Vehicle trajectory planning method and device, electronic equipment and storage medium

Abstract

The invention relates to a trajectory planning method for a vehicle. The method comprises the following steps: determining a to-be-avoided target obstacle of the vehicle in a driving direction; determining a benchmark reference trajectory of the vehicle for avoiding the target obstacle, and determining a target duration required by the vehicle for avoiding the target obstacle; based on the response delay of the vehicle to the avoidance request, performing compensation processing on a steering wheel turning angle of the vehicle at the avoidance starting point to obtain a target steering wheel turning angle; based on the target duration, the speed information of the vehicle at the avoidance starting point and the target steering wheel turning angle, planning a transverse offset trajectory of the vehicle relative to the datum reference trajectory in the avoidance process; and determining a target obstacle avoidance trajectory corresponding to the vehicle based on the benchmark reference trajectory and the lateral offset trajectory. According to the method, the steering wheel angle is compensated, the influence of delay on the driving track of the vehicle is reduced, meanwhile, the target obstacle avoidance track is determined through the benchmark reference track and the transverse offset track, and the accuracy of the target obstacle avoidance track is improved.

Description

Technical Field

[0001] The present application relates to the field of safe driving of automobiles, and in particular to a vehicle trajectory planning method and device, electronic equipment and storage medium. Background Art

[0002] During the driving process of the vehicle, you may encounter sudden emergency situations (for example, obstacles appearing in front, pedestrians suddenly intruding, etc.), and you need to make an emergency turn to avoid a collision. In the related technology, when the vehicle triggers an emergency turn, there is a link delay between the steering wheel angle request issued and the actual response of the steering wheel angle, so that the steering wheel angle value determined may be smaller than the actual steering wheel angle value, which may lead to the inability to avoid obstacles. At the same time, the lane line measured by the perception module can be used as the vehicle's driving trajectory. However, after the vehicle's emergency steering function is triggered, the vehicle turns a large angle in a short period of time. The vehicle trajectory detected and output only by the perception module cannot match the vehicle with a rapidly changing posture, and there are problems such as low trajectory accuracy and poor flexibility. Summary of the invention

[0003] The present application provides a vehicle trajectory planning method, device, electronic device and storage medium to solve the problems of low accuracy and poor flexibility of vehicle trajectory in related technologies.

[0004] In order to achieve the above object, the present application provides a vehicle trajectory planning method, the method comprising:

[0005] Determine the target obstacle to be avoided by the vehicle in the direction of travel;

[0006] Determine a baseline reference trajectory for the vehicle to avoid a target obstacle, and determine a target time required for the vehicle to avoid the target obstacle;

[0007] Based on the response delay of the vehicle to the avoidance request, the steering wheel angle of the vehicle at the avoidance starting point is compensated to obtain a target steering wheel angle;

[0008] Based on the target duration, the vehicle's speed information at the avoidance starting point, and the target steering wheel angle, the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process is planned;

[0009] Based on the baseline reference trajectory and the lateral offset trajectory, the target obstacle avoidance trajectory corresponding to the vehicle is determined.

[0010] According to the above technical means, after determining the target obstacle to be avoided by the vehicle in the driving direction, first, by determining the reference trajectory of the vehicle to avoid the target obstacle and the target time required for the vehicle to avoid the target obstacle, secondly, by compensating the steering wheel angle of the vehicle at the starting point of the avoidance through the response delay of the vehicle to the avoidance request, the target steering wheel angle is obtained, and further, by the target time, the speed information of the vehicle at the starting point of the avoidance and the target steering wheel angle, the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process is planned, so as to determine the target obstacle avoidance trajectory corresponding to the vehicle according to the reference reference trajectory and the lateral offset trajectory. On the one hand, the present application determines the lateral offset trajectory using the target steering wheel angle after delay compensation, reduces the influence of the delay on the lateral offset trajectory of the vehicle, and improves the accuracy of the lateral offset trajectory; on the other hand, compared with using a single trajectory as the target obstacle avoidance trajectory, the target obstacle avoidance trajectory is determined based on the reference reference trajectory and the lateral offset trajectory, so that the target obstacle avoidance trajectory contains more information, which improves the accuracy of the target obstacle avoidance trajectory and the flexibility of the vehicle's trajectory planning.

[0011] Furthermore, based on the response delay of the vehicle to the avoidance request, the steering wheel angle of the vehicle at the avoidance starting point is compensated to obtain a target steering wheel angle, including: obtaining the steering wheel speed of the vehicle at the avoidance starting point; based on the steering wheel speed and the response delay, compensating the steering wheel angle of the vehicle at the avoidance starting point to obtain the target steering wheel angle.

[0012] According to the above technical means, the steering wheel angle of the vehicle at the avoidance starting point is compensated by the steering wheel speed and the response delay, thereby improving the accuracy of the target steering wheel angle and reducing the influence of the delay on the target steering wheel angle.

[0013] Further, determining a reference trajectory for the vehicle to avoid a target obstacle includes: planning an avoidance direction and a target lateral displacement for the vehicle to avoid the target obstacle based on surrounding obstacle information of the target obstacle; and planning a reference trajectory for the vehicle to avoid the target obstacle based on the avoidance direction, the target lateral displacement, and the motion state information of the vehicle.

[0014] According to the above technical means, the avoidance direction and the target lateral displacement of the surrounding obstacle information of the target obstacle are used, and the baseline reference trajectory is planned by the avoidance direction, the target lateral displacement and the motion state information of the vehicle, so that the baseline reference trajectory includes multiple information, thereby improving the accuracy of the baseline reference trajectory.

[0015] Furthermore, the baseline reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; based on the avoidance direction, the target lateral displacement and the motion state information of the vehicle, the baseline reference trajectory for the vehicle to avoid the target obstacle is planned, including: determining the reference trajectory point at the initial sampling moment based on the avoidance direction and the target lateral displacement; determining the reference trajectory point at the next sampling moment based on the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment.

[0016] According to the above technical means, the reference trajectory point at the initial sampling moment is determined by the avoidance direction and the target lateral displacement, and then the reference trajectory point at the next sampling moment is determined according to the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment. Compared with determining the baseline reference trajectory only through the reference trajectory detected by the perception module, since the reference trajectory point at each moment is determined based on the reference trajectory point and motion state information at the previous sampling moment, the accuracy of the reference trajectory point and the baseline reference trajectory is improved, thereby reducing the possibility of avoidance failure.

[0017] Further, based on the avoidance direction and the target lateral displacement, a reference trajectory point at an initial moment is determined, including: based on the avoidance direction, determining a target reference lane line from a left lane line and a right lane line perceived by the vehicle; based on the target reference lane line and the target lateral displacement, determining a reference trajectory point at an initial moment.

[0018] According to the above technical means, the reference trajectory point at the initial moment is determined by the target reference lane line and the target lateral displacement determined by the avoidance direction, thereby improving the accuracy of the reference trajectory point at the initial moment. At the same time, since the reference trajectory points at other sampling moments are determined based on the reference trajectory points, the accuracy of the reference trajectory points at multiple sampling moments is improved.

[0019] Furthermore, the motion state information includes yaw angular velocity and vehicle speed; based on the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment, the reference trajectory point at the next sampling moment is determined, including: based on the yaw angular velocity of the vehicle at the current sampling moment, the angle change of the vehicle between the current sampling moment and the next sampling moment is determined; based on the angle change, the yaw angular velocity of the vehicle at the current sampling moment and the driving speed of the vehicle at the current sampling moment, the lateral distance and longitudinal distance of the vehicle between the current sampling moment and the next sampling moment are determined; based on the lateral distance, the longitudinal distance, the angle change and the reference trajectory point at the current sampling moment, the reference trajectory point at the next sampling moment is determined.

[0020] According to the above technical means, the angle change of the vehicle between the current sampling moment and the next sampling moment is determined by the yaw angular velocity of the vehicle at the current sampling moment, and then the reference trajectory point at the next sampling moment is determined according to the lateral distance and longitudinal distance determined by parameters such as the angle change and the reference trajectory point at the current sampling moment, thereby enriching the information of the reference trajectory points at multiple sampling moments, and flexibly and accurately determining the reference trajectory points at multiple sampling moments through multiple parameters.

[0021] Further, based on the lateral distance, the longitudinal distance, the angle change and the reference trajectory point at the current sampling moment, the reference trajectory point at the next sampling moment is determined, including: determining the heading angle at the next sampling moment based on the heading angle and the angle change corresponding to the reference trajectory point at the current sampling moment; determining the lateral displacement at the next sampling moment based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment; determining the curvature information at the next sampling moment based on the curvature information corresponding to the target reference lane line; determining the reference trajectory point at the next sampling moment based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

[0022] According to the above technical means, the reference trajectory point at the next sampling moment is determined by determining the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment, thereby improving the accuracy of the reference trajectory point, so that the reference trajectory point at the next sampling moment contains the same type of information as the reference trajectory point at the initial moment.

[0023] Furthermore, the speed information of the vehicle at the avoidance starting point includes the vehicle speed; based on the target duration, the speed information of the vehicle at the avoidance starting point and the target steering wheel angle, a lateral offset trajectory of the vehicle relative to the baseline reference trajectory during the avoidance process is planned, including: determining an initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed; determining an initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point; determining an initial lateral speed of the vehicle based on the vehicle speed; and planning a lateral offset trajectory based on the target duration, the initial lateral acceleration, the initial lateral displacement and the initial lateral speed.

[0024] According to the above technical means, the lateral offset trajectory is planned by determining the target duration, initial lateral acceleration, initial lateral displacement and initial lateral speed, and a variety of lateral information is utilized to improve the accuracy of the lateral offset trajectory.

[0025] Furthermore, based on the target duration, the initial lateral acceleration, the initial lateral displacement and the initial lateral velocity, a lateral offset trajectory is planned, including: determining a motion parameter matrix corresponding to the initial lateral acceleration, the initial lateral displacement and the initial lateral velocity; determining a time parameter matrix corresponding to the target duration; determining a target offset parameter based on the time parameter matrix and the motion parameter matrix; and planning a lateral offset trajectory based on the target offset parameter, the target lateral displacement and the vehicle speed.

[0026] According to the above technical means, by determining the target offset parameter, the target lateral displacement and the vehicle speed, the lateral offset trajectory is planned, so that a variety of information at multiple moments of the lateral offset trajectory can be obtained, thereby improving the accuracy of the lateral offset trajectory.

[0027] Further, determining a target time required for the vehicle to avoid a target obstacle includes: obtaining lateral motion parameters of the vehicle at a starting point of avoidance relative to a reference trajectory; wherein the lateral motion parameters include at least one of the following: lateral position, lateral speed, lateral acceleration; determining the target time based on the lateral motion parameters and the vehicle speed at the starting point of avoidance.

[0028] According to the above-mentioned technical means, since the present application takes into account the vehicle's lateral position, speed, acceleration and other information when planning the target obstacle avoidance trajectory, the target duration is determined by obtaining the lateral motion parameters and the vehicle speed at the starting point of avoidance, thereby improving the accuracy of the target duration.

[0029] Furthermore, the target obstacle avoidance trajectory includes target trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; based on the baseline reference trajectory and the lateral offset trajectory, determining the target obstacle avoidance trajectory corresponding to the vehicle includes: determining the reference trajectory point at the next sampling moment in the baseline reference trajectory at the current sampling moment; superimposing the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory to obtain the target trajectory point at the next sampling moment; the above method also includes: based on the target trajectory point at the next sampling moment, controlling the vehicle to travel at the next moment.

[0030] According to the above technical means, at the current sampling moment, the reference trajectory point of the next sampling moment in the baseline reference trajectory will be determined, and the reference trajectory point of the next sampling moment and the lateral trajectory point of the next sampling moment in the lateral offset trajectory will be superimposed to obtain the target trajectory point of the next sampling moment, so that the trajectory of the vehicle at the next sampling moment is planned in advance, and the driving of the vehicle is accurately controlled. At the same time, since the target trajectory point at the next sampling moment includes information on the lateral trajectory point and the reference trajectory point, the accuracy of the target trajectory point is improved.

[0031] Furthermore, the method also includes: determining an estimated collision time between the target obstacle and the vehicle; and triggering an avoidance request when the estimated collision time satisfies a collision condition.

[0032] According to the above technical means, compared with continuously planning the avoidance trajectory, the avoidance request will only be triggered when the determined estimated collision time meets the collision conditions, so that the vehicle can trigger the emergency steering function more accurately, thereby improving the flexibility of the vehicle's trajectory planning.

[0033] A vehicle trajectory planning device, the device comprising:

[0034] A first determining unit, used to determine a target obstacle to be avoided by the vehicle in the driving direction;

[0035] A second determination unit is used to determine a reference trajectory for the vehicle to avoid a target obstacle, and to determine a target time required for the vehicle to avoid the target obstacle;

[0036] a compensation unit, configured to compensate a steering wheel angle of the vehicle at an avoidance starting point based on a response delay of the vehicle to the avoidance request, so as to obtain a target steering wheel angle;

[0037] A planning unit, used to plan a lateral offset trajectory of the vehicle relative to a reference trajectory during the avoidance process based on a target duration, speed information of the vehicle at the avoidance starting point, and a target steering wheel angle;

[0038] The third determining unit is used to determine a target obstacle avoidance trajectory corresponding to the vehicle based on the baseline reference trajectory and the lateral offset trajectory.

[0039] An electronic device comprises a processor and a memory, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, any one of the above methods is implemented.

[0040] A computer-readable storage medium stores a computer program, which implements any of the above methods when executed by a processor.

[0041] A computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the steps in any of the above methods are implemented.

[0042] A vehicle comprises the above electronic device.

[0043] Beneficial effects of this application:

[0044] (1) The present application uses a target steering wheel angle after delay compensation to determine the lateral deviation trajectory, thereby reducing the impact of delay on the lateral deviation trajectory of the vehicle and improving the accuracy of the lateral deviation trajectory;

[0045] (2) Compared with using a single trajectory as the target obstacle avoidance trajectory, the target obstacle avoidance trajectory is determined based on the reference trajectory and the lateral offset trajectory, so that the target obstacle avoidance trajectory contains more information, which improves the accuracy of the target obstacle avoidance trajectory and the flexibility of the vehicle trajectory planning;

[0046] (3) Compared with determining the reference trajectory only through the reference trajectory detected by the perception module, since the reference trajectory point at each moment is determined based on the reference trajectory point and motion state information at the previous sampling moment, the accuracy of the reference trajectory point and the reference reference trajectory is improved, thereby reducing the possibility of avoidance failure;

[0047] (4) The trajectory of the vehicle at the next sampling moment is planned in advance, and the vehicle is accurately controlled. At the same time, since the target trajectory point at the next sampling moment includes the information of the lateral trajectory point and the reference trajectory point, the accuracy of the target trajectory point is improved;

[0048] (5) Compared with continuously planning the avoidance trajectory, the avoidance request is triggered only when the estimated collision time meets the collision conditions, so that the vehicle can trigger the emergency steering function more accurately, thereby improving the flexibility of the vehicle's trajectory planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A schematic diagram of the implementation process of a vehicle trajectory planning method provided in an embodiment of the present application Figure 1 ;

[0050] Figure 2 A schematic diagram of a vehicle trajectory planning system provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of the implementation process of a vehicle trajectory planning method provided in an embodiment of the present application Figure 2 ;

[0052] Figure 4 A schematic diagram of a vehicle trajectory planning provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the structure of a vehicle trajectory planning device provided in an embodiment of the present application;

[0054] Figure 6 A hardware entity schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.

[0056] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0057] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0058] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] During the driving process, the vehicle may encounter sudden emergency situations (for example, obstacles appearing in front, pedestrians suddenly intruding, etc.), and emergency steering is required to avoid collision. The emergency steering function includes automatic emergency steering and driver-triggered emergency steering. Among them, automatic emergency steering mainly monitors the driving environment in front, side and rear of the vehicle in real time through on-board sensors, and automatically controls the steering of the vehicle when there is a risk of collision to avoid collision or mitigate the consequences of collision. Driver-triggered emergency steering is to avoid collision by turning the steering wheel manually. When there is a risk of collision in front of the vehicle, the driver triggers emergency steering to change the vehicle's driving trajectory. When the vehicle's driving trajectory triggered by the driver's emergency steering is not enough to avoid collision, the system emergency steering intervenes to avoid or mitigate the collision.

[0061] In the related technology, when the vehicle triggers an emergency turn, there is a link delay between the steering wheel angle request issued and the actual response of the steering wheel angle, so that the determined steering wheel angle value may be smaller than the actual steering wheel angle value, which may lead to the inability to avoid obstacles. In addition, in actual situations, the angle at which the driver manually turns the steering wheel may be greater than the angle requested when the system triggers the function, causing the steering wheel to turn back, posing certain safety hazards. At the same time, the lane line measured by the perception module can be used as the vehicle's driving trajectory. However, after the vehicle's emergency steering function is triggered, the vehicle turns a large angle in a short period of time (up to 400° / s or more). The vehicle trajectory detected and output only by the perception module cannot match the vehicle with rapidly changing posture, resulting in inaccurate delay compensation for lane line perception under non-steady state, and problems such as low trajectory accuracy and poor flexibility.

[0062] The embodiment of the present application provides a vehicle trajectory planning method. After determining the target obstacle to be avoided by the vehicle in the driving direction, first, by determining the reference trajectory of the vehicle to avoid the target obstacle and the target time required for the vehicle to avoid the target obstacle, secondly, by compensating the steering wheel angle of the vehicle at the starting point of the avoidance through the response delay of the vehicle to the avoidance request, the target steering wheel angle is obtained. Further, by the target time, the speed information of the vehicle at the starting point of the avoidance, and the target steering wheel angle, the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process is planned, so as to determine the target obstacle avoidance trajectory corresponding to the vehicle according to the reference reference trajectory and the lateral offset trajectory. On the one hand, the present application determines the lateral offset trajectory using the target steering wheel angle after delay compensation, reduces the influence of the delay on the lateral offset trajectory of the vehicle, and improves the accuracy of the lateral offset trajectory; on the other hand, compared with using a single trajectory as the target obstacle avoidance trajectory, the target obstacle avoidance trajectory is determined based on the reference reference trajectory and the lateral offset trajectory, so that the target obstacle avoidance trajectory contains more information, which improves the accuracy of the target obstacle avoidance trajectory and the flexibility of the vehicle's trajectory planning.

[0063] Below, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application.

[0064] Figure 1 A schematic diagram of the implementation process of a vehicle trajectory planning method provided in an embodiment of the present application Figure 1 ,like Figure 1 As shown, the method includes steps S101 to S105, wherein:

[0065] Step S101, determining a target obstacle to be avoided by the vehicle in the driving direction.

[0066] Here, the driving direction refers to the forward direction of the vehicle when driving. In some embodiments, the driving direction can be represented by a geographical direction or a road direction. For example, when the driving direction is represented by a geographical direction, the driving direction can include but is not limited to one of the following: east, south, west, north, etc. For another example, when the driving direction is represented by a road direction, the driving direction can include but is not limited to one of the following: go straight, turn left, turn right, turn around, etc.

[0067] The target obstacle is the obstacle with the highest risk of collision with the vehicle. In some embodiments, the target obstacle can be of any suitable type, such as a pedestrian, a vehicle, etc.

[0068] The method for determining the target obstacle to be avoided by the vehicle in the driving direction may include but is not limited to: determining the target obstacle to be avoided by the vehicle in the driving direction through a target detection algorithm, determining the target obstacle to be avoided by the vehicle in the driving direction through a sensor, etc. For example, the target detection algorithm uses image processing and computer vision technology to detect potential obstacles in the image. The target detection algorithm may include but is not limited to: at least one of the single-stage multi-layer target detection (Single Shot MultiBox Detector, SSD) algorithm, YOLO, etc. SDD uses VGG16 as the basic model, and adds a convolutional layer for the detection of target obstacles, which has a faster speed and accuracy. YOLO is a deep learning framework for object detection. It only needs to view the image once to detect the objects and their positions in the image, and can be used to realize the detection of target obstacles. For another example, the sensor may include but is not limited to at least one of an ultrasonic sensor, a lidar sensor, etc. The sensor can collect data about the surrounding environment of the vehicle, so as to determine the target obstacle to be avoided by the vehicle in the driving direction according to the data about the surrounding environment of the vehicle.

[0069] In some embodiments, at least one obstacle in the driving direction of the vehicle can be detected, and then the distance between the at least one obstacle and the vehicle can be determined, and the minimum distance is selected from the distances between the at least one obstacle and the vehicle, and the obstacle corresponding to the minimum distance is used as the target obstacle.

[0070] In some embodiments, the vehicle is equipped with an obstacle avoidance target selection module, which can screen out the nearest target with a collision risk on the vehicle's driving path based on at least one of the information such as the lateral and longitudinal distance, speed, type, etc. of obstacles such as a target vehicle in front of the vehicle, and use the nearest target as the target obstacle to be avoided by the vehicle in the driving direction.

[0071] Step S102, determining a reference trajectory for the vehicle to avoid a target obstacle, and determining a target time required for the vehicle to avoid the target obstacle.

[0072] Here, the baseline reference trajectory refers to the basic trajectory that the vehicle needs to achieve when avoiding the target obstacle.

[0073] Methods for determining the baseline reference trajectory may include, but are not limited to: determining the baseline reference trajectory through the vehicle's decision planning system, determining the baseline reference trajectory through the vehicle's perception module, etc. For example, the decision planning system is responsible for processing the data collected by the sensor, making driving decisions, and generating corresponding control instructions. The decision planning system can decide how the vehicle should act based on the environmental information around the vehicle, including whether it needs to avoid, how to avoid, etc. If avoidance is required, the baseline reference trajectory is determined by considering factors such as vehicle dynamics, road rules, and traffic conditions. For another example, the vehicle can be equipped with a perception module, which can include a camera, and the baseline reference trajectory can be determined based on the lane line equation coefficients detected by the camera.

[0074] In some embodiments, the reference trajectory may be any suitable curve, for example, a quadratic curve, a cubic curve, etc. The reference trajectory may be determined by determining at least one coefficient.

[0075] In some embodiments, the vehicle is equipped with a reference trajectory calculation module, which can determine the reference trajectory according to the vehicle speed, the vehicle's yaw rate, and the vehicle trajectory measured by the perception module.

[0076] In some embodiments, the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle can be planned based on the surrounding obstacle information of the target obstacle, and then the reference trajectory of the vehicle to avoid the target obstacle can be planned based on the avoidance direction, target lateral displacement and the motion state information of the vehicle.

[0077] The target duration refers to the time required for the vehicle to avoid the target obstacle. The target duration can be any suitable value, for example, 0.5s (seconds), 1.1s, etc.

[0078] Methods for determining the target duration may include, but are not limited to: determining the target duration through kinematic prediction, determining the target duration through a probability model, etc. For example, the future position of the target obstacle may be predicted based on the current speed and direction of the target obstacle, and then the target duration may be determined based on the future position of the target obstacle through a kinematic equation. For another example, a probability model takes into account uncertainty and randomness, and can be used to predict the future behavior of the target obstacle, thereby determining the target duration.

[0079] In some embodiments, the vehicle is equipped with a planning time calculation module, which can calculate the target duration based on the lateral position, lateral velocity, lateral acceleration and vehicle speed of the vehicle relative to the baseline reference trajectory.

[0080] Step S103 : Based on the response delay of the vehicle to the avoidance request, the steering wheel angle of the vehicle at the avoidance starting point is compensated to obtain a target steering wheel angle.

[0081] Here, due to the response delay of the vehicle to the avoidance request, the vehicle uses the steering wheel angle before the delay when planning the target obstacle avoidance trajectory at the avoidance starting point. Therefore, it is necessary to compensate for the steering wheel angle of the vehicle at the avoidance starting point based on the response delay of the vehicle to the avoidance request.

[0082] The vehicle's response delay to the avoidance request refers to the time difference between the vehicle sending the avoidance request and the vehicle responding to the avoidance request. The vehicle's response delay to the avoidance request can be any suitable value, for example, 0.2s, 0.4s, etc.

[0083] The avoidance starting point refers to the initial point where the vehicle avoids. The steering wheel angle refers to the angle at which the steering wheel rotates relative to its initial position. The steering wheel angle can be any suitable size, for example, 20°, 33°, etc. The target steering wheel angle refers to the angle at which the steering wheel rotates after delay compensation. The target steering wheel angle can be any suitable size, for example, 35°, 18°, etc.

[0084] In some implementations, since the target steering wheel angle is obtained by compensating the steering wheel angle of the vehicle at the avoidance starting point based on the response delay of the vehicle to the avoidance request, the target steering wheel angle is greater than the steering wheel angle.

[0085] In some implementations, the actual steering wheel angle of the vehicle within the response delay of the vehicle to the avoidance request may be calculated, and then the steering wheel angle of the vehicle at the avoidance starting point may be compensated based on the actual steering wheel angle to obtain a target steering wheel angle.

[0086] In some embodiments, the response delay of a vehicle to an avoidance request is related to the type of vehicle. Vehicles of the same vehicle type have the same response delay to an avoidance request, while vehicles of different vehicle types may have the same or different response delay to an avoidance request.

[0087] In some embodiments, the response delay of a vehicle to an avoidance request is a preset empirical value, that is, the response delay of the vehicle to an avoidance request corresponding to the vehicle can be determined through multiple experiments during vehicle manufacturing.

[0088] In some implementations, an estimated collision time between the target obstacle and the vehicle may be determined, and an avoidance request may be triggered if the estimated collision time satisfies a collision condition.

[0089] In some implementations, the steering wheel speed of the vehicle at the avoidance starting point may be acquired, and then based on the steering wheel speed and the response delay, the steering wheel angle of the vehicle at the avoidance starting point may be compensated to obtain a target steering wheel angle.

[0090] Step S104 , planning a lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process based on the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle.

[0091] Here, the speed information of the vehicle at the avoidance starting point is used to characterize the motion state of the vehicle at the avoidance starting point. The lateral offset trajectory is used to characterize the lateral displacement of the vehicle relative to the reference trajectory during the avoidance process.

[0092] In some embodiments, the lateral offset trajectory may be any suitable curve, for example, a quadratic curve, a cubic curve, etc. The lateral offset trajectory may be determined by determining at least one coefficient.

[0093] In some embodiments, the target lateral displacement of the vehicle can be determined based on the lateral distance between the baseline reference trajectory and the vehicle, and then the lateral offset trajectory of the vehicle relative to the baseline reference trajectory during the avoidance process is planned based on the target lateral displacement, target duration, vehicle speed information at the avoidance starting point, and target steering wheel angle.

[0094] In some embodiments, the vehicle is equipped with a curve planning module, which can plan the lateral offset trajectory of the vehicle relative to the baseline reference trajectory during the avoidance process based on the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle.

[0095] In some embodiments, the speed information of the vehicle at the avoidance starting point includes the vehicle speed. The initial lateral acceleration of the vehicle at the avoidance starting point can be determined based on the target steering wheel angle and the vehicle speed. The initial lateral displacement of the vehicle can be determined based on the position information of the vehicle at the avoidance starting point. The initial lateral speed of the vehicle can be determined based on the vehicle speed. Then, the lateral offset trajectory can be planned based on the target duration, the initial lateral acceleration, the initial lateral displacement and the initial lateral speed.

[0096] Step S105, determining a target obstacle avoidance trajectory corresponding to the vehicle based on the baseline reference trajectory and the lateral offset trajectory.

[0097] Here, the target obstacle avoidance trajectory refers to the trajectory along which the vehicle travels to avoid the target obstacle.

[0098] The method for determining the target obstacle avoidance trajectory corresponding to the vehicle may include, but is not limited to: determining the target obstacle avoidance trajectory corresponding to the vehicle by sampling, determining the target obstacle avoidance trajectory corresponding to the vehicle by a preset model, etc. For example, any suitable sampling algorithm may be used, such as a rapidly expanding random tree, a probabilistic roadmap, etc., to randomly sample multiple points from the baseline reference trajectory and the lateral offset trajectory, and then determine the target obstacle avoidance trajectory corresponding to the vehicle based on the sampled points. For another example, the preset model has the function of superimposing a curve, the baseline reference trajectory and the lateral offset trajectory are input into the preset model, and the result output by the preset model is used as the target obstacle avoidance trajectory corresponding to the vehicle.

[0099] In some embodiments, the target obstacle avoidance trajectory integrates information of the baseline reference trajectory and the lateral offset trajectory. When determining the target obstacle avoidance trajectory corresponding to the vehicle based on the baseline reference trajectory and the lateral offset trajectory, different weight values ​​can be assigned to the baseline reference trajectory and the lateral offset trajectory so that the target obstacle avoidance trajectory contains different proportions of the baseline reference trajectory and the lateral offset trajectory.

[0100] In some embodiments, the vehicle is equipped with a lateral control final trajectory calculation module, which can determine a target obstacle avoidance trajectory corresponding to the vehicle based on a baseline reference trajectory and a lateral offset trajectory.

[0101] In some embodiments, the target obstacle avoidance trajectory includes target trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle. The reference trajectory point at the next sampling moment in the baseline reference trajectory can be determined at the current sampling moment, and the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory are superimposed to obtain the target trajectory point at the next sampling moment.

[0102] In the embodiment of the present application, after determining the target obstacle to be avoided by the vehicle in the driving direction, first, by determining the reference trajectory of the vehicle to avoid the target obstacle and the target time required for the vehicle to avoid the target obstacle, secondly, by compensating the steering wheel angle of the vehicle at the starting point of the avoidance through the response delay of the vehicle to the avoidance request, the target steering wheel angle is obtained, and further, by the target time, the speed information of the vehicle at the starting point of the avoidance and the target steering wheel angle, the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process is planned, so as to determine the target obstacle avoidance trajectory corresponding to the vehicle according to the reference reference trajectory and the lateral offset trajectory. On the one hand, the present application determines the lateral offset trajectory using the target steering wheel angle after delay compensation, reduces the influence of the delay on the lateral offset trajectory of the vehicle, and improves the accuracy of the lateral offset trajectory; on the other hand, compared with using a single trajectory as the target obstacle avoidance trajectory, the target obstacle avoidance trajectory is determined based on the reference reference trajectory and the lateral offset trajectory, so that the target obstacle avoidance trajectory contains more information, while improving the accuracy of the target obstacle avoidance trajectory, it also improves the flexibility of the vehicle's trajectory planning.

[0103] In some embodiments, the vehicle trajectory planning method of the present application can be executed when the emergency avoidance operation of the vehicle is triggered. After the emergency avoidance operation is triggered, the response delay between the avoidance request and the actual response of the vehicle's actuator can be reduced to reduce the impact of the vehicle's obstacle avoidance trajectory planning, thereby improving the accuracy of obstacle avoidance control. Among them, the vehicle's emergency avoidance operation may include but is not limited to the vehicle's automatic emergency steering operation, and / or the driver-triggered emergency steering operation. The vehicle's actuator is used to perform the automatic emergency avoidance operation in response to the avoidance request.

[0104] In some embodiments, the trajectory planning method of the vehicle of the present application can be implemented at the trajectory planning end of the vehicle. In this way, the vehicle's steering wheel angle at the avoidance starting point is compensated by the trajectory planning method of the vehicle of the present application to obtain the target steering wheel angle, so that the target obstacle avoidance trajectory obtained based on the target steering wheel angle planning has taken into account the compensation for the response delay of the avoidance request, and the control end and / or the execution end of the vehicle can perform automatic emergency avoidance operations according to the target obstacle avoidance trajectory, without the need for the control end and / or the execution end to adjust parameters according to the response delay under different emergency avoidance mechanisms, which can simplify the control and / or response logic of the vehicle's automatic emergency avoidance operation, save computing resources, and at the same time, improve the flexibility of the vehicle's trajectory planning. Among them, the emergency avoidance mechanism may include but is not limited to the vehicle's automatic emergency steering (AES) mechanism, and / or the driver-triggered emergency steering (DES) mechanism, etc.

[0105] In some implementations, step S103 includes step S131 and step S132, wherein:

[0106] Step S131, obtaining the steering wheel speed of the vehicle at the avoidance starting point.

[0107] Here, the steering wheel speed refers to the speed at which the steering wheel rotates, that is, the angle the steering wheel turns per unit time. The steering wheel speed of the vehicle at the avoidance starting point can be any suitable value, for example, 22.6° / s, 100° / s, etc.

[0108] The method for obtaining the steering wheel speed of the vehicle at the avoidance starting point may include but is not limited to: obtaining the steering wheel speed of the vehicle at the avoidance starting point through a steering wheel angle sensor (SAS), obtaining the steering wheel speed of the vehicle at the avoidance starting point through an incremental angle encoder, etc. For example, the SAS can be used to detect the middle position, rotation direction, rotation angle and rotation speed of the steering wheel, and the steering wheel speed of the vehicle at the avoidance starting point can be obtained by reading the parameters of the SAS. For another example, the incremental angle encoder uses the principle of photoelectric conversion to output three sets of square waves, and the steering wheel speed can be calculated through these three sets of square waves, thereby obtaining the steering wheel speed of the vehicle at the avoidance starting point.

[0109] In some embodiments, the vehicle is equipped with a vehicle motion state module, which can be used to obtain the steering wheel speed of the vehicle at the avoidance starting point.

[0110] Step S132: Based on the steering wheel speed and the response delay, the steering wheel angle of the vehicle at the avoidance starting point is compensated to obtain a target steering wheel angle.

[0111] Here, the steering wheel rotation angle within the response delay can be determined based on the steering wheel speed and the response delay, and then the steering wheel angle of the vehicle at the avoidance starting point can be compensated based on the steering wheel rotation angle within the response delay to obtain the target steering wheel angle.

[0112] In some implementations, the target steering wheel angle SteerAnglePre may be determined by the following formula (1-1), that is, see formula (1-1):

[0113] SteerAnglePre=SteerAngle+SteerAngleRate*T_daly (1-1);

[0114] In formula (1-1), SteerAngle is the steering wheel angle of the vehicle at the avoidance starting point, SteerAngleRate is the steering wheel speed, and T_daly is the response delay.

[0115] In the implementation manner of the present application, the steering wheel angle of the vehicle at the avoidance starting point is compensated by the steering wheel speed and the response delay, thereby improving the accuracy of the target steering wheel angle and reducing the influence of the delay on the target steering wheel angle.

[0116] In some embodiments, the “determining a reference trajectory for the vehicle to avoid a target obstacle” in step S102 includes steps S11 and S12, wherein:

[0117] Step S11, based on the surrounding obstacle information of the target obstacle, planning the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle.

[0118] Here, when avoiding a target obstacle, the vehicle needs to refer to the surrounding obstacle information of the target obstacle so that the planned target obstacle avoidance trajectory will not collide with other obstacles again, thereby improving the driving safety of the vehicle.

[0119] The surrounding obstacle information of the target obstacle refers to the information of other obstacles on the left and right sides of the target obstacle. The surrounding obstacle information of the target obstacle may include but is not limited to: at least one of the position information of the surrounding obstacles, the size information of the surrounding obstacles, the speed and movement direction of the surrounding obstacles, the type of the surrounding obstacles, the road boundary conditions, etc.

[0120] In some implementations, the environmental information around the vehicle may be acquired through a perception module, thereby extracting relevant information of the target obstacle based on the environmental information around the vehicle, and then determining surrounding obstacle information of the target obstacle based on the relevant information of the target obstacle.

[0121] The avoidance direction of the target obstacle can be any suitable direction, for example, left, right, etc. The target lateral displacement refers to the lateral displacement of the vehicle at the avoidance end point relative to the vehicle at the avoidance start point. The target lateral displacement can be any suitable size, for example, 1.5m (meters), 2m, etc.

[0122] The planning method of the avoidance direction and the target lateral displacement may include but is not limited to: planning the avoidance direction and the target lateral displacement through the Frenet coordinate system, planning the avoidance direction and the target lateral displacement through optimization methods, etc. For example, the Frenet coordinate system is widely used in trajectory planning. The movement of surrounding obstacles can be decomposed into two dimensions, longitudinal and lateral, which can make trajectory decisions and planning more efficient. This method involves variable boundary constraints such as maximum lateral displacement, maximum speed, maximum acceleration, and constraints based on kinematic formulas.

[0123] In some embodiments, the vehicle is equipped with an emergency steering decision module, which can plan the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle based on the surrounding obstacle information of the target obstacle.

[0124] In some embodiments, the lateral displacement of the vehicle when avoiding a target obstacle should not be too large or too small. If the lateral displacement is too large, the vehicle will turn a larger angle within the avoidance time, affecting the driver's driving experience. If the lateral displacement is too small, the vehicle may not be able to avoid the target obstacle sufficiently, causing a traffic accident. Therefore, when planning the target lateral displacement, the offset interval can be determined based on the surrounding obstacle information of the target obstacle, and the median or average value can be selected in the offset interval, and then the median or average value can be used as the target lateral displacement.

[0125] Exemplarily, by analyzing the surrounding obstacle information of the target obstacle, it is found that there are fewer surrounding obstacles on the left side of the target obstacle than on the right side of the target obstacle, and the space on the left side of the target obstacle is larger. The left can be used as the avoidance direction of the target obstacle, and the target lateral displacement can be planned on the left side of the target obstacle.

[0126] Step S12, planning a reference trajectory for the vehicle to avoid the target obstacle based on the avoidance direction, the target lateral displacement and the motion state information of the vehicle.

[0127] Here, the vehicle's motion state information may include, but is not limited to, at least one of: yaw rate, vehicle speed, and the like.

[0128] In some implementations, at least one coefficient may be determined based on the avoidance direction, the target lateral displacement, and the motion state information of the vehicle, so as to plan the reference trajectory according to the at least one coefficient and the number of the reference trajectory.

[0129] In some embodiments, the vehicle is equipped with a vehicle motion state module, which can be used to provide current motion state information of the vehicle.

[0130] In some embodiments, the baseline reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle. The reference trajectory points at the initial sampling moment can be determined based on the avoidance direction and the target lateral displacement, and then the reference trajectory points at the next sampling moment can be determined based on the reference trajectory points at the current sampling moment and the motion state information of the vehicle at the current sampling moment, thereby determining the baseline reference trajectory.

[0131] In some embodiments, a key point may be selected as the vehicle coordinate origin, a vehicle coordinate system may be established based on the vehicle coordinate origin, and then a reference track may be planned in the vehicle coordinate system. The reference track may be represented by the lateral displacement of the vehicle relative to the avoidance starting point, the heading angle of the vehicle, and the curvature information of the vehicle. The curvature information may include, but is not limited to, at least one of the curvature at the vehicle coordinate origin, the curvature change rate at the vehicle coordinate origin, and the like.

[0132] In some implementations, when the reference trajectory is a cubic curve, the reference trajectory may be expressed by the following formula (1-2), that is, see formula (1-2):

[0133] y=A0+A1*x+A2*x 2 +A3*x 3 (1-2);

[0134] In formula (1-2), x is the longitudinal position in the vehicle coordinate system, y is the lateral position in the vehicle coordinate system, A0 corresponds to the lateral displacement of the vehicle relative to the avoidance starting point, A1 corresponds to the heading angle at the origin of the vehicle coordinate system, A2 corresponds to the curvature at the origin of the vehicle coordinate system, and A3 corresponds to the rate of change of curvature at the origin of the vehicle coordinate system.

[0135] In an embodiment of the present application, the avoidance direction and the target lateral displacement of the surrounding obstacle information of the target obstacle are used, and the baseline reference trajectory is planned by the avoidance direction, the target lateral displacement and the motion state information of the vehicle, so that the baseline reference trajectory includes multiple information, thereby improving the accuracy of the baseline reference trajectory.

[0136] In some embodiments, the reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; step S12 includes step S121 and step S122, wherein:

[0137] Step S121, determining a reference trajectory point at an initial sampling time based on the avoidance direction and the target lateral displacement.

[0138] Here, the reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle, and the multiple sampling moments include an initial sampling moment. The initial sampling moment is the moment when the vehicle is at the avoidance starting point.

[0139] In some implementations, the baseline reference trajectory may be represented by heading angles corresponding to a plurality of sampling moments, lateral displacements corresponding to a plurality of sampling moments, and curvature information corresponding to a plurality of sampling moments.

[0140] In some implementations, there is a fixed time interval between the multiple sampling moments, and the time interval may be of any appropriate size, for example, 0.01 s, 0.05 s, etc.

[0141] In some implementations, at least one coefficient may be determined based on the avoidance direction and the target lateral displacement, and then a coordinate point may be determined according to the at least one coefficient, and the coordinate point may be used as a reference trajectory point at the initial sampling moment.

[0142] In some embodiments, the target reference lane line can be determined from the left lane line and the right lane line perceived by the vehicle based on the avoidance direction, and then the reference trajectory point at the initial moment is determined based on the target reference lane line and the target lateral displacement.

[0143] Step S122, based on the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment, determine the reference trajectory point at the next sampling moment.

[0144] Here, the reference trajectory point at the current sampling moment may be compensated based on the motion state information at the current sampling moment to determine the reference trajectory point at the next sampling moment.

[0145] In some embodiments, the offset information of the reference trajectory point at the current sampling moment within the time interval can be determined based on the time interval between the current sampling moment and the next sampling moment and the motion state information at the current sampling moment, and then the reference trajectory point at the current sampling moment is compensated based on the offset information of the reference trajectory point at the current sampling moment within the time interval to determine the reference trajectory point at the next sampling moment.

[0146] In some embodiments, the motion state information includes the yaw angular velocity and the vehicle speed. The angular change of the vehicle between the current sampling moment and the next sampling moment can be determined based on the yaw angular velocity of the vehicle at the current sampling moment, and then the lateral distance and longitudinal distance of the vehicle between the current sampling moment and the next sampling moment can be determined based on the angular change, the yaw angular velocity of the vehicle at the current sampling moment, and the driving speed of the vehicle at the current sampling moment. Finally, the reference trajectory point at the next sampling moment is determined based on the lateral distance, the longitudinal distance, the angular change, and the reference trajectory point at the current sampling moment.

[0147] In an embodiment of the present application, the reference trajectory point at the initial sampling moment is determined by the avoidance direction and the target lateral displacement, and then the reference trajectory point at the next sampling moment is determined according to the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment. Compared with determining the baseline reference trajectory only by the reference trajectory detected by the perception module, since the reference trajectory point at each moment is determined based on the reference trajectory point and the motion state information at the previous sampling moment, the accuracy of the reference trajectory point and the baseline reference trajectory is improved, thereby reducing the possibility of avoidance failure.

[0148] In some implementations, step S121 includes step S1211 and step S1212, wherein:

[0149] Step S1211, based on the avoidance direction, determine the target reference lane line from the left lane line and the right lane line perceived by the vehicle.

[0150] Here, the left lane line refers to the lane line on the left side of the vehicle, and the right lane line refers to the lane line on the right side of the vehicle.

[0151] In some embodiments, the left lane line and the right lane line are lane lines located in a real scene. The left lane line and the right lane line can be detected by a perception module.

[0152] In some implementations, a first correspondence relationship between the avoidance direction and the lane line may be established, and according to the first correspondence relationship, the target reference lane line may be determined based on the avoidance direction.

[0153] In some implementations, when the avoidance direction is to the left, the left lane line is used as the target reference lane line, and when the avoidance direction is to the right, the right lane line is used as the target reference lane line.

[0154] In some embodiments, the target reference lane line may be any suitable curve, such as a quadratic curve, a cubic curve, etc.

[0155] Step S1212, determining the reference trajectory point at the initial moment based on the target reference lane line and the target lateral displacement.

[0156] Here, the target reference lane line and the reference trajectory point at the initial moment can be represented by the lateral displacement, heading angle, and curvature information of the vehicle relative to the avoidance starting point.

[0157] In some embodiments, the curvature information of the target reference lane line can be used as the curvature information of the reference trajectory point at the initial moment, the heading angle of the target reference lane line can be used as the heading angle of the reference trajectory point at the initial moment, and the target lateral displacement can be used as the lateral displacement of the reference trajectory point at the initial moment, and then the reference trajectory point at the initial moment can be determined based on the target reference lane line and the target lateral displacement.

[0158] In the implementation manner of the present application, the reference trajectory point at the initial moment is determined by the target reference lane line and the target lateral displacement determined by the avoidance direction, thereby improving the accuracy of the reference trajectory point at the initial moment. At the same time, since the reference trajectory points at other sampling moments are determined based on the reference trajectory points, the accuracy of the reference trajectory points at multiple sampling moments is improved.

[0159] In some embodiments, the motion state information includes yaw rate and vehicle speed; step S122 includes steps S1221 to S1223, wherein:

[0160] Step S1221, based on the yaw angular velocity of the vehicle at the current sampling moment, determine the angle change of the vehicle between the current sampling moment and the next sampling moment.

[0161] Here, the motion state information includes yaw rate and vehicle speed. The yaw rate refers to the speed at which the vehicle rotates laterally during a turn. The yaw rate can be any suitable value, for example, 300° / s, 120° / s, etc. The vehicle speed can be any suitable value, for example, 60km / h (kilometers per hour), 15m / s (meters per second), etc. The angle change can be any suitable value, for example, 15°, 43°, etc.

[0162] In some implementations, the angular change of the vehicle between the current sampling moment and the next sampling moment may be determined based on the yaw rate of the vehicle at the current sampling moment and the time interval between the current sampling moment and the next sampling moment.

[0163] In some embodiments, the angle change delta_θ may be determined by the following formula (1-3), that is, see formula (1-3):

[0164] delta_θ=HostYawRate*SampleTime (1-3);

[0165] In formula (1-3), HostYawRate is the yaw angular velocity, and SampleTime is the time interval between sampling moments.

[0166] Step S1222, based on the angle change, the yaw rate of the vehicle at the current sampling time, and the driving speed of the vehicle at the current sampling time, determine the lateral distance and longitudinal distance of the vehicle between the current sampling time and the next sampling time.

[0167] Here, the driving speed of the vehicle at the current sampling moment may be any appropriate value, for example, 54 km / h, 12 m / s, etc.

[0168] In some embodiments, it is possible to first determine whether the vehicle is in uniform circular motion or uniform linear motion between the current sampling moment and the next sampling moment based on the angle change, and then select a target parameter based on the determination result to determine the lateral distance and longitudinal distance of the vehicle between the current sampling moment and the next sampling moment. The target parameter may include, but is not limited to, at least one of the angle change, the yaw rate of the vehicle at the current sampling moment, and the driving speed of the vehicle at the current sampling moment.

[0169] In some embodiments, when the angle change is greater than the angle threshold, it is considered that the vehicle is performing uniform circular motion between the current sampling moment and the next sampling moment. When the angle change is not greater than the angle threshold, it is considered that the vehicle is performing uniform linear motion between the current sampling moment and the next sampling moment.

[0170] In some embodiments, when the vehicle performs uniform circular motion between the current sampling moment and the next sampling moment, the lateral distance dx and the longitudinal distance dy of the vehicle between the current sampling moment and the next sampling moment can be determined by the following formula (1-4), that is, see formula (1-4):

[0171]

[0172] In formula (1-4), delta_θ is the angle change of the vehicle at the current sampling time, HostSpeed ​​is the driving speed of the vehicle at the current sampling time, and HostYawRate is the yaw angular velocity of the vehicle at the current sampling time.

[0173] In some embodiments, when the vehicle is moving in a uniform straight line between the current sampling moment and the next sampling moment, the lateral distance dx and the longitudinal distance dy of the vehicle between the current sampling moment and the next sampling moment can be determined by the following formula (1-5), that is, see formula (1-5):

[0174] dx=HostSpeed*SampleTime

[0175] dy=0.5*HostYawRate*HostSpeed*SampleTime*SampleTime (1-5);

[0176] In formula (1-5), HostSpeed ​​is the vehicle's driving speed at the current sampling time, and HostYawRate is the vehicle's yaw angular velocity at the current sampling time.

[0177] Step S1223, based on the horizontal distance, the vertical distance, the angle change and the reference trajectory point at the current sampling moment, determine the reference trajectory point at the next sampling moment.

[0178] Here, the reference trajectory at the current sampling moment may be compensated based on the lateral distance, the longitudinal distance, and the angle variation, so as to determine the reference trajectory point at the next sampling moment.

[0179] In some embodiments, the heading angle at the next sampling moment can be determined based on the heading angle and angle change corresponding to the reference trajectory point at the current sampling moment, the lateral displacement at the next sampling moment can be determined based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment, the curvature information at the next sampling moment can be determined based on the curvature information corresponding to the target reference lane line, and then the reference trajectory point at the next sampling moment can be determined based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

[0180] In an implementation manner of the present application, the angular change of the vehicle between the current sampling moment and the next sampling moment is determined by the yaw angular velocity of the vehicle at the current sampling moment, and then the reference trajectory point at the next sampling moment is determined based on the lateral distance and longitudinal distance determined by parameters such as the angular change and the reference trajectory point at the current sampling moment, thereby enriching the information of the reference trajectory points at multiple sampling moments, and flexibly and accurately determining the reference trajectory points at multiple sampling moments through multiple parameters.

[0181] In some embodiments, step S1223 includes steps S1223a to S1223d, wherein:

[0182] Step S1223a, based on the heading angle and angle change corresponding to the reference trajectory point at the current sampling moment, determine the heading angle at the next sampling moment.

[0183] Here, the angle change refers to the angle change between the current sampling moment and the next sampling moment. Based on the angle change, the heading angle corresponding to the reference trajectory point at the current sampling moment can be compensated to determine the heading angle at the next sampling moment.

[0184] In some implementations, the heading angle A11 at the next sampling moment may be determined by the following formula (1-6), that is, see formula (1-6):

[0185] A11=tan(atan(A1_n_1)-delta_θ) (1-6);

[0186] In formula (1-6), A1_n_1 is the heading angle corresponding to the reference trajectory point at the current sampling time, and delta_θ is the angle change corresponding to the reference trajectory point at the current sampling time.

[0187] Step S1223b, based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment, determines the lateral displacement at the next sampling moment.

[0188] Here, the curvature information corresponding to the reference trajectory point at the current sampling moment may include but is not limited to: at least one of the curvature corresponding to the reference trajectory point at the current sampling moment, the curvature change rate corresponding to the reference trajectory point at the current sampling moment, and the like.

[0189] In some embodiments, the curvature information corresponding to the reference trajectory point at the current sampling moment and the heading angle corresponding to the reference trajectory point at the current sampling moment can be compensated based on the lateral distance and the longitudinal distance, and then the lateral displacement at the next sampling moment is determined in combination with the lateral displacement corresponding to the reference trajectory point at the current sampling moment.

[0190] In some implementations, the heading angle A01 at the next sampling moment may be determined by the following formula (1-7), that is, see formula (1-7):

[0191] A01=A0_n_1+A1_n_1*dx+A2_n_1*(dx 2 )+A3_n_1d(dx 2 *dx)-dy (1-7);

[0192] In formula (1-7), dx is the lateral distance, dy is the longitudinal distance, A0_n_1 is the lateral displacement corresponding to the reference trajectory point at the current sampling time, A1_n_1 is the heading angle corresponding to the reference trajectory point at the current sampling time, A2_n_1 is the curvature corresponding to the reference trajectory point at the current sampling time, and A3_n_1 is the curvature change rate corresponding to the reference trajectory point at the current sampling time.

[0193] Step S1223c, based on the curvature information corresponding to the target reference lane line, determine the curvature information at the next sampling moment.

[0194] Here, since the shape of the baseline reference trajectory is less affected by the steering motion of the vehicle, the curvature information corresponding to the target reference lane line can be used to determine the curvature information at the next sampling moment.

[0195] In some implementations, the curvature information corresponding to the target reference lane line, the weighted / logarithmic / indexed value of the curvature information corresponding to the target reference lane line, etc. may be used as the curvature information at the next sampling moment.

[0196] Step S1223d, determining the reference trajectory point at the next sampling moment based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

[0197] Here, since the reference trajectory point can be represented by the heading angle, the lateral displacement and the curvature information, the heading angle at the next sampling moment, the lateral displacement at the next sampling moment and the curvature information at the next sampling moment can be used as at least one coefficient to determine the reference trajectory point at the next sampling moment based on the at least one coefficient.

[0198] In an embodiment of the present application, the reference trajectory point at the next sampling moment is determined by determining the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment, thereby improving the accuracy of the reference trajectory point, so that the reference trajectory point at the next sampling moment contains the same type of information as the reference trajectory point at the initial moment.

[0199] In some embodiments, the speed information of the vehicle at the avoidance starting point includes the vehicle speed; step S104 includes steps S141 to S144, wherein:

[0200] Step S141, determining the initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed.

[0201] Here, the target steering wheel angle can be any suitable value, such as 35°, 18°, etc. The vehicle speed can be any suitable value, such as 60 km / h, 15 m / s, etc. The initial lateral acceleration of the vehicle at the avoidance starting point can be any suitable value, such as 5 m / s 2 (m / s2), 2.56m / s 2 wait.

[0202] In some embodiments, the front wheel steering angle can be determined based on the target steering wheel angle and the steering ratio of the vehicle, and then the initial lateral acceleration of the vehicle at the avoidance starting point can be determined based on the front wheel steering angle and the vehicle speed. The steering ratio of the vehicle refers to the ratio of the steering wheel steering angle to the wheel steering angle. The steering ratio of the vehicle can be any suitable value, for example, 1.1, 0.5, etc.

[0203] In some embodiments, the steering ratio of a vehicle is related to the type of vehicle. The steering ratios corresponding to the same vehicle type are the same, and the steering ratios corresponding to different vehicle types may be the same or different.

[0204] The front wheel steering angle δ can be determined by the following formula (1-8), that is, see formula (1-8):

[0205] δ=SteerAnglePre / SteerRatio (1-8);

[0206] In formula (1-8), SteerAnglePre is the target steering wheel angle, and SteerRation is the steering ratio of the vehicle.

[0207] In some embodiments, the curvature of the circular motion of the vehicle can be calculated based on the front wheel steering angle in combination with the Ackermann angle formula and the vehicle dynamics equation, and then the initial lateral acceleration of the vehicle at the avoidance starting point can be determined based on the curvature of the circular motion of the vehicle, the curvature corresponding to the baseline reference trajectory, and the vehicle speed at the avoidance starting point.

[0208] The initial lateral acceleration LatAccel can be determined by the following formula (1-9), that is, see formula (1-9):

[0209] LatAccel=(host_ρ-2*A2)*HostSpeed*HostSpeed ​​(1-9);

[0210] In formula (1-9), host_ρ is the curvature of the ego vehicle's circular motion, A2 is the curvature corresponding to the reference trajectory, and HostSpeed ​​is the vehicle speed at the starting point of the avoidance. L is the vehicle wheelbase, K is the understeer slope, and R is the turning radius. According to the Ackerman turning angle formula and the vehicle dynamics equations Calculate host_ρ, where HostAccel is the absolute lateral acceleration of the vehicle.

[0211] Step S142, determining the initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point.

[0212] Here, the initial lateral displacement may be any appropriate size, for example, 0.5 m, 3 m, etc.

[0213] In some implementations, the initial lateral displacement of the vehicle may be determined based on a lateral position relationship between the position information of the vehicle at the avoidance starting point and the reference trajectory.

[0214] In some implementations, the initial lateral displacement of the vehicle may be determined based on deviation information between the position information of the vehicle at the avoidance start point and the position information of the vehicle at the avoidance end point.

[0215] Step S143, determining the initial lateral speed of the vehicle based on the vehicle speed.

[0216] Here, the initial lateral velocity may be any appropriate value, for example, 5 m / s, 1.5 m / s, etc.

[0217] In some implementations, the vehicle speed may be decomposed to obtain an initial longitudinal speed of the vehicle and an initial lateral speed of the vehicle, thereby determining the initial lateral speed of the vehicle.

[0218] In some implementations, an initial lateral velocity of the vehicle may be determined based on the vehicle velocity and a heading angle at a vehicle coordinate origin.

[0219] In some embodiments, the initial lateral speed LatSpeed ​​may be determined by the following formula (1-10), that is, see formula (1-10):

[0220] LatSpeed=HostSpeed*sin(atan(A1)) (1-10);

[0221] In formula (1-10), HostSpeed ​​is the vehicle speed at the avoidance starting point, and A1 is the heading angle at the vehicle coordinate origin.

[0222] In some embodiments, the vehicle is equipped with a trajectory initial state calculation module, which can determine the initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed, determine the initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point, and determine the initial lateral speed of the vehicle based on the vehicle speed.

[0223] Step S144, planning a lateral deviation trajectory based on the target duration, the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity.

[0224] Here, the target duration, the initial lateral acceleration, the initial lateral displacement, and the initial lateral speed may be used as at least one parameter to plan the lateral offset trajectory according to the at least one parameter.

[0225] In some embodiments, the vehicle is equipped with a curve planning module, which can plan a lateral offset trajectory based on a target duration, an initial lateral acceleration, an initial lateral displacement, and an initial lateral velocity.

[0226] In some embodiments, a motion parameter matrix corresponding to the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity can be determined, and a time parameter matrix corresponding to the target duration can be determined. Then, a target offset parameter can be determined based on the time parameter matrix and the motion parameter matrix, so as to plan a lateral offset trajectory based on the target offset parameter, the target lateral displacement, and the vehicle speed.

[0227] In the implementation manner of the present application, the lateral offset trajectory is planned by determining the target duration, initial lateral acceleration, initial lateral displacement and initial lateral speed, and a variety of lateral information is utilized to improve the accuracy of the lateral offset trajectory.

[0228] In some implementations, step S144 includes steps S1441 to S1444, wherein:

[0229] Step S1441, determining a motion parameter matrix corresponding to the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity.

[0230] Here, the motion parameter matrix may be a matrix including row vectors or column vectors.

[0231] In some implementations, the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity may be used as matrix elements in a motion parameter matrix to determine the motion parameter matrix corresponding to the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity.

[0232] The motion parameter matrix y can be determined by the following formula (1-11): out , that is, see formula (1-11):

[0233]

[0234] In formula (1-11), LatAccel is the initial lateral acceleration, LatPos is the initial lateral displacement, and LatSpeed ​​is the initial lateral speed.

[0235] Step S1442, determining the time parameter matrix corresponding to the target duration.

[0236] Here, the time parameter matrix includes at least one element.

[0237] In some implementations, the time parameter matrix corresponding to the target duration may be determined by performing interpolation planning on the target duration.

[0238] In some implementations, the target duration may be interpolated any appropriate number of times, for example, five times, four times, etc.

[0239] In some embodiments, the motion parameter matrix T can be determined by the following formula (1-12): matrix , that is, see formula (1-12):

[0240]

[0241] In formula (1-12), T is the target duration.

[0242] Step S1443: Determine the target offset parameter based on the time parameter matrix and the motion parameter matrix.

[0243] Here, the target offset parameters are used to plan the lateral offset trajectory.

[0244] In some implementations, the target offset parameter may be determined based on an inverse matrix corresponding to a time parameter matrix and a motion parameter matrix.

[0245] In some implementations, the target offset parameter C[c(1), c(2), c(3)] may be determined by the following formula (1-13), that is, see formula (1-13):

[0246] C[c(1),c(2),c(3)]=T matrix \y out (1-13);

[0247] In formula (1-13), T matrix is the motion parameter matrix, y out is the motion parameter matrix, c(1), c(2), c(3) are the first element, second element and third element in the target offset parameter respectively.

[0248] Step S1444, planning a lateral offset trajectory based on the target offset parameter, the target lateral displacement and the vehicle speed.

[0249] Here, the target lateral displacement and the vehicle speed may be compensated based on the target offset parameter to plan the lateral offset trajectory.

[0250] In some embodiments, the lateral offset trajectory includes offset trajectory points at multiple sampling moments during the process of the vehicle avoiding the target obstacle. The lateral offset trajectory can be planned based on the time interval between the sampling moments, the target offset parameter, the target lateral displacement, and the vehicle speed.

[0251] In some embodiments, the lateral offset trajectory includes at least one coefficient, and the offset trajectory points at different sampling moments can be planned based on the time interval between sampling moments, the target offset parameter, the target lateral displacement, and the vehicle speed to plan the lateral offset trajectory.

[0252] In some embodiments, the offset trajectory points at different sampling moments are represented by a first offset trajectory coefficient, a second offset trajectory coefficient, and a third offset trajectory coefficient.

[0253] In some embodiments, when planning the lateral offset trajectory, it is necessary to count the total duration corresponding to each sampling moment. When the total duration is greater than the target duration or the lateral control is exited, the first offset trajectory coefficient is equal to the target lateral displacement, and the first offset trajectory coefficient and the second offset trajectory coefficient are 0.

[0254] In some embodiments, the first deviation track coefficient DeltA0, the second deviation track coefficient DeltA1, and the third deviation track coefficient DeltA2 may be determined by the following formula (1-14), that is, see formula (1-14):

[0255] DeltA0=c(1)*t 3 +c(2)*t 4 +c(3)*t 5 -DeltOffset

[0256] DeltA1=(3*c(1)*t 2 +4*c(2)*t 3 +5*c(3)*t 4 ) / Speed

[0257] DeltA2=(6*c(1)*t+12*c(2)*t 2 +20*c(3)*t 3 ) / (2*Speed) (1-14);

[0258] In formula (1-14), t = t last +dt, t is 0 when the interpolation is triggered, dt is the time interval, DeltOffset is the lateral displacement LatPos of the avoidance starting point, Speed ​​is the vehicle speed at the avoidance starting point, c(1), c(2), c(3) are the first element, second element and third element in the target offset parameter respectively.

[0259] In the implementation manner of the present application, by determining the target offset parameter, the target lateral displacement and the vehicle speed, the lateral offset trajectory is planned, so that a variety of information at multiple moments of the lateral offset trajectory can be obtained, thereby improving the accuracy of the lateral offset trajectory.

[0260] In some embodiments, the “determining the target time required for the vehicle to avoid the target obstacle” in step S102 includes step S1021 and step S1022, wherein:

[0261] Step S1021, obtaining the lateral motion parameters of the vehicle at the avoidance starting point relative to the reference trajectory; wherein the lateral motion parameters include at least one of the following: lateral position, lateral velocity, and lateral acceleration.

[0262] Here, the lateral motion parameter is used to indicate the lateral motion state of the vehicle. The lateral motion parameter includes at least one of the following: lateral position, lateral velocity, and lateral acceleration. The lateral acceleration can be any suitable value, for example, 5 m / s 2 , 2.56m / s 2 wait.

[0263] In some implementations, the lateral motion parameters of the vehicle at the avoidance starting point relative to the reference trajectory may be obtained by reading the parameters in the vehicle motion state module.

[0264] Step S1022, determining a target duration based on the lateral motion parameter and the vehicle speed at the avoidance starting point.

[0265] Here, the target duration may be any appropriate size, for example, 1.1s, 2s, etc.

[0266] In some embodiments, the vehicle is equipped with a planning time calculation module, which can determine the target duration based on the lateral motion parameters and the vehicle speed at the avoidance starting point.

[0267] In the implementation manner of the present application, since the present application takes into account information such as the vehicle's lateral position, speed, and acceleration when planning the target obstacle avoidance trajectory, the target duration is determined by obtaining the lateral motion parameters and the vehicle speed at the starting point of avoidance, thereby improving the accuracy of the target duration.

[0268] In some embodiments, the target obstacle avoidance trajectory includes target trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; step S105 includes step S151 and step S152, and the method further includes step S106, wherein:

[0269] Step S151, determining a reference trajectory point at the next sampling time in the baseline reference trajectory at the current sampling time.

[0270] Here, at the current sampling moment, the reference trajectory point at the next sampling moment may be determined through the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment.

[0271] In some embodiments, the angle change of the vehicle between the current sampling moment and the next sampling moment can be determined based on the yaw velocity of the vehicle at the current sampling moment; the lateral distance and longitudinal distance of the vehicle between the current sampling moment and the next sampling moment can be determined based on the angle change, the yaw velocity of the vehicle at the current sampling moment, and the driving speed of the vehicle at the current sampling moment; and the reference trajectory point at the next sampling moment can be determined based on the lateral distance, the longitudinal distance, the angle change, and the reference trajectory point at the current sampling moment.

[0272] In some embodiments, the heading angle at the next sampling moment can be determined based on the heading angle and angle change corresponding to the reference trajectory point at the current sampling moment, the lateral displacement at the next sampling moment can be determined based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment, the curvature information at the next sampling moment can be determined based on the curvature information corresponding to the target reference lane line, and then the reference trajectory point at the next sampling moment can be determined based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

[0273] Step S152, superimposing the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory to obtain the target trajectory point at the next sampling moment.

[0274] Here, the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory are superimposed. The method of superimposition processing may include but is not limited to: superimposing the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory by weighted average, superimposing the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory by feature fusion, etc. For example, the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory may correspond to different weight values, respectively, and the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory may be superimposed by the weight value. For another example, the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory contain multiple features. These features can be fused to generate a superimposed point containing all features, and then the superimposed point is used as the target trajectory point.

[0275] In some embodiments, the vehicle is equipped with a lateral control final trajectory calculation module, which is used to superimpose the reference trajectory points at the next sampling moment and the lateral trajectory points at the next sampling moment in the lateral offset trajectory to obtain the target trajectory points at the next sampling moment.

[0276] Step S106, based on the target trajectory point at the next sampling moment, the vehicle is controlled to travel at the next moment.

[0277] Here, the target trajectory point at the next sampling moment may be used as the target position that the vehicle needs to reach at the next sampling moment, so that the vehicle is controlled to travel at the next moment based on the target trajectory point at the next sampling moment.

[0278] In some embodiments, the vehicle is equipped with a lateral control execution module, and the lateral control execution module is used to control the vehicle's driving at the next moment based on the target trajectory point at the next sampling moment.

[0279] In an implementation manner of the present application, at the current sampling moment, the reference trajectory point of the next sampling moment in the baseline reference trajectory is determined, and the reference trajectory point of the next sampling moment and the lateral trajectory point of the next sampling moment in the lateral offset trajectory are superimposed to obtain the target trajectory point of the next sampling moment, so that the trajectory of the vehicle at the next sampling moment is planned in advance, and the driving of the vehicle is accurately controlled. At the same time, since the target trajectory point of the next sampling moment includes information on the lateral trajectory point and the reference trajectory point, the accuracy of the target trajectory point is improved.

[0280] In some embodiments, the method further comprises step S107 and step S108, wherein:

[0281] Step S107, determining the estimated collision time between the target obstacle and the vehicle.

[0282] Here, the estimated collision time may be any appropriate value, for example, 5 s, 2.1 s, etc.

[0283] In some implementations, the expected collision time between the target obstacle and the vehicle may be determined based on the distance between the target obstacle and the vehicle, the speed of the target obstacle, and the speed of the vehicle.

[0284] In some embodiments, the vehicle is equipped with an obstacle avoidance target selection module, which can determine the expected collision time between the target obstacle and the vehicle after screening out the target obstacle.

[0285] Step S108: When the estimated collision time meets the collision condition, an avoidance request is triggered.

[0286] Here, the avoidance request is used to activate the emergency steering function. The collision condition can be any suitable condition, for example, less than a time threshold, not greater than a time threshold, etc. The time threshold can be any suitable size, for example, 3s, 2.5s, etc.

[0287] In some implementations, the time threshold is related to the type of vehicle. The time thresholds corresponding to the same vehicle type are the same, and the time thresholds corresponding to different vehicle types may be the same or different.

[0288] In some embodiments, the vehicle is equipped with an emergency steering decision module, which is used to trigger an avoidance request when the estimated collision time meets the collision condition.

[0289] In the implementation mode of the present application, compared with continuously planning the avoidance trajectory, the avoidance request will only be triggered when the determined estimated collision time meets the collision conditions, so that the vehicle can trigger the emergency steering function more accurately, thereby improving the flexibility of the vehicle's trajectory planning.

[0290] The following describes the application of the vehicle trajectory planning method provided in an embodiment of the present application in an actual scenario, taking a vehicle equipped with a vehicle trajectory planning system as an example.

[0291] During the driving process, the vehicle may encounter sudden emergency situations (for example, obstacles appearing in front, pedestrians suddenly intruding, etc.), and emergency steering is required to avoid collision. The emergency steering function includes automatic emergency steering and driver-triggered emergency steering. Among them, automatic emergency steering mainly monitors the driving environment in front, side and rear of the vehicle in real time through on-board sensors, and automatically controls the steering of the vehicle when there is a risk of collision to avoid collision or mitigate the consequences of collision. Driver-triggered emergency steering is to avoid collision by turning the steering wheel manually. When there is a risk of collision in front of the vehicle, the driver triggers emergency steering to change the vehicle's driving trajectory. When the vehicle's driving trajectory triggered by the driver's emergency steering is not enough to avoid collision, the system emergency steering intervenes to avoid or mitigate the collision.

[0292] In the related technology, when the vehicle triggers an emergency turn, there is a link delay between the steering wheel angle request issued and the actual response of the steering wheel angle, so that the determined steering wheel angle value may be smaller than the actual steering wheel angle value, which may lead to the inability to avoid obstacles. In addition, in actual situations, the angle at which the driver manually turns the steering wheel may be greater than the angle requested when the system triggers the function, causing the steering wheel to turn back, posing certain safety hazards. At the same time, the lane line measured by the perception module can be used as the vehicle's driving trajectory. However, after the vehicle's emergency steering function is triggered, the vehicle turns a large angle in a short period of time (up to 400° / s or more). The vehicle trajectory detected and output only by the perception module cannot match the vehicle with rapidly changing posture, resulting in inaccurate delay compensation for lane line perception under non-steady state, and problems such as low trajectory accuracy and poor flexibility.

[0293] Figure 2 A schematic diagram of a vehicle trajectory planning system provided in an embodiment of the present application, such as Figure 2 As shown, the vehicle trajectory planning system 20 includes: a perception module 21, a vehicle motion state module 22, an emergency steering decision module 23, an obstacle avoidance target selection module 24, a trajectory initial state calculation module 25, a planning time calculation module 26, a reference reference trajectory calculation module 27, a curve planning module 28, a lateral control final trajectory calculation module 29, and a lateral control execution module 210, wherein:

[0294] The perception module 21 mainly includes a front-view camera, a periscopic camera, a front millimeter-wave radar, a corner radar, and a laser radar, and is used to output at least one coefficient detected by the camera to the reference trajectory calculation module 27, and output the targets detected by the camera and the radar to the obstacle avoidance target selection module 24 after fusion;

[0295] The vehicle motion state module 22 is used to provide the vehicle's current motion state information and the vehicle's current speed information, including but not limited to at least one of the following: vehicle speed, yaw rate, steering wheel angle, steering wheel speed;

[0296] The emergency steering decision module 23 is used to plan the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle according to the surrounding obstacle information of the target obstacle, and trigger the avoidance request when the estimated collision time meets the collision condition;

[0297] The obstacle avoidance target selection module 24 is used to select a target obstacle that the vehicle needs to avoid based on the fusion target around the vehicle output by the perception module 21, and determine the estimated collision time between the target obstacle and the vehicle;

[0298] The trajectory initial state calculation module 25 is used to determine the initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed, determine the initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point, determine the initial lateral speed of the vehicle based on the vehicle speed, and at the same time, compensate the steering wheel angle of the vehicle at the avoidance starting point based on the steering wheel speed and the response delay to obtain the target steering wheel angle;

[0299] A planning time calculation module 26, for calculating a target duration based on a lateral position, a lateral velocity, a lateral acceleration and a vehicle speed of the vehicle relative to a reference trajectory;

[0300] A reference trajectory calculation module 27, configured to determine a reference trajectory according to the vehicle speed, the vehicle yaw rate and the vehicle trajectory measured by the perception module;

[0301] The curve planning module 28 is used to plan the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process according to the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle;

[0302] A lateral control final trajectory calculation module 29 is used to perform superposition processing on the baseline reference trajectory and the lateral offset trajectory to obtain a target obstacle avoidance trajectory;

[0303] The lateral control execution module 210 is used to follow the target obstacle avoidance trajectory.

[0304] The vehicle trajectory planning system provided in the present application takes into account the influence of delay on the target obstacle avoidance trajectory when planning the vehicle trajectory, and compensates for the steering wheel angle through the trajectory initial state calculation module, thereby reducing the influence of delay on the lateral deviation trajectory of the vehicle, improving the accuracy of the lateral deviation trajectory, and thus improving the accuracy of the target obstacle avoidance trajectory.

[0305] The embodiment of the present application provides a vehicle trajectory planning method. After determining the target obstacle to be avoided by the vehicle in the driving direction, first, by determining the reference trajectory of the vehicle to avoid the target obstacle and the target time required for the vehicle to avoid the target obstacle, secondly, by compensating the steering wheel angle of the vehicle at the starting point of the avoidance through the response delay of the vehicle to the avoidance request, the target steering wheel angle is obtained. Further, by the target time, the speed information of the vehicle at the starting point of the avoidance, and the target steering wheel angle, the lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process is planned, so as to determine the target obstacle avoidance trajectory corresponding to the vehicle according to the reference reference trajectory and the lateral offset trajectory. On the one hand, the present application determines the lateral offset trajectory using the target steering wheel angle after delay compensation, reduces the influence of the delay on the lateral offset trajectory of the vehicle, and improves the accuracy of the lateral offset trajectory; on the other hand, compared with using a single trajectory as the target obstacle avoidance trajectory, the target obstacle avoidance trajectory is determined based on the reference reference trajectory and the lateral offset trajectory, so that the target obstacle avoidance trajectory contains more information, which improves the accuracy of the target obstacle avoidance trajectory and the flexibility of the vehicle's trajectory planning.

[0306] Figure 3 A schematic diagram of the implementation process of a vehicle trajectory planning method provided in an embodiment of the present application Figure 2 ,like Figure 3 As shown, the method includes steps S201 to S207, wherein:

[0307] Step S201, determining a target obstacle to be avoided by the vehicle in the driving direction through an obstacle avoidance target selection module;

[0308] Step S202, determining the estimated collision time between the target obstacle and the vehicle through an obstacle avoidance target selection module;

[0309] Step S203, when the estimated collision time meets the collision condition, triggering an avoidance request through the emergency steering decision module;

[0310] Step S204, determining a reference trajectory according to the vehicle speed, the vehicle yaw rate and the vehicle trajectory measured by the perception module through a reference trajectory calculation module;

[0311] Step S205, planning a lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process according to the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle through a curve planning module;

[0312] Step S206, superimposing the reference trajectory and the lateral offset trajectory through the lateral control final trajectory calculation module to obtain a target obstacle avoidance trajectory;

[0313] Step S207, following the target obstacle avoidance trajectory through the lateral control execution module.

[0314] Figure 4 A schematic diagram of a vehicle trajectory planning provided in an embodiment of the present application, such as Figure 4 As shown, a vehicle 41 is traveling between a right lane line 43 and a left lane line 44. The vehicle 41 detects a target obstacle 42 in front of it. The vehicle trajectory planning method provided by the present application plans a reference trajectory 45 and a target obstacle avoidance trajectory 48. The reference trajectory 45 is located between the left lane line 46 and the left lane line 44. At the same time, Figure 4 The driving trajectory 47 predicted by the steering wheel angle alone is shown. It can be seen that, compared with the driving trajectory 47 predicted by the steering wheel angle alone, the target obstacle avoidance trajectory 48 planned by the present application is more accurate, which improves the accuracy of the target obstacle avoidance trajectory, thereby improving driving safety. In some embodiments, when the automatic emergency steering is triggered and the driver triggers the emergency steering at the same time, the possibility of the steering wheel turning back is reduced.

[0315] Based on the above embodiments, the present application also provides a vehicle trajectory planning device, Figure 5 A schematic diagram of the structure of a vehicle trajectory planning device provided in an embodiment of the present application is shown in FIG. Figure 5 As shown, the vehicle trajectory planning device 500 includes a first determination unit 501, a second determination unit 502, a compensation unit 503, a planning unit 504 and a third determination unit 505, wherein:

[0316] The first determining unit 501 is used to determine a target obstacle to be avoided by the vehicle in the driving direction;

[0317] A second determining unit 502 is used to determine a reference trajectory for the vehicle to avoid a target obstacle, and to determine a target time required for the vehicle to avoid the target obstacle;

[0318] A compensation unit 503 is used to compensate the steering wheel angle of the vehicle at the avoidance starting point based on the response delay of the vehicle to the avoidance request to obtain a target steering wheel angle;

[0319] A planning unit 504, configured to plan a lateral offset trajectory of the vehicle relative to a reference trajectory during the avoidance process based on a target duration, speed information of the vehicle at the avoidance start point, and a target steering wheel angle;

[0320] The third determining unit 505 is used to determine a target obstacle avoidance trajectory corresponding to the vehicle based on the baseline reference trajectory and the lateral offset trajectory.

[0321] In some embodiments, the compensation unit 503 is further used to obtain the steering wheel speed of the vehicle at the avoidance starting point; based on the steering wheel speed and the response delay, the steering wheel angle of the vehicle at the avoidance starting point is compensated to obtain a target steering wheel angle.

[0322] In some embodiments, the second determination unit 502 is further used to plan the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle based on the surrounding obstacle information of the target obstacle; and to plan a reference trajectory for the vehicle to avoid the target obstacle based on the avoidance direction, target lateral displacement and the motion state information of the vehicle.

[0323] In some embodiments, the baseline reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; the second determination unit 502 is further used to determine the reference trajectory points at the initial sampling moment based on the avoidance direction and the target lateral displacement; based on the reference trajectory points at the current sampling moment and the motion state information of the vehicle at the current sampling moment, determine the reference trajectory points at the next sampling moment.

[0324] In some embodiments, the second determination unit 502 is further used to determine the target reference lane line from the left lane line and the right lane line perceived by the vehicle based on the avoidance direction; and determine the reference trajectory point at the initial moment based on the target reference lane line and the target lateral displacement.

[0325] In some embodiments, the motion state information includes the yaw angular velocity and the vehicle speed; the second determination unit 502 is further used to determine the angle change of the vehicle between the current sampling moment and the next sampling moment based on the yaw angular velocity of the vehicle at the current sampling moment; determine the lateral distance and longitudinal distance of the vehicle between the current sampling moment and the next sampling moment based on the angle change, the yaw angular velocity of the vehicle at the current sampling moment and the driving speed of the vehicle at the current sampling moment; determine the reference trajectory point at the next sampling moment based on the lateral distance, the longitudinal distance, the angle change and the reference trajectory point at the current sampling moment.

[0326] In some embodiments, the second determination unit 502 is further used to determine the heading angle at the next sampling moment based on the heading angle and angle change corresponding to the reference trajectory point at the current sampling moment; determine the lateral displacement at the next sampling moment based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment; determine the curvature information at the next sampling moment based on the curvature information corresponding to the target reference lane line; determine the reference trajectory point at the next sampling moment based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

[0327] In some embodiments, the speed information of the vehicle at the avoidance starting point includes the vehicle speed; the planning unit 504 is further used to determine the initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed; determine the initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point; determine the initial lateral speed of the vehicle based on the vehicle speed; and plan the lateral offset trajectory based on the target duration, the initial lateral acceleration, the initial lateral displacement, and the initial lateral speed.

[0328] In some embodiments, the planning unit 504 is further used to determine a motion parameter matrix corresponding to an initial lateral acceleration, an initial lateral displacement, and an initial lateral velocity; determine a time parameter matrix corresponding to a target duration; determine a target offset parameter based on the time parameter matrix and the motion parameter matrix; and plan a lateral offset trajectory based on the target offset parameter, the target lateral displacement, and the vehicle speed.

[0329] In some embodiments, the second determination unit 502 is further used to obtain lateral motion parameters of the vehicle at the avoidance starting point relative to the reference trajectory; wherein the lateral motion parameters include at least one of the following: lateral position, lateral speed, lateral acceleration; based on the lateral motion parameters and the vehicle speed at the avoidance starting point, the target duration is determined.

[0330] In some embodiments, the target obstacle avoidance trajectory includes target trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; the third determination unit 505 is also used to determine the reference trajectory point at the next sampling moment in the baseline reference trajectory at the current sampling moment; the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory are superimposed to obtain the target trajectory point at the next sampling moment; the vehicle trajectory planning device 500 also includes a control unit, which is used to control the vehicle's driving at the next moment based on the target trajectory point at the next sampling moment.

[0331] In some embodiments, the vehicle trajectory planning device 500 further includes a trigger unit for determining an estimated collision time between the target obstacle and the vehicle; and triggering an avoidance request when the estimated collision time satisfies a collision condition.

[0332] The description of the above device embodiment is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of the present application, please refer to the description of the method embodiment of the present application for understanding.

[0333] It should be noted that in the embodiment of the present application, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0334] The present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the above method is implemented when the processor executes the computer program.

[0335] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. The computer-readable storage medium can be transient or non-transient.

[0336] The present application also provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements some or all of the steps in the above method. The computer program product can be implemented specifically by hardware, software, or a combination thereof. The computer program product can be implemented specifically by hardware, software, or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium, and in another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0337] It should be noted that Figure 6 A hardware entity diagram of an electronic device provided in an embodiment of the present application, such as Figure 6As shown, the hardware entity of the electronic device 600 includes: a processor 601, a communication interface 602 and a memory 603, wherein:

[0338] The processor 601 generally controls the overall operation of the electronic device 600 .

[0339] The communication interface 602 enables the electronic device 600 to communicate with other terminals or servers through a network.

[0340] The memory 603 is configured to store instructions and applications executable by the processor 601, and can also cache data to be processed or processed by the processor 601 and each module in the electronic device 600 (for example, image data, audio data, voice communication data, and video communication data), which can be implemented by flash memory (FLASH) or RAM. Data can be transmitted between the processor 601, the communication interface 602, and the memory 603 through the bus 604.

[0341] Here, the electronic device may be a vehicle computer in a vehicle.

[0342] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0343] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial numbers of the above-mentioned steps / processes does not mean the order of execution, and the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0344] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0345] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the above-mentioned units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0346] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0347] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0348] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, read-only memories, magnetic disks or optical disks.

[0349] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0350] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A vehicle trajectory planning method, characterized in that: The method comprises: Determining a target obstacle to be avoided by the vehicle in the direction of travel; Determining a reference trajectory for the vehicle to avoid the target obstacle, and determining a target duration required for the vehicle to avoid the target obstacle; Based on the response delay of the vehicle to the avoidance request, compensating the steering wheel angle of the vehicle at the avoidance starting point to obtain a target steering wheel angle; Planning a lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process based on the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle; A target obstacle avoidance trajectory corresponding to the vehicle is determined based on the baseline reference trajectory and the lateral offset trajectory.

2. The trajectory planning method according to claim 1, characterized in that: The compensating the steering wheel angle of the vehicle at the avoidance starting point based on the response delay of the vehicle to the avoidance request to obtain a target steering wheel angle includes: Obtaining a steering wheel speed of the vehicle at the avoidance starting point; Based on the steering wheel speed and the response delay, a compensation process is performed on the steering wheel angle of the vehicle at the avoidance starting point to obtain a target steering wheel angle.

3. The trajectory planning method according to claim 1, characterized in that: The determining of a reference trajectory for the vehicle to avoid the target obstacle includes: Based on the surrounding obstacle information of the target obstacle, planning the avoidance direction and target lateral displacement of the vehicle to avoid the target obstacle; A reference trajectory for the vehicle to avoid the target obstacle is planned based on the avoidance direction, the target lateral displacement, and the motion state information of the vehicle.

4. The trajectory planning method according to claim 3, characterized in that: The benchmark reference trajectory includes reference trajectory points at multiple sampling moments in the process of the vehicle avoiding the target obstacle; The planning of a reference trajectory for the vehicle to avoid the target obstacle based on the avoidance direction, the target lateral displacement, and the motion state information of the vehicle includes: Determining a reference trajectory point at an initial sampling time based on the avoidance direction and the target lateral displacement; Based on the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment, the reference trajectory point at the next sampling moment is determined.

5. The trajectory planning method according to claim 4, characterized in that: The determining of the reference trajectory point at the initial moment based on the avoidance direction and the target lateral displacement includes: Based on the avoidance direction, determining a target reference lane line from a left lane line and a right lane line perceived by the vehicle; Based on the target reference lane line and the target lateral displacement, a reference trajectory point at the initial moment is determined.

6. The trajectory planning method according to claim 4, characterized in that: The motion state information includes yaw rate and vehicle speed; The determining of the reference trajectory point at the next sampling moment based on the reference trajectory point at the current sampling moment and the motion state information of the vehicle at the current sampling moment comprises: Determining an angle change of the vehicle between the current sampling moment and the next sampling moment based on the yaw angular velocity of the vehicle at the current sampling moment; Determine a lateral distance and a longitudinal distance of the vehicle between the current sampling moment and the next sampling moment based on the angle change, the yaw rate of the vehicle at the current sampling moment, and the driving speed of the vehicle at the current sampling moment; Based on the lateral distance, the longitudinal distance, the angle change, and the reference trajectory point at the current sampling moment, a reference trajectory point at the next sampling moment is determined.

7. The trajectory planning method according to claim 6, characterized in that: The determining of the reference trajectory point at the next sampling moment based on the lateral distance, the longitudinal distance, the angle change, and the reference trajectory point at the current sampling moment comprises: Determine the heading angle at the next sampling moment based on the heading angle corresponding to the reference trajectory point at the current sampling moment and the angle change; Determine the lateral displacement at the next sampling moment based on the lateral distance, the longitudinal distance, the heading angle corresponding to the reference trajectory point at the current sampling moment, the lateral displacement corresponding to the reference trajectory point at the current sampling moment, and the curvature information corresponding to the reference trajectory point at the current sampling moment; Determining curvature information at a next sampling time based on the curvature information corresponding to the target reference lane line; A reference trajectory point at the next sampling moment is determined based on the heading angle at the next sampling moment, the lateral displacement at the next sampling moment, and the curvature information at the next sampling moment.

8. The trajectory planning method according to claim 1, characterized in that: The speed information of the vehicle at the avoidance starting point includes the vehicle speed; The planning of a lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process based on the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle includes: determining an initial lateral acceleration of the vehicle at the avoidance starting point based on the target steering wheel angle and the vehicle speed; Determining an initial lateral displacement of the vehicle based on the position information of the vehicle at the avoidance starting point; determining an initial lateral velocity of the vehicle based on the vehicle velocity; The lateral offset trajectory is planned based on the target duration, the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity.

9. The trajectory planning method according to claim 8, characterized in that: The planning of the lateral offset trajectory based on the target duration, the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity includes: Determine a motion parameter matrix corresponding to the initial lateral acceleration, the initial lateral displacement, and the initial lateral velocity; Determine a time parameter matrix corresponding to the target duration; Determining a target offset parameter based on the time parameter matrix and the motion parameter matrix; The lateral offset trajectory is planned based on the target offset parameter, the target lateral displacement and the vehicle speed.

10. The trajectory planning method according to claim 1, characterized in that: The determining of a target time required for the vehicle to avoid the target obstacle includes: Acquire the lateral motion parameters of the vehicle at the avoidance starting point relative to the reference trajectory; wherein the lateral motion parameters include at least one of the following: lateral position, lateral velocity, lateral acceleration; The target duration is determined based on the lateral motion parameter and a vehicle speed of the vehicle at the avoidance starting point.

11. The trajectory planning method according to any one of claims 1 to 10, characterized in that: The target obstacle avoidance trajectory includes target trajectory points at multiple sampling moments during the process of the vehicle avoiding the target obstacle; The determining, based on the reference trajectory and the lateral offset trajectory, a target obstacle avoidance trajectory corresponding to the vehicle comprises: Determine, at the current sampling moment, a reference trajectory point at the next sampling moment in the baseline reference trajectory; Superimposing the reference trajectory point at the next sampling moment and the lateral trajectory point at the next sampling moment in the lateral offset trajectory to obtain the target trajectory point at the next sampling moment; The method further comprises: Based on the target trajectory point at the next sampling moment, the vehicle is controlled to travel at the next moment.

12. The trajectory planning method according to any one of claims 1 to 10, characterized in that: The method further comprises: determining an estimated collision time between the target obstacle and the vehicle; When the estimated collision time satisfies the collision condition, an avoidance request is triggered.

13. A vehicle trajectory planning device, characterized in that: The device comprises: A first determining unit, configured to determine a target obstacle to be avoided by the vehicle in a driving direction; A second determining unit is used to determine a reference trajectory for the vehicle to avoid the target obstacle, and to determine a target time required for the vehicle to avoid the target obstacle; a compensation unit, configured to compensate a steering wheel angle of the vehicle at an avoidance starting point based on a response delay of the vehicle to the avoidance request, so as to obtain a target steering wheel angle; a planning unit, configured to plan a lateral offset trajectory of the vehicle relative to the reference trajectory during the avoidance process based on the target duration, the speed information of the vehicle at the avoidance starting point, and the target steering wheel angle; The third determining unit is used to determine a target obstacle avoidance trajectory corresponding to the vehicle based on the baseline reference trajectory and the lateral offset trajectory.

14. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program executable on the processor, and the processor implements the method according to any one of claims 1 to 12 when executing the computer program.

15. A vehicle, characterized in that: The vehicle includes the electronic device of claim 14.

16. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 12 are implemented.

17. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps in the method according to any one of claims 1 to 12 are implemented.

Images