self-driving vehicles are being used, it is inevitable that they will meet other vehicles while driving on the road.

[0003] like Figure 1 As shown, when the main vehicle A is driving, there is an oncoming vehicle B on the lane, and the width of the lane can meet the requirement that the main vehicle A and the oncoming vehicle B can pass each other side by side and drive in parallel, that is, the trajectory L1 of the main vehicle A and the trajectory L2 of the oncoming vehicle B have no time and space overlap. In this case, the main vehicle A usually enters the road directly after passing the intersection and meets the oncoming vehicle B according to the trajectory L1, which may result in the lateral distance with the oncoming vehicle B being too small, resulting in reduced comfort of the main vehicle, especially when the oncoming vehicle B is a large vehicle such as a truck, van, bus, etc., the lateral distance is too small, which will make the main vehicle feel more uncomfortable, such as a strong sense of oppression. Summary of the invention

[0004] The present invention provides a vehicle meeting control method, device, vehicle control equipment and storage medium to solve the problem in the prior art that when a main vehicle and an oncoming vehicle meet, the lateral distance between the two vehicles is too small, resulting in reduced comfort of the main vehicle.

[0005] In a first aspect, the present invention provides a vehicle-meeting control method, comprising:

[0006] When an oncoming vehicle is detected during the driving of the main vehicle, the width of the drivable area between the main vehicle and the oncoming vehicle is determined, and whether the width satisfies the passing of the main vehicle and the oncoming vehicle;

[0007] If yes, generate a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively the driving trajectories of the main vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is the trajectory of the main vehicle stopping to avoid the oncoming vehicle;

[0008] Calculating a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and calculating a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet;

[0009] Determining whether the lateral meeting cost is less than the longitudinal meeting cost;

[0010] If yes, controlling the main vehicle to travel according to the first trajectory;

[0011] If not, control the main vehicle to travel according to the second trajectory.

[0012] In a second aspect, the present invention provides a vehicle-meeting control device, comprising:

[0013] A width judgment module is used to determine the width of the drivable area between the main vehicle and the oncoming vehicle when an oncoming vehicle is detected during the driving of the main vehicle, and to judge whether the width satisfies the passing of the main vehicle and the oncoming vehicle;

[0014] A trajectory generation module, used to generate a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively driving trajectories of the main vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is a trajectory of the main vehicle stopping to avoid the oncoming vehicle;

[0015] a meeting cost calculation module, configured to calculate a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and to calculate a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet;

[0016] A meeting cost judgment module, used to judge whether the lateral meeting cost is less than the longitudinal meeting cost;

[0017] A first meeting module, used for controlling the main vehicle to travel according to the first trajectory;

[0018] The second meeting module is used to control the main vehicle to travel according to the second trajectory.

[0019] In a third aspect, the present invention provides a vehicle control device, the vehicle control device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle meeting control method described in the first aspect of the present invention.

[0023] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle meeting control method described in the first aspect of the present invention when executed.

[0024] In the embodiment of the present invention, when the width of the drivable area between the main vehicle and the oncoming vehicle satisfies the requirement for the main vehicle and the oncoming vehicle to pass each other, a first trajectory and a third trajectory are respectively generated for the lateral passing of the main vehicle and the oncoming vehicle, and a second trajectory is generated for the main vehicle to stop and avoid the oncoming vehicle, and a lateral meeting cost of the main vehicle is further calculated based on the first trajectory and the third trajectory, and a longitudinal meeting cost of the main vehicle is calculated based on the second trajectory, wherein the lateral meeting cost is negatively correlated with the lateral distance between the main vehicle and the oncoming vehicle when the two vehicles meet, and it is determined whether the lateral meeting cost is less than the longitudinal meeting cost; if so, the main vehicle is controlled to travel according to the first trajectory If not, the main vehicle is controlled to travel according to the second trajectory, thereby realizing the selection of a meeting method with a smaller cost according to the costs of the two meeting methods, namely, lateral passing and longitudinal parking to avoid meeting, so as to control the main vehicle to meet, and the lateral distance between the two vehicles during lateral passing is taken into account when calculating the lateral meeting cost, and the lateral meeting cost is negatively correlated with the lateral distance, that is, the smaller the lateral distance, the greater the lateral meeting cost, the lower the comfort of the main vehicle, and the greater the possibility of choosing longitudinal parking to avoid the oncoming vehicle. Finally, the main vehicle can choose a more comfortable meeting method to meet the oncoming vehicle, thereby improving the comfort of the main vehicle when meeting.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a schematic diagram of a vehicle-meeting scenario according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of a vehicle-meeting control method provided in Embodiment 1 of the present invention;

[0029] Figure 3 is a schematic diagram of a meeting trajectory in an embodiment of the present invention;

[0030] Figure 4 is a flow chart of a vehicle-meeting control method provided by Embodiment 2 of the present invention;

[0031] Figure 5 is a structural schematic diagram of a vehicle-meeting control device provided in Embodiment 3 of the present invention;

[0032] Figure 6It is a structural schematic diagram of a vehicle control device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] Embodiment 1

[0035] Figure 2 This is a flow chart of a vehicle-meeting control method provided in Embodiment 1 of the present invention. This embodiment can be applied to controlling an autonomous driving vehicle to select a suitable vehicle-meeting method to meet an oncoming vehicle. This method can be executed by a vehicle-meeting control device, which can be implemented in the form of hardware and / or software. The vehicle-meeting control device can be configured in a vehicle control device, which can be a driving computer of an autonomous driving vehicle or a remote server that communicates with the autonomous driving vehicle. Figure 2 As shown, the vehicle-meeting control method includes:

[0036] S201. When an oncoming vehicle is detected during the driving of the main vehicle, the width of the drivable area between the main vehicle and the oncoming vehicle is determined, and whether the width satisfies the passing of the main vehicle and the oncoming vehicle.

[0037] In this embodiment, the main vehicle may be an autonomous driving vehicle, and the oncoming vehicle may be a vehicle traveling in the opposite direction of the main vehicle. The main vehicle may be equipped with various sensors that can sense the surrounding environment of the main vehicle, such as lidar, millimeter-wave radar, camera, ultrasonic and other sensors, so as to determine whether there is an oncoming vehicle, the drivable area between the main vehicle and the oncoming vehicle, etc. after sensing the environment through sensors. The drivable area may refer to the area on the road between the main vehicle and the oncoming vehicle where the main vehicle and the oncoming vehicle can meet each other except for obstacles.

[0038] like Figure 1As shown, after passing the intersection, the main vehicle A needs to drive to the road where the oncoming vehicle B is located, resulting in a meeting between the main vehicle A and the oncoming vehicle B. Multiple social vehicles C (or other obstacles) may be parked on one side or both sides of the road where the oncoming vehicle B is located. After the main vehicle A senses the environment through sensors, it can determine the drivable area D, and determine the minimum width of the drivable area and the width of the oncoming vehicle B, and further determine whether the minimum width is greater than the sum of the width of the oncoming vehicle B and the width of the main vehicle A. If so, it means that the drivable area D can satisfy the lateral passing of the main vehicle A and the oncoming vehicle B, that is, it satisfies the parallel driving and meeting of the main vehicle A and the object vehicle B, then execute S202, otherwise, the drivable area D cannot satisfy the lateral passing of the main vehicle A and the oncoming vehicle B, then the main vehicle A or the oncoming vehicle B needs to stop to avoid the other vehicle.

[0039] S202, generating a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively driving trajectories of the host vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is a trajectory of the host vehicle stopping to avoid the oncoming vehicle.

[0040] In this embodiment, the ways of meeting the main vehicle and the oncoming vehicle include lateral passing and longitudinal parking to avoid meeting. Among them, lateral passing can be that the main vehicle enters the drivable area and passes the oncoming vehicle in parallel, and longitudinal parking to avoid meeting can be that the main vehicle pulls over outside the drivable area to avoid the oncoming vehicle, and then drives into the drivable area after the oncoming vehicle drives out of the drivable area.

[0041] In one embodiment, after obtaining the status information such as the position, posture, speed, acceleration, and road data of the host vehicle and the oncoming vehicle, the status information and road data of the host vehicle and the oncoming vehicle are input into a pre-trained trajectory prediction model to obtain a first trajectory, a second trajectory, and a third trajectory, wherein the first trajectory and the third trajectory are respectively the driving trajectories of the host vehicle and the oncoming vehicle when passing each other laterally, and the second trajectory is the trajectory of the host vehicle when it stops to avoid the oncoming vehicle.

[0042] In another optional embodiment, the first target position and the second target position of the main vehicle and the oncoming vehicle after the lateral passing can be respectively determined according to the road data sensed by the main vehicle, and the third target position of the main vehicle for longitudinal parking to avoid the oncoming vehicle can be determined. The current position of the main vehicle is taken as the starting point and the first target position is taken as the end point. The first state data is input into the trajectory planning algorithm to obtain the first trajectory of the main vehicle. The current position of the oncoming vehicle is taken as the starting point and the second target position is taken as the end point. The state information of the oncoming vehicle and the road data are input into the trajectory planning algorithm to obtain the third trajectory of the oncoming vehicle. The current position of the main vehicle is taken as the starting point and the third target position is taken as the end point. The state information of the main vehicle is input into the trajectory planning algorithm to obtain the second trajectory of the main vehicle, wherein the state information of the main vehicle includes the position and speed of the main vehicle, and the state information of the oncoming vehicle includes the position and speed of the oncoming vehicle. The trajectory planning algorithm can be a trajectory search algorithm, a secondary optimization algorithm, etc. in the prior art.

[0043] like Figure 3 As shown, in one way of meeting, the main vehicle A meets the oncoming vehicle B in the drivable area D via the first trajectory L1 and the oncoming vehicle B meets the oncoming vehicle B via the third trajectory L2, that is, the main vehicle A and the main vehicle B meet each other transversely in the drivable area D. Another way of meeting is that the main vehicle A travels according to the second trajectory L3, that is, the main vehicle A stops outside the drivable area D to avoid the oncoming vehicle B, and after the oncoming vehicle B drives out of the drivable area D, the main vehicle A drives into the drivable area D.

[0044] S203, calculating a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and calculating a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet.

[0045] In this embodiment, the lateral meeting cost of the host vehicle indicates the comfort of the host vehicle when the host vehicle and the oncoming vehicle meet laterally, and the longitudinal meeting cost indicates the comfort of the host vehicle when the host vehicle and the oncoming vehicle meet longitudinally.

[0046] For the lateral meeting cost, the main vehicle position and the oncoming vehicle position when the main vehicle and the oncoming vehicle meet can be determined in the first trajectory and the third trajectory respectively, and the lateral meeting distance between the main vehicle and the oncoming vehicle is calculated using the main vehicle position, the oncoming vehicle position, the main vehicle width of the main vehicle and the vehicle width of the oncoming vehicle, and the inverse of the lateral meeting distance is calculated as the lateral meeting distance cost. At the same time, the speed and front wheel angle of the oncoming vehicle when it laterally avoids the main vehicle are determined from the third trajectory, and the angular velocity of the oncoming vehicle is calculated using the speed and the front wheel angle, and the meeting comfort cost of the oncoming vehicle is calculated based on the angular velocity, wherein the meeting comfort is negatively correlated with the angular velocity, and the sum of the lateral meeting distance cost and the comfort cost is calculated as the lateral meeting cost of the main vehicle, wherein the smaller the lateral distance between the main vehicle and the oncoming vehicle is, the larger the lateral meeting cost is, indicating that the comfort of the main vehicle and the oncoming vehicle when passing each other laterally is lower.

[0047] For the longitudinal meeting cost, the longitudinal driving distance of the main vehicle for stopping to avoid the oncoming vehicle can be determined from the second trajectory, and the inverse of the longitudinal driving distance can be calculated as the longitudinal avoidance distance cost of the main vehicle. The braking amount of the main vehicle can be determined from the second trajectory, and the braking cost of the main vehicle can be calculated based on the braking amount. The braking cost is positively correlated with the braking amount. The sum of the longitudinal avoidance distance cost and the braking cost is calculated to obtain the longitudinal meeting cost of the main vehicle. Among them, the smaller the longitudinal meeting distance and the larger the braking amount, it means that the main vehicle needs to brake suddenly and stop in a short distance to avoid the oncoming vehicle, and the comfort level of the main vehicle in longitudinal meeting is low.

[0048] S204: Determine whether the lateral meeting cost is less than the longitudinal meeting cost.

[0049] Specifically, the lateral meeting cost and the longitudinal meeting cost may be compared. When the lateral meeting cost is smaller than the longitudinal meeting cost, S205 is executed. When the lateral meeting cost is greater than or equal to the longitudinal meeting cost, S206 is executed.

[0050] S205: Control the main vehicle to travel along the first trajectory.

[0051] Specifically, Figure 3 As shown, the main vehicle A is controlled to travel to the drivable area D according to the position, speed, acceleration, etc. of the main vehicle in the first trajectory L1, so as to achieve lateral passing with the oncoming vehicle B in the drivable area.

[0052] S206: Control the main vehicle to travel along the second trajectory.

[0053] Specifically, Figure 3 As shown, the main vehicle A is controlled to travel to an avoidance position outside the drivable area D according to the position, speed, acceleration, etc. of the main vehicle in the second trajectory L3, so that the main vehicle A stops outside the drivable area D to avoid the oncoming vehicle B.

[0054] In an embodiment of the present invention, when the width of the drivable area between the main vehicle and the oncoming vehicle satisfies the requirement for the main vehicle and the oncoming vehicle to pass each other, a first trajectory and a third trajectory are respectively generated for the main vehicle and the oncoming vehicle to pass each other laterally, and a second trajectory is generated for the main vehicle to stop and avoid the oncoming vehicle, and a lateral meeting cost of the main vehicle is further calculated according to the first trajectory and the third trajectory, and a longitudinal meeting cost of the main vehicle is calculated according to the second trajectory, wherein the lateral meeting cost is negatively correlated with the lateral distance between the main vehicle and the oncoming vehicle when the two vehicles meet, and whether the lateral meeting cost is less than the longitudinal meeting cost is determined; if so, the main vehicle is controlled to follow the first trajectory. If not, the main vehicle is controlled to drive according to the second trajectory, thereby realizing the meeting by selecting the less costly meeting method from the two meeting methods of lateral passing and longitudinal parking to avoid meeting, and the lateral distance between the two vehicles when lateral passing is considered when calculating the lateral meeting cost, and the negative correlation between the lateral meeting cost and the lateral distance, that is, the smaller the lateral distance, the greater the lateral meeting cost, the lower the comfort of the main vehicle, and the greater the possibility of choosing longitudinal parking to avoid the oncoming vehicle. Finally, the main vehicle can choose a more comfortable meeting method to meet the oncoming vehicle, thereby improving the comfort of the main vehicle when meeting.

[0055] Embodiment 2

[0056] Figure 4 Flow chart of a vehicle-meeting control method provided in Embodiment 2 of the present invention. Embodiment 2 of the present invention is optimized on the basis of Embodiment 1 above. Figure 4 As shown, the vehicle-meeting control method includes:

[0057] S401. When an oncoming vehicle is detected during the driving of the main vehicle, the width of the drivable area between the main vehicle and the oncoming vehicle is determined, the main vehicle width of the main vehicle and the oncoming vehicle width of the oncoming vehicle are obtained, and the sum of the main vehicle width and the oncoming vehicle width is calculated.

[0058] During the driving process, the main vehicle of this embodiment can sense the surrounding environment of the main vehicle through the sensors on the main vehicle to obtain environmental data, and use the environmental data to identify whether there is an oncoming vehicle on the road in front of the main vehicle. If so, the drivable area between the main vehicle and the oncoming vehicle is further determined through the environmental data, and the width of the drivable area is obtained, wherein the width can be multiple, that is, the width at different positions in the drivable area. Further, when an oncoming vehicle is identified through the environmental data, the width of the oncoming vehicle is obtained, and the sum of the width of the oncoming vehicle and the width of the main vehicle is further calculated.

[0059] like Figure 3 As shown, the main vehicle A and the oncoming vehicle B are traveling towards each other. The drivable area D between the main vehicle A and the oncoming vehicle B can be identified, and multiple widths di of the drivable area D can be detected. At the same time, the main vehicle width of the main vehicle A and the oncoming vehicle width of the oncoming vehicle B are obtained, and the sum of the main vehicle width and the oncoming vehicle width is calculated.

[0060] S402: Determine a minimum width from multiple widths of the drivable area, and determine whether the minimum width is greater than the sum value.

[0061] Specifically, when multiple widths di of the drivable area D are detected, the minimum width dmin can be determined, and it is judged whether dmin is greater than the sum of the widths of the main vehicle and the oncoming vehicle. If so, it means that the drivable area D can meet the parallel driving of the main vehicle A and the oncoming vehicle B and the sideways passing each other, and S403 is executed. If not, it means that the drivable area cannot meet the parallel driving of the main vehicle and the oncoming vehicle, and the main vehicle needs to pull over to avoid the oncoming vehicle, or the oncoming vehicle needs to pull over to avoid the main vehicle.

[0062] S403: Acquire the host vehicle status information of the host vehicle and the oncoming vehicle status information of the oncoming vehicle.

[0063] Specifically, the main vehicle status information may include the main vehicle's position, speed, acceleration, posture and other data, and the oncoming vehicle status information may include the oncoming vehicle's position, speed, acceleration, posture and other data. Among them, the main vehicle status information can be measured by sensors such as positioning sensors and inertial measurement units on the main vehicle, and the oncoming vehicle status information can be obtained after identifying the oncoming vehicle through the environmental data perceived by the main vehicle.

[0064] S404: Acquire road data of the road between the host vehicle and the oncoming vehicle.

[0065] The road between the main vehicle and the oncoming vehicle is Figure 3 The road data of the drivable area shown may include the length, curvature, map data, and the locations of parked vehicles or other obstacles of the drivable area.

[0066] S405 , generating a first trajectory, a second trajectory, and a third trajectory according to the host vehicle state information, the oncoming vehicle state information, and the road data.

[0067] In an optional embodiment, the first target position and the second target position of the main vehicle and the oncoming vehicle after the lateral passing can be determined respectively according to the road data, and the third target position of the main vehicle for longitudinal parking to avoid the oncoming vehicle can be determined. Taking the current position of the main vehicle as the starting point and the first target position as the end point, the first state data is input into the trajectory planning algorithm to obtain the first trajectory of the main vehicle. Taking the current position of the oncoming vehicle as the starting point and the second target position as the end point, the oncoming vehicle state information and the road data are input into the trajectory planning algorithm to obtain the third trajectory of the oncoming vehicle. Taking the current position of the main vehicle as the starting point and the third target position as the end point, the main vehicle state information is input into the trajectory planning algorithm to obtain the second trajectory of the main vehicle. The main vehicle state information includes the position and speed of the main vehicle, and the oncoming vehicle state information includes the position and speed of the oncoming vehicle.

[0068] For example, Figure 3 As shown, the first target position P2 of the main vehicle A, the second target position P5 of the oncoming vehicle B, and the third target position P3 of the main vehicle A are determined, wherein the first target position P2 and the second target position P5 are respectively the positions of the main vehicle A and the oncoming vehicle B after they have passed each other laterally in the drivable area D, and the third target position P3 is the parking position of the main vehicle A when it pulls over outside the drivable area D to avoid the oncoming vehicle B from driving out of the drivable area D. The current position P1 of the main vehicle A can be taken as the starting point and the first target position P2 can be taken as the end point, the current position P4 of the oncoming vehicle B can be taken as the starting point and the second target position P5 can be taken as the end point, and in combination with the road data of the drivable area D, the position, speed, acceleration and other data of the main vehicle A and the oncoming vehicle B, a first trajectory L1 and a third trajectory L2 of the main vehicle A and the main vehicle B when they pass each other laterally in the drivable area D can be respectively planned through a preset trajectory planning algorithm, wherein the first trajectory L1 and the third trajectory L2 have no overlapping area in time and space. Similarly, in combination with the current position P1 of the main vehicle A and the third target position P3 can be taken as the starting point and the third target position P3 can be taken as the end point, and in combination with the road data, the position, speed, acceleration and other data of the main vehicle A, a second trajectory L3 of the main vehicle A from the current position P1 to the third target position P3 can be planned through a preset trajectory planning algorithm.

[0069] The trajectory planning algorithm of this embodiment may be a path search algorithm, a secondary optimization algorithm, etc. in the prior art, which will not be described in detail in this embodiment.

[0070] S406: Determine the position of the host vehicle and the position of the oncoming vehicle when the host vehicle and the oncoming vehicle meet in the first trajectory and the third trajectory respectively.

[0071] The position of the main vehicle and the position of the oncoming vehicle when the main vehicle and the oncoming vehicle meet each other may refer to the position of the main vehicle and the position of the oncoming vehicle when the main vehicle and the oncoming vehicle pass each other while driving side by side in the drivable area, such as Figure 3 As shown, assuming that the main vehicle A and the oncoming vehicle B meet in the drivable area D, the main vehicle A travels according to the first trajectory L1, and the oncoming vehicle B travels according to the third trajectory L2. The main vehicle A and the oncoming vehicle B will inevitably intersect in the drivable area D. For example, when they intersect, the position of the main vehicle is P7 and the position of the oncoming vehicle B is P6.

[0072] Specifically, the trajectory includes the arrival time of the vehicle at each location and the x and y coordinates of the location, where the x and y coordinates are as follows: Figure 3 As shown, the positions in the first trajectory and the third trajectory where the arrival time and the x-coordinate are the same can be determined as the host vehicle position and the oncoming vehicle position when the host vehicle and the oncoming vehicle intersect.

[0073] S407, calculating the lateral meeting distance between the main vehicle and the oncoming vehicle using the main vehicle position, the oncoming vehicle position, the main vehicle width and the oncoming vehicle width, and calculating the inverse of the lateral meeting distance as the lateral meeting distance cost.

[0074] In one embodiment, the difference between the position of the main vehicle and the position of the oncoming vehicle can be calculated, the sum of the width of the main vehicle and the width of the oncoming vehicle can be calculated, the ratio of the sum to the value 2 can be calculated, and the difference between the difference and the ratio can be calculated to obtain the lateral meeting distance between the main vehicle and the oncoming vehicle. Finally, the inverse of the lateral meeting distance is taken as the lateral meeting distance cost, so that the lateral meeting distance cost is negatively correlated with the lateral meeting distance, that is, the smaller the lateral meeting distance between the main vehicle and the oncoming vehicle, the greater the lateral meeting distance cost, and the lower the comfort of the main vehicle.

[0075] Of course, in addition to taking the inverse of the lateral meeting distance as the lateral meeting distance cost, those skilled in the art may also calculate the lateral meeting distance cost by using a negative correlation equation with the lateral meeting distance as an independent variable.

[0076] S408. Determine the speed and front wheel angle of the oncoming vehicle when it laterally avoids the main vehicle from the third trajectory, calculate the angular velocity of the oncoming vehicle using the speed and the front wheel angle, and calculate the meeting comfort cost of the oncoming vehicle based on the angular velocity, wherein the meeting comfort is negatively correlated with the angular velocity.

[0077] In this embodiment, assuming that the host vehicle and the oncoming vehicle are traveling in opposite directions and passing each other laterally in the drivable area, the oncoming vehicle needs to pull over to avoid colliding with the host vehicle. When the oncoming vehicle pulls over, it may turn the steering wheel to cause the front wheels of the oncoming vehicle to turn. In this case, the position of the oncoming vehicle to avoid the host vehicle laterally can be determined from the third trajectory, such as Figure 3 As shown, in the third trajectory L2, the oncoming vehicle B turns to drive sideways at position P8, then the speed and front wheel angle of the oncoming vehicle can be obtained from the third trajectory, and the angular velocity can be calculated by the following formula:

[0078] w=v / r

[0079] r=L / tan(angle)

[0080] angle is the front wheel angle, L is the wheelbase of the oncoming vehicle, V is the speed of the oncoming vehicle, and w is the angular velocity of the oncoming vehicle.

[0081] In an example, the greater the speed V of the oncoming vehicle, the greater the front wheel angle angle, and the angular velocity, the lower the comfort of the oncoming vehicle when turning to avoid the main vehicle, that is, the comfort cost of the oncoming vehicle is positively correlated with the angular velocity of the oncoming vehicle. The angular velocity of the oncoming vehicle can be directly used as the comfort cost of the oncoming vehicle. Of course, the comfort cost of the oncoming vehicle can also be calculated through other positive correlation equations with angular velocity as the independent variable.

[0082] S409: Calculate the lateral meeting cost of the host vehicle according to the lateral meeting distance cost and the meeting comfort cost.

[0083] In an optional embodiment, the lateral meeting cost of the host vehicle may be calculated by the following formula:

[0084] cost_lateral_avoid=a×cost_lateral_dist+b×cost_steering_wheel

[0085] cost_lateral_avoid is the lateral meeting cost, cost_lateral_dist is the lateral meeting distance cost, cost_steering_wheel is the meeting comfort cost of the oncoming vehicle, a and b are weights, where weight a is related to the vehicle type of the oncoming vehicle. For example, when the oncoming vehicle is a large vehicle, weight a can be set to a larger value.

[0086] This embodiment calculates the lateral passing cost by the lateral distance between the main vehicle and the oncoming vehicle and the speed and front wheel angle of the oncoming vehicle. On the one hand, the lateral distance between the main vehicle and the oncoming vehicle is taken into account, and on the other hand, the comfort of the oncoming vehicle when the oncoming vehicle gives way to the main vehicle is taken into account, thereby avoiding the problem that the comfort of the main vehicle is reduced and the oncoming vehicle is prone to safety hazards when the lateral distance is too small, the speed of the oncoming vehicle is too fast and the steering is too large, and the oncoming vehicle also passes or meets the main vehicle laterally in the drivable area. The lateral distance, the speed of the oncoming vehicle and the front wheel angle are comprehensively considered to determine whether to pass or meet the oncoming vehicle laterally within the drivable area, thereby ensuring a more comfortable lateral distance when passing or meeting the oncoming vehicle laterally and improving the comfort of the main vehicle, and avoiding the main vehicle entering the drivable area, which causes the oncoming vehicle to avoid the main vehicle due to its excessive speed, resulting in reduced comfort of the oncoming vehicle and even a traffic accident.

[0087] S410: Determine the longitudinal travel distance of the host vehicle when it stops to avoid the oncoming vehicle from the second trajectory, and calculate the inverse of the longitudinal travel distance as the longitudinal avoidance distance cost of the host vehicle.

[0088] Specifically, Figure 3 As shown, the longitudinal driving distance of the main vehicle when it stops to avoid the oncoming vehicle is the distance from the starting point P1 to the end point P3 of the second trajectory L3. The larger the distance is, the more time the main vehicle has to brake to stop at the end point P3 with a smaller braking amount, and the higher the comfort of the main vehicle. On the contrary, the smaller the distance is, the less time the main vehicle has to brake to stop at the end point P3 with a smaller braking amount, and the main vehicle will brake with a larger braking amount, i.e., emergency braking, and the lower the comfort of the main vehicle. Based on this, in an example, the inverse of the longitudinal driving distance can be calculated as the longitudinal avoidance distance cost of the main vehicle, so that the longitudinal avoidance distance cost is negatively correlated with the longitudinal driving distance.

[0089] S411. Determine the braking amount of the host vehicle from the second trajectory, and calculate the braking cost of the host vehicle according to the braking amount. The braking cost is positively correlated with the braking amount.

[0090] In one example, the braking amount can be the braking amount of the brake pedal, and of course it can also be measured by the acceleration of the main vehicle. The measurement method of the braking amount in this embodiment is not limited. In this embodiment, the braking cost is positively correlated with the braking amount, that is, the greater the braking amount, the greater the braking cost, and the lower the comfort of the main vehicle.

[0091] S412: Calculate the sum of the longitudinal avoidance distance cost and the braking cost to obtain the longitudinal meeting cost of the host vehicle.

[0092] Right now:

[0093] cost_lon_yield=cost_lon_progress+cost_brake

[0094] cost_lon_yield is the longitudinal avoidance distance cost, cost_lon_progress is the longitudinal avoidance distance cost, and cost_brake is the braking cost.

[0095] S413: Determine whether the lateral meeting cost is less than the longitudinal meeting cost.

[0096] Specifically, the lateral meeting cost and the longitudinal meeting cost may be compared. When the lateral meeting cost is smaller than the longitudinal meeting cost, S414 is executed. When the lateral meeting cost is greater than or equal to the longitudinal meeting cost, S415 is executed.

[0097] S414: Control the main vehicle to travel along a first trajectory.

[0098] Specifically, Figure 3 As shown, the main vehicle A is controlled to travel to the drivable area D according to the position, speed, acceleration, etc. of the main vehicle in the first trajectory L1, so as to achieve lateral passing with the oncoming vehicle B in the drivable area.

[0099] S415: Control the main vehicle to travel along the second trajectory.

[0100] Specifically, Figure 3 As shown, the main vehicle A is controlled to travel to an avoidance position outside the drivable area D according to the position, speed, acceleration, etc. of the main vehicle in the second trajectory L3, so that the main vehicle A stops outside the drivable area D to avoid the oncoming vehicle B.

[0101] In this embodiment, when the width of the drivable area is greater than the sum of the widths of the main vehicle and the oncoming vehicle, the first trajectory, the second trajectory and the third trajectory are generated according to the main vehicle state information, the oncoming vehicle state information and the road data, and after further determining the meeting positions of the main vehicle and the oncoming vehicle from the first trajectory and the third trajectory, the lateral meeting distance of the main vehicle and the oncoming vehicle is calculated, and the inverse of the lateral meeting distance is taken as the lateral meeting distance cost, and the speed and front wheel angle of the oncoming vehicle when avoiding the main vehicle are further determined from the third trajectory to calculate the meeting comfort cost of the oncoming vehicle, and the sum of the lateral meeting distance cost and the meeting comfort cost is taken as the lateral meeting cost of the main vehicle. , and the longitudinal driving distance and braking amount of the main vehicle when stopping to avoid the oncoming vehicle are determined from the second trajectory to calculate the longitudinal meeting cost of the main vehicle, so as to realize the meeting method with the smaller cost among the two meeting methods of lateral passing and longitudinal stopping to avoid meeting, and the lateral distance between the two vehicles when lateral passing is considered when calculating the lateral meeting cost, and the negative correlation between the lateral meeting cost and the lateral distance, that is, the smaller the lateral distance, the greater the lateral meeting cost, the lower the comfort of the main vehicle, and the greater the possibility of choosing longitudinal stopping to avoid the oncoming vehicle. Finally, the main vehicle can choose a more comfortable meeting method to meet the oncoming vehicle, thereby improving the comfort of the main vehicle when meeting.

[0102] Embodiment 3

[0103] Figure 5 This is a schematic diagram of the structure of a vehicle-meeting control device provided in Embodiment 3 of the present invention. Figure 5 As shown, the vehicle-meeting control device comprises:

[0104] The width judgment module 501 is used to determine the width of the drivable area between the main vehicle and the oncoming vehicle when an oncoming vehicle is detected during the driving of the main vehicle, and to judge whether the width satisfies the passing of the main vehicle and the oncoming vehicle;

[0105] The trajectory generation module 502 is used to generate a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively driving trajectories of the host vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is the trajectory of the host vehicle stopping to avoid the oncoming vehicle;

[0106] a meeting cost calculation module 503, configured to calculate a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and to calculate a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet;

[0107] A meeting cost judgment module 504 is used to judge whether the lateral meeting cost is less than the longitudinal meeting cost;

[0108] A first meeting module 505, used to control the host vehicle to travel according to the first trajectory;

[0109] The second meeting module 506 is used to control the host vehicle to travel according to the second trajectory.

[0110] In one embodiment, the width includes multiple widths, and the width determination module 401 includes:

[0111] a vehicle width calculation unit, configured to obtain the vehicle width of the main vehicle and the vehicle width of the oncoming vehicle, and calculate the sum of the vehicle width of the main vehicle and the vehicle width of the oncoming vehicle;

[0112] The width judgment unit is used to determine a minimum width from the multiple widths of the drivable area, and to judge whether the minimum width is greater than the sum value.

[0113] In one embodiment, the trajectory generation module 502 includes:

[0114] A status information acquisition unit, used to acquire the main vehicle status information of the main vehicle and the oncoming vehicle status information of the oncoming vehicle;

[0115] A road data acquisition unit, used to acquire road data of a road between the host vehicle and the oncoming vehicle;

[0116] The trajectory generating unit is used to generate a first trajectory, a second trajectory and a third trajectory according to the host vehicle state information, the oncoming vehicle state information and the road data.

[0117] In one embodiment, the trajectory generating unit comprises:

[0118] The trajectory prediction subunit is used to input the host vehicle state information, the oncoming vehicle state information and the road data into a trajectory prediction model to obtain a first trajectory, a second trajectory and a third trajectory.

[0119] In one embodiment, the trajectory generating unit comprises:

[0120] A vehicle target position determination subunit, for determining, according to the road data, a first target position and a second target position of the host vehicle and the oncoming vehicle after the lateral passing, and a third target position of the host vehicle for longitudinal parking to avoid the oncoming vehicle;

[0121] A first trajectory generating subunit is used for taking the current position of the main vehicle as a starting point and the first target position as an end point, and inputting the first state data into a trajectory planning algorithm to obtain a first trajectory of the main vehicle;

[0122] A third trajectory generating subunit is configured to take the current position of the oncoming vehicle as a starting point and the second target position as an end point, input the oncoming vehicle state information and the road data into a trajectory planning algorithm to obtain a third trajectory of the oncoming vehicle;

[0123] A second trajectory generating subunit is used for taking the current position of the main vehicle as a starting point and the third target position as an end point, and inputting the state information of the main vehicle into a trajectory planning algorithm to obtain a second trajectory of the main vehicle;

[0124] The host vehicle status information includes the position and speed of the host vehicle, and the oncoming vehicle status information includes the position and speed of the oncoming vehicle.

[0125] In one embodiment, the first trajectory includes multiple positions of the host vehicle and the speed of the host vehicle at each position, the third trajectory includes multiple positions of the oncoming vehicle and the speed and front wheel angle of the oncoming vehicle at each position, and the meeting cost judgment module 504 includes:

[0126] a vehicle-meeting position determining unit, used to determine the position of the host vehicle and the position of the oncoming vehicle when the host vehicle and the oncoming vehicle meet in the first trajectory and the third trajectory respectively;

[0127] a lateral meeting distance cost calculation unit, configured to calculate a lateral meeting distance between the main vehicle and the oncoming vehicle by using the main vehicle position, the oncoming vehicle position, the main vehicle width of the main vehicle, and the vehicle width of the oncoming vehicle, and calculate the inverse of the lateral meeting distance as a lateral meeting distance cost;

[0128] an oncoming vehicle passing comfort calculation unit, configured to determine the speed and front wheel angle of the oncoming vehicle when the oncoming vehicle laterally avoids the host vehicle from the third trajectory, calculate the angular velocity of the oncoming vehicle using the speed and front wheel angle, and calculate the passing comfort cost of the oncoming vehicle according to the angular velocity, wherein the passing comfort is negatively correlated with the angular velocity;

[0129] a lateral meeting cost calculation unit, configured to calculate the lateral meeting cost of the host vehicle according to the lateral meeting distance cost and the meeting comfort cost;

[0130] The lateral meeting cost of the main vehicle is calculated by the following formula:

[0131] cost_lateral_avoid=a×cost_lateral_dist+b×cost_steering_wheel

[0132] cost_lateral_avoid is the cost of lateral meeting, cost_lateral_dist is the cost of lateral meeting distance, cost_steering_wheel is the comfort cost of the oncoming vehicle, a and b are weights, among which weight a is related to the vehicle type of the oncoming vehicle.

[0133] In one embodiment, the meeting cost calculation module 503 includes:

[0134] a longitudinal avoidance distance cost calculation unit, configured to determine, from the second trajectory, a longitudinal travel distance of the host vehicle when stopping to avoid the oncoming vehicle, and calculate a reciprocal of the longitudinal travel distance as a longitudinal avoidance distance cost of the host vehicle;

[0135] a braking cost calculation unit, configured to determine the braking amount of the host vehicle from the second trajectory, and calculate the braking cost of the host vehicle according to the braking amount, wherein the braking cost is positively correlated with the braking amount;

[0136] The longitudinal meeting cost calculation unit is used to calculate the sum of the longitudinal avoidance distance cost and the braking cost to obtain the longitudinal meeting cost of the host vehicle.

[0137] The vehicle-meeting control device provided in the embodiment of the present invention can execute the vehicle-meeting control method provided in the first embodiment and the second embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0138] Embodiment 4

[0139] Figure 6 A schematic diagram of a vehicle control device 60 that can be used to implement the present invention is shown. The vehicle control device is intended to represent devices including various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.

[0140] like Figure 6As shown, the vehicle control device includes at least one processor 61, and a memory connected to the at least one processor 61 in communication, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 61 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 62 or the computer program loaded from the storage unit 68 to the random access memory (RAM) 63. In the RAM 63, various programs and data required for the operation of the vehicle control device 60 can also be stored. The processor 61, the ROM 62, and the RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 64.

[0141] Multiple components in the vehicle control device 60 are connected to the I / O interface 65, including: an input unit 66, such as a keyboard, a mouse, a laser radar, a millimeter-wave radar, a camera, etc. on the vehicle; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a disk, an optical disk, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the vehicle control device 60 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0142] The processor 61 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 61 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, microcontroller, etc. The processor 61 executes the various methods and processes described above, such as the vehicle-meeting control method.

[0143] In some embodiments, the vehicle-meeting control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 68. In some embodiments, part or all of the computer program may be loaded and / or installed on the vehicle control device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, the vehicle-meeting control method described above, and / or one or more steps of the detection method may be executed. Alternatively, in other embodiments, the processor 61 may be configured to execute the vehicle-meeting control method in any other appropriate manner (e.g., by means of firmware).

[0144] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0146] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0147] To provide interaction with a user, the systems and techniques described herein may be implemented on a vehicle control device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the vehicle control device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0148] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0149] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0150] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0151] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle-meeting control method, characterized in that: include: When an oncoming vehicle is detected during the driving of the main vehicle, the width of the drivable area between the main vehicle and the oncoming vehicle is determined, and whether the width satisfies the passing of the main vehicle and the oncoming vehicle; If yes, generate a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively the driving trajectories of the main vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is the trajectory of the main vehicle stopping to avoid the oncoming vehicle; Calculating a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and calculating a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet; Determining whether the lateral meeting cost is less than the longitudinal meeting cost; If yes, controlling the main vehicle to travel according to the first trajectory; If not, control the main vehicle to travel according to the second trajectory.

2. The method according to claim 1, characterized in that The width includes multiple widths, and the determining whether the width satisfies the requirement for the host vehicle and the oncoming vehicle to pass each other includes: Obtaining the vehicle width of the main vehicle and the vehicle width of the oncoming vehicle, and calculating the sum of the vehicle width of the main vehicle and the vehicle width of the oncoming vehicle; A minimum width is determined from the multiple widths of the drivable area, and it is determined whether the minimum width is greater than the sum value.

3. The method according to claim 1, characterized in that The generating of the first trajectory, the second trajectory and the third trajectory comprises: Acquire the main vehicle status information of the main vehicle and the oncoming vehicle status information of the oncoming vehicle; Acquiring road data of a road between the host vehicle and the oncoming vehicle; A first trajectory, a second trajectory and a third trajectory are generated according to the host vehicle state information, the oncoming vehicle state information and the road data.

4. The method according to claim 3, characterized in that The generating of the first trajectory, the second trajectory and the third trajectory according to the host vehicle state information, the oncoming vehicle state information and the road data comprises: The host vehicle state information, the oncoming vehicle state information and the road data are input into a trajectory prediction model to obtain a first trajectory, a second trajectory and a third trajectory.

5. The method according to claim 3, characterized in that The generating the first trajectory, the second trajectory and the third trajectory according to the host vehicle state information, the oncoming vehicle state information and the road data comprises: Determine, according to the road data, a first target position and a second target position of the host vehicle and the oncoming vehicle after lateral passing, and a third target position of the host vehicle for longitudinal parking to avoid the oncoming vehicle; Taking the current position of the host vehicle as the starting point and the first target position as the end point, inputting the host vehicle state information and the road data into a trajectory planning algorithm to obtain a first trajectory of the host vehicle; Taking the current position of the oncoming vehicle as the starting point and the second target position as the end point, inputting the oncoming vehicle state information and the road data into a trajectory planning algorithm to obtain a third trajectory of the oncoming vehicle; Taking the current position of the main vehicle as the starting point and the third target position as the end point, inputting the state information of the main vehicle into the trajectory planning algorithm to obtain the second trajectory of the main vehicle; The host vehicle status information includes the position and speed of the host vehicle, and the oncoming vehicle status information includes the position and speed of the oncoming vehicle.

6. The method according to claim 1, characterized in that The first trajectory includes multiple positions of the host vehicle and the speed of the host vehicle at each position, the third trajectory includes multiple positions of the oncoming vehicle and the speed and front wheel angle of the oncoming vehicle at each position, and calculating the lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory includes: Determining the position of the host vehicle and the position of the oncoming vehicle when the host vehicle and the oncoming vehicle meet in the first trajectory and the third trajectory respectively; The lateral meeting distance between the main vehicle and the oncoming vehicle is calculated by using the main vehicle position, the oncoming vehicle position, the main vehicle width of the main vehicle and the vehicle width of the oncoming vehicle, and the inverse of the lateral meeting distance is calculated as the lateral meeting distance cost; Determine the speed and front wheel angle of the oncoming vehicle when it laterally avoids the host vehicle from the third trajectory, calculate the angular velocity of the oncoming vehicle using the speed and front wheel angle, and calculate the meeting comfort cost of the oncoming vehicle according to the angular velocity, wherein the meeting comfort is negatively correlated with the angular velocity; Calculating the lateral meeting cost of the host vehicle according to the lateral meeting distance cost and the comfort cost; The lateral meeting cost of the main vehicle is calculated by the following formula: cost_lateral_avoid = a×cost_lateral_dist +b×cost_steering_wheel cost_lateral_avoid is the cost of lateral meeting, cost_lateral_dist is the cost of lateral meeting distance, cost_steering_wheel is the comfort cost of the oncoming vehicle, a and b are weights, among which weight a is related to the vehicle type of the oncoming vehicle.

7. The method according to claim 1, characterized in that The calculating the longitudinal meeting cost of the host vehicle according to the second trajectory includes: Determining the longitudinal travel distance of the host vehicle when stopping to avoid the oncoming vehicle from the second trajectory, and calculating the reciprocal of the longitudinal travel distance as the longitudinal avoidance distance cost of the host vehicle; Determine the braking amount of the main vehicle from the second trajectory, and calculate the braking cost of the main vehicle according to the braking amount, wherein the braking cost is positively correlated with the braking amount; The sum of the longitudinal avoidance distance cost and the braking cost is calculated to obtain the longitudinal meeting cost of the host vehicle.

8. A vehicle-meeting control device, characterized in that: include: A width judgment module is used to determine the width of the drivable area between the main vehicle and the oncoming vehicle when an oncoming vehicle is detected during the driving of the main vehicle, and to judge whether the width satisfies the passing of the main vehicle and the oncoming vehicle; A trajectory generation module, used to generate a first trajectory, a second trajectory and a third trajectory, wherein the first trajectory and the third trajectory are respectively driving trajectories of the main vehicle and the oncoming vehicle passing each other laterally, and the second trajectory is a trajectory of the main vehicle stopping to avoid the oncoming vehicle; a meeting cost calculation module, configured to calculate a lateral meeting cost of the host vehicle according to the first trajectory and the third trajectory, and to calculate a longitudinal meeting cost of the host vehicle according to the second trajectory, wherein the lateral meeting cost is negatively correlated with a lateral distance between the host vehicle and the oncoming vehicle when the two vehicles meet; A meeting cost judgment module, used to judge whether the lateral meeting cost is less than the longitudinal meeting cost; A first meeting module, used for controlling the main vehicle to travel according to the first trajectory; The second meeting module is used to control the main vehicle to travel according to the second trajectory.

9. A vehicle control device, characterized in that: The vehicle control device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle meeting control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle-meeting control method according to any one of claims 1 to 7 when executed.

Images