Path determination method, device, electronic device, and storage medium

Abstract

The present application provides a path determination method, device, electronic device, and storage medium, the method comprising: obtaining attribute information of an obstacle, and obtaining current driving information of a vehicle; determining a target point based on the current driving information and attribute information, and determining an endpoint based on the target point; determining a reference path trajectory of the vehicle based on the vehicle's starting point, endpoint, and target point; determining whether an optimal solution exists in the vehicle dynamics model based on the current driving information; if an optimal solution exists in the vehicle dynamics model, determining the target path trajectory of the vehicle based on the optimal solution; or if the vehicle dynamics model does not have an optimal solution, determining the reference path trajectory as the target path trajectory. The present application can improve the accuracy of the target path trajectory determined based on the vehicle dynamics model, and can avoid obstacles safely even when the vehicle dynamics does not have an optimal solution, thereby improving the driving safety of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of automotive electronics technology, and more specifically, to a method, device, electronic device, and storage medium for determining a path. Background Art

[0002] With the continuous advancement of technology, more and more people own their own cars, leading to increasingly prominent problems such as urban congestion, energy consumption, and traffic accidents. Autonomous driving has become a key feature of automobiles. Path planning, as one of the core technologies for autonomous driving, not only helps reduce the burden on drivers but also effectively improves commuting efficiency and reduces energy consumption. Currently, common trajectory planning algorithms include random search methods based on trajectory tracking and trajectory planning methods based on specific functions. However, these algorithms fail to incorporate the actual operating conditions of the vehicle, resulting in low path accuracy and, in turn, the inability of the vehicle to safely avoid obstacles. Therefore, improving path accuracy to enable safe avoidance has become an urgent issue. Summary of the Invention

[0003] In view of this, embodiments of the present application propose a path determination method, device, electronic device, and storage medium to improve the above-mentioned problem.

[0004] According to one aspect of an embodiment of the present application, a path determination method is provided, the method comprising: obtaining attribute information of an obstacle and current driving information of a vehicle; determining a target point based on the current driving information and the attribute information, and determining an endpoint based on the target point; determining a reference path trajectory of the vehicle based on the starting point, the endpoint, and the target point of the vehicle; determining whether a vehicle dynamics model has an optimal solution based on the current driving information; if the vehicle dynamics model has an optimal solution, determining the target path trajectory of the vehicle based on the optimal solution; or if the vehicle dynamics model does not have an optimal solution, determining the reference path trajectory as the target path trajectory.

[0005] According to one aspect of an embodiment of the present application, a path determination device is provided, the device comprising: an acquisition module for acquiring attribute information of an obstacle and current driving information of a vehicle; a first determination module for determining a target point based on the current driving information and the attribute information and determining an endpoint based on the target point; a reference path trajectory determination module for determining a reference path trajectory of the vehicle based on the starting point, the endpoint and the target point of the vehicle; a second determination module for determining whether a vehicle dynamics model has an optimal solution based on the current driving information; a first target path trajectory determination module for determining a target path trajectory of the vehicle based on the optimal solution if the vehicle dynamics model has an optimal solution; or a second target path trajectory determination module for determining the reference path trajectory as the target path trajectory if the vehicle dynamics model does not have an optimal solution.

[0006] According to one aspect of an embodiment of the present application, an electronic device is provided, including: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the path determination method described above is implemented.

[0007] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the path determination method described above is implemented.

[0008] In the solution of the present application, the target point and endpoint are determined based on the vehicle's current driving information and the attribute information of the obstacle, and then the reference path trajectory is determined based on the vehicle's starting point, target point, and endpoint; and the vehicle dynamics model is optimized and solved based on the vehicle's current driving information. When the vehicle dynamics model has an optimal solution, the target path trajectory is determined based on the optimal solution, so that the vehicle can safely avoid obstacles based on the target path trajectory determined by the optimal solution; when the vehicle dynamics model does not have an optimal solution, the reference path trajectory is used as the target path trajectory to avoid obstacles even when the vehicle dynamics model does not have an optimal solution. The present application can improve the accuracy of the target path trajectory determined based on the vehicle dynamics model, and can avoid obstacles even when the vehicle dynamics does not have an optimal solution, thereby improving the driving safety of the vehicle.

[0009] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0011] Figure 1 This is a schematic diagram of an application scenario applicable to the present application according to an embodiment of the present application.

[0012] Figure 2 It is a flowchart of a method for determining a path according to an embodiment of the present application.

[0013] Figure 3 It is a flowchart illustrating the specific steps of step 220 according to an embodiment of the present application.

[0014] Figure 4 is based on Figure 3 FIG. 1 is a schematic diagram showing the distances in the specific steps of step 220 in an embodiment.

[0015] Figure 5 It is a flowchart illustrating the specific steps of step 250 according to an embodiment of the present application.

[0016] Figure 6 It is a flowchart illustrating the specific steps of step 253 according to an embodiment of the present application.

[0017] Figure 7 It is a flowchart of specific steps after step 253 according to an embodiment of the present application.

[0018] Figure 8 It is a flowchart illustrating the specific steps of step 255 according to an embodiment of the present application.

[0019] Figure 9 It is a flowchart illustrating the specific steps of step 2552 according to an embodiment of the present application.

[0020] Figure 10 It is a flowchart of the specific steps before step 2552 according to an embodiment of the present application.

[0021] Figure 11 It is a flowchart of the specific steps before step 2552 according to another embodiment of the present application.

[0022] Figure 12 It is a flowchart of the specific steps before step 220 according to an embodiment of the present application.

[0023] Figure 13 It is a block diagram of a path determination device according to an embodiment of the present application.

[0024] Figure 14 It is a hardware structure diagram of an electronic device according to an embodiment of the present application.

[0025] The above-mentioned drawings have shown clear embodiments of the present invention, which will be described in more detail later. These drawings and textual descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention to computer technicians in this field through specific embodiments. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0029] Figure 1 This is an application scenario diagram applicable to this application according to an embodiment of this application. Figure 1 As shown, a vehicle 110 , an obstacle 120 , a target point 130 , an end point 140 , a starting point 150 and a reference path trajectory 160 are included.

[0030] As one approach, a determination is made as to whether the vehicle 110 will collide with the obstacle 120 based on the current driving information of the vehicle 110 and the attribute information of the obstacle 120. When it is determined that the vehicle 110 will collide with the obstacle 120, a target point 130 and an endpoint 140 are determined based on the current driving information of the vehicle 110 and the attribute information of the obstacle 120. Then, the center of the front axle of the vehicle 110 is determined as the starting point 150 of the vehicle. Based on the target point 130, the endpoint 140, and the starting point 150, a reference path trajectory 160 is determined. Then, based on the current driving information of the vehicle 110 and the vehicle dynamics model, a determination is made as to whether the vehicle dynamics model of the vehicle 110 has an optimal solution. If an optimal solution exists, a target path trajectory is determined based on the optimal solution and the vehicle dynamics model of the vehicle 110. If no optimal solution exists, the reference path trajectory 160 is used as the target driving trajectory of the vehicle 110, and the vehicle 110 performs avoidance driving according to the target driving trajectory to bypass the obstacle 120.

[0031] See also Figure 2 , Figure 2 The method for determining a path provided by an embodiment of the present application is shown. In a specific embodiment, the method for determining a path can be applied to Figure 13 The path determination device 400 and the electronic device 500 equipped with the path determination device 400 are shown. Figure 14 The specific process of this embodiment will be described below. Of course, it is understandable that the method can be executed by electronic devices with computing and processing capabilities, such as desktop computers, laptops, vehicle-mounted terminals, vehicle-mounted large screens and other terminal devices. The method can also be interactively executed by a processing system including a server and a terminal, or by a domain controller related to automatic avoidance in the vehicle. Figure 2 The process shown in FIG. 1 is described in detail, and the method for determining the path may specifically include the following steps:

[0032] Step 210: Obtain attribute information of the obstacle and current driving information of the vehicle.

[0033] As a method, the attribute information of the obstacle may include the location information of the obstacle, the speed of the obstacle, the width of the obstacle, etc., which are not specifically limited here. Optionally, the obstacle can be a stationary object, such as a roadblock, a road bollard, a stationary vehicle (such as a vehicle temporarily parked on the roadside), etc. The obstacle can also be a moving object or a moving living thing, such as other vehicles traveling in front of or behind the vehicle, a moving pedestrian or animal, etc. Optionally, if the obstacle is movable, it is necessary to obtain the movement speed of the obstacle.

[0034] As one approach, the vehicle may include a distance detection device and a visual sensing device. The distance detection device may be a millimeter-wave radar detector, a laser ranging sensor, or the like, and the visual sensing device may be a camera sensor or other visual sensing device, without limitation. Optionally, the visual sensing device and the distance detection device may be used to determine the attribute information of an obstacle, and then the attribute information of the obstacle may be obtained by acquiring data from the visual sensing device and the distance detection device.

[0035] As a way, the current driving information of the vehicle may include the current speed of the vehicle, the current position of the vehicle, the current heading angle of the vehicle, the current torque of the steering wheel of the vehicle, etc., which are not specifically limited here. Optionally, the current driving information of the vehicle may be detected by multiple sensors in the vehicle and then obtained by acquiring data from multiple sensors, or may be detected by other devices in the vehicle. Optionally, the current driving information of the vehicle may be data detected by the Global Navigation Satellite System (GNSS) or the Inertial Measurement Unit (IMU) in the vehicle.

[0036] Step 220: Determine a target point based on the current driving information and the attribute information, and determine an endpoint based on the target point.

[0037] The target point is the point where the vehicle can safely avoid an obstacle, determined based on the obstacle's attributes and the vehicle's current driving information, to avoid collision or scraping. The target point can be determined based on the vehicle's steering direction, vehicle width, and obstacle location. For example, if the vehicle's steering wheel is turned right, the leftmost end of the vehicle is used as the reference for avoidance, meaning that the leftmost end of the vehicle can avoid contact with the obstacle. The reference point can be the point where the leftmost end of the vehicle is farthest from the obstacle, and the target point can be the point where the reference point avoids contact with the obstacle during the avoidance process.

[0038] Alternatively, a distance threshold can be pre-set, and the target point can be determined based on the obstacle's location information, the vehicle's steering direction, and the distance threshold. For example, when the vehicle's steering wheel is turning left, the point closest to the obstacle on the vehicle's left side is the reference point, and the point whose distance from the reference point exceeds the distance threshold is the target point. The distance threshold can be set based on actual needs and is not specifically defined here.

[0039] As a method, the endpoint refers to the destination point to which the vehicle moves after avoiding an obstacle. Alternatively, the endpoint can be a point obtained by translating the target point. Optionally, after the target point and endpoint are determined, the vehicle can move based on the location information of the target point and the location information of the endpoint.

[0040] In some embodiments, the attribute information of the obstacle includes the width of the obstacle and the position information of the obstacle, such as Figure 3 As shown, step 220 includes:

[0041] Step 221 : determining a first distance based on the width information of the vehicle and the front overhang distance of the vehicle, wherein the first distance is the distance from the center of the front axle of the vehicle to the vertex of the vehicle.

[0042] The front overhang distance refers to the distance from the center of the vehicle's front wheels to the front end of the vehicle. Optionally, the vehicle can be a front-wheel steering passenger car. When the front wheels can bypass obstacles, the vehicle body can also bypass the obstacles without colliding with the obstacles.

[0043] As a way to ensure that the front wheels of the vehicle can avoid obstacles, the center of the front axle of the vehicle can be used as the center of the circle, and the distance from the center of the front axle of the vehicle to the leftmost end (or rightmost end) of the front end of the vehicle can be used as the radius, and the radius can be used as the first distance. Optionally, the first distance is calculated based on the width information of the vehicle and the front overhang distance of the vehicle. If the width of the vehicle is W ego , the front overhang distance is d f , the first distance is R, according to the formula: Calculate the first distance. Figure 4 As shown, in Figure 4 The distance between the center of the front wheel 150 and the front end 112 of the vehicle 110 is the front overhang distance d f The first distance may be the length of the distance between the front wheel center 150 of the vehicle 110 and the point 113 .

[0044] As another method, in order to ensure that the vehicle can safely bypass the obstacle and does not come into contact with the obstacle, a preset distance is added to determine the first distance, that is, the first distance R is: Optionally, the preset distance may be 0.5 m or other values, which may be set according to actual needs and is not specifically limited here.

[0045] Step 222: Determine the fourth distance based on the first distance, the width of the obstacle, the second distance, and the third distance, wherein the second distance is the distance between the center of mass of the vehicle and the obstacle, and the third distance is the distance between the center of mass of the vehicle and the center of the front axle of the vehicle.

[0046] Optionally, the second distance may be the longitudinal distance between the center of mass of the vehicle and the obstacle, wherein the longitudinal distance may be the shortest longitudinal distance. Optionally, the third distance may be the longitudinal distance between the center of mass of the vehicle and the center of the front axle of the vehicle. Figure 4 As shown, the second distance is the distance between the center of mass 111 of the vehicle and the front end 121 of the obstacle, the third distance is the distance between the center of mass 111 of the vehicle 110 and the front axle center 112 of the vehicle 110, and the fourth distance is the distance between the point 121 of the obstacle 120 closest to the reference trajectory 160 and the target point 130.

[0047] As a method, the fourth distance can be calculated based on the first distance, the width of the obstacle, the second distance and the third distance. If the first distance is R and the width of the obstacle is W obs ; The second distance is d x ; The third distance is l f , the fourth distance is d, according to the formula: The fourth distance is calculated.

[0048] Step 223: Determine the target point based on the current driving information, the position information of the obstacle, and the fourth distance.

[0049] As a method, the current driving information of the vehicle may include the avoidance direction of the vehicle (i.e., the steering direction of the vehicle's steering wheel), and a reference point is determined based on the avoidance direction of the vehicle. The reference point is the corner point of the obstacle in the avoidance direction of the vehicle. According to the position information of the reference point, the point offset from the reference point by a fourth distance is used as the target point.

[0050] Step 224 : determining the endpoint according to the target point, the length of the vehicle, and the width of the vehicle.

[0051] As a way, after determining the target point, the target point is translated according to the position information of the target point to determine the end point. Optionally, in order to ensure that the vehicle can be at the end point without colliding with the obstacle, the translation distance of the target point can be determined according to the length and width of the vehicle. If the length of the vehicle is L ego ; The width of the vehicle is W ego , then you can first use L ego The target point is translated horizontally by the horizontal translation distance, and then For the longitudinal translation distance, the target point is longitudinally translated to determine the endpoint. Optionally, the target point can be longitudinally translated first and then horizontally translated, which is not specifically limited here.

[0052] In some embodiments, before step 220, it may also be determined whether the vehicle currently needs to perform an evasive turn based on the obstacle's attribute information and the vehicle's current driving information. Optionally, evasive turn, unlike lane changing, can be performed without evading to an adjacent lane or by occupying only a small space in the adjacent lane. Avoiding evasion by not evading to an adjacent lane or by occupying only a small space in the adjacent lane can prevent the vehicle from moving a large distance laterally in a short period of time, thereby increasing the vehicle's lateral acceleration. This can cause significant interference with other vehicles in adjacent lanes during lateral movement, as well as significant impact force on the driver during lateral movement, leading to accidents.

[0053] As one approach, whether a swerve is required can be determined based on the current steering wheel direction and obstacle width information in the vehicle's current driving information. For example, if the vehicle's current steering wheel direction is left, and it is determined whether the distance between the left side of the obstacle and the lane line is greater than a width threshold, when the distance between the left side of the obstacle and the lane line is greater than the width threshold, it can be determined that the vehicle currently needs to swerve, and the left side is determined to be the swerve direction; if the distance between the left side of the obstacle and the lane line is not greater than the width threshold, it is determined that a swerve is not possible. When it is determined that a swerve cannot be made on the left, it can be determined whether the distance between the right side of the obstacle and the lane line is greater than the width threshold to determine whether a swerve can be made on the right. When it is determined that a swerve is not possible on either side, the driver can be prompted to make an emergency stop or to change lanes.

[0054] In other embodiments, before step 220, it can be determined whether the vehicle is in automatic driving or the assisted driving function is turned on. When the vehicle is in automatic driving or the assisted driving function is turned on, it is determined whether the vehicle currently needs to steer to avoid the situation.

[0055] Please continue reading Figure 2 , step 230, determining a reference path trajectory of the vehicle based on the starting point, the endpoint and the target point of the vehicle.

[0056] As a method, a reference path trajectory can be determined using a cubic spline curve based on the point where the center of mass of the vehicle is located, the point where the center of the front axle of the vehicle is located, the endpoint, and the target point. The cubic spline curve is a combined curve that can be obtained by interpolating between two adjacent value points using a cubic function. If n segments of cubic curves are connected so that the slope and curvature of two adjacent curves at the connection point (called a node) are equal, a curve composed of n segments of cubic functions is obtained, that is, a cubic spline curve, that is, the reference path trajectory in this application. Optionally, the slopes at the starting point of the vehicle (the point where the center of mass of the vehicle is located) and at the endpoint are both zero. As Figure 4As shown, a reference trajectory 160 is determined using a cubic spline curve according to a starting point 111 of the vehicle 110 , a front axle center 150 of the vehicle 110 , a target point 130 , and an end point 140 .

[0057] Alternatively, the starting point can be the center of mass of the vehicle or the center of the front axle. The starting point can be selected based on actual needs and is not specifically limited here. As one approach, the center of the front axle of the vehicle is used as the starting point, and the starting point, target point, and endpoint are connected using a smooth curve to obtain a reference path trajectory.

[0058] Step 240 : Determine whether there is an optimal solution for the vehicle dynamics model based on the current driving information.

[0059] Vehicle dynamics models can be used to analyze the ride comfort and handling stability of a vehicle. That is, the vehicle's motion state during driving can be determined through the vehicle dynamics model. For a vehicle, the study of vehicle dynamics primarily focuses on the forces acting on the vehicle's tires and related components. For example, longitudinal speed control is achieved by controlling tire speed, and lateral heading control is achieved by controlling tire angle. In autonomous driving or assisted driving functions, the vehicle's control parameters (such as heading angle, yaw rate, wheel angle, etc.) can be determined based on the vehicle dynamics model, allowing the vehicle to perform autonomous driving or assisted driving based on these control parameters.

[0060] As a method, since the vehicle needs to control lateral movement when avoiding obstacles, the vehicle dynamics model can be determined based on the force analysis and lateral dynamics of the vehicle in the lateral direction. In this embodiment, the center of the vehicle is used as the center of mass of the vehicle, and the vehicle is analyzed for translation and rotation respectively to determine the vehicle dynamics model. Optionally, the vehicle dynamics model of the vehicle can be:

[0061]

[0062] Where m is the mass of the vehicle; v is the current speed of the vehicle; β is the sideslip angle of the vehicle's center of mass; is the yaw angle of the vehicle; k f is the vehicle's front wheel cornering stiffness; k r is the rear wheel cornering stiffness of the vehicle; l f is the distance from the center of mass of the vehicle to the center of the front axle; l r is the distance from the center of mass of the vehicle to the center of the rear axle; ω r is the yaw rate of the vehicle; δ is the front wheel turning angle of the vehicle; I z is the central moment of inertia of the vehicle; x is the longitudinal displacement of the vehicle; y is the lateral displacement of the vehicle.

[0063] Optionally, in the above vehicle dynamics model, β, ω r , x, y are the current driving information of the vehicle, δ and is the control parameter of the vehicle, and determines whether there is an optimal solution for the vehicle dynamics model, that is, whether there are control parameters δ and This enables the vehicle to perform safe avoidance based on the above vehicle dynamics model.

[0064] Step 250: If an optimal solution exists for the vehicle dynamics model, a target path trajectory of the vehicle is determined according to the optimal solution.

[0065] As a way, when it is determined that the vehicle dynamics model has an optimal solution, that is, there are control parameters δ and This enables the vehicle to perform safe avoidance based on the control parameters.

[0066] As a method, the target path trajectory is a path trajectory composed of multiple predicted path points determined based on the vehicle dynamics model and the optimal solution.

[0067] Step 260: If the vehicle dynamics model does not have an optimal solution, the reference path trajectory is determined as the target path trajectory.

[0068] As a way to avoid the vehicle's path changing during the avoidance process due to the absence of an optimal solution in the vehicle dynamics model, which may lead to accidents during the vehicle's avoidance driving process, the reference path trajectory can be used as the target path trajectory to ensure that the vehicle can perform safe avoidance.

[0069] In an embodiment of the present application, a target point and an endpoint are determined based on the vehicle's current driving information and the attribute information of the obstacle, and then a reference path trajectory is determined based on the vehicle's starting point, target point, and endpoint; and the vehicle dynamics model is optimized and solved based on the vehicle's current driving information. When the vehicle dynamics model has an optimal solution, the target path trajectory is determined based on the optimal solution, so that the vehicle can safely avoid obstacles based on the target path trajectory determined by the optimal solution; when the vehicle dynamics model does not have an optimal solution, the reference path trajectory is used as the target path trajectory to avoid obstacles even when the vehicle dynamics model does not have an optimal solution. The present application can improve the accuracy of the target path trajectory determined based on the vehicle dynamics model, and can avoid obstacles even when the vehicle dynamics does not have an optimal solution, thereby improving the driving safety of the vehicle.

[0070] In some embodiments, as Figure 5 As shown, step 250 includes:

[0071] Step 251 : determining a state equation of the vehicle dynamics model based on the current driving information, and discretizing the state equation to obtain a discrete state equation.

[0072] As a method, the current driving information of the vehicle may include the current speed of the vehicle, the front wheel turning angle of the vehicle, the sideslip angle of the center of mass of the vehicle, the lateral displacement of the vehicle, and the longitudinal displacement of the vehicle. The vehicle state matrix and the vehicle control input (control parameter) matrix may be determined first. Based on the vehicle dynamics model, the vehicle state matrix, and the vehicle control input matrix in step 250, the vehicle dynamics model may be rewritten as a state equation. Optionally, the state equation may be: Where X is the vehicle state matrix, U is the vehicle control input matrix, and optionally, the vehicle state matrix can be X = [β ω r xy] T ; The vehicle's control input matrix can be: According to the vehicle's state matrix, the vehicle's control input matrix, the vehicle dynamics model, and the vehicle's current driving information, the A in the vehicle's state equation can be determined as follows:

[0073]

[0074] B is:

[0075]

[0076] C is: C = [0 0 v 0] T .

[0077] As a method, since the above state equation is a continuous quantity, and the vehicle controller uses discrete numbers for control, it is necessary to discretize the state equation. Optionally, discretization can be performed based on the sampling time, where the sampling time can be a preset period for obtaining the current driving information of the vehicle. If the sampling time is T, the discrete state equation obtained after discretization of the state equation is: X (k+1) =A d X k +B d U k +C d , where A d =(I-AT) -1 ; B d =(I-AT) -1 BT;C d =(I-AT) -1 CT, I is a unit matrix, which is optional. T=100ms, or other values. The sampling time can be set according to actual needs and is not specifically limited here.

[0078] Step 252 : Acquire a first key parameter of the vehicle and a second key parameter of the vehicle, wherein the first key parameter is the cornering stiffness of the front wheels of the vehicle, and the second key parameter is the cornering stiffness of the rear wheels of the vehicle.

[0079] As one approach, the first key parameter and the second key parameter of the vehicle can be obtained from a parameter identification module of the vehicle. The parameter identification module may include multiple detection sensors, each of which is used to detect parameters such as the vehicle's current driving information, parameters corresponding to the vehicle's front and rear wheels, and the vehicle's heading angle.

[0080] Step 253 : Determine whether the vehicle dynamics model has an optimal solution based on the discrete state equation, the first key parameter, and the second key parameter.

[0081] As a method, the first key parameter and the second key parameter are substituted into the discrete state equation in step 252 to obtain A d 、B d and C d , based on A d 、B d 、C d and discretized state equations to determine the existence of an optimal solution to the vehicle dynamics model.

[0082] As a way, based on A d 、B d 、C d The optimization solution is performed based on the discrete state equation. Since the optimization solution based on the discrete state equation is repeatedly performed online with the prospect of sampling time, it is also called rolling optimization solution. The rolling optimization solution can repeatedly optimize and solve the current driving information of the vehicle obtained at each sampling time and the first key parameter and the second key parameter determined by the parameter identification module, and can timely correct various complex situations that may occur during the vehicle avoidance process.

[0083] In some embodiments, as Figure 6 As shown, step 253 includes:

[0084] Step 2531 : Determine the position information of a reference point, wherein the reference point is the point at which the vehicle is closest to the reference path trajectory.

[0085] As one approach, the position information of the reference point may be determined by a distance detection device of the vehicle, wherein the position information of the reference point may include the coordinates of the reference point, the heading angle of the vehicle corresponding to the reference point, and the like.

[0086] Step 2532: Determine a cost function based on the position information of the reference point, the current position information, the current vehicle speed, the discrete state equation, the first key parameter, and the second key parameter.

[0087] In order to prevent the vehicle's avoidance failure and thus accidents caused by the error between the actual and reference path trajectories, as well as the accumulation of errors, which may lead to a large difference between the vehicle's driving path trajectory and the reference path trajectory, a cost function can be determined based on the error between the reference path trajectory information and the vehicle's current driving information. The cost function can then be used to determine whether there is an optimal solution for the vehicle dynamics model.

[0088] Optionally, the cost function can generally be expressed as a quadratic function of the state and the control input. Optionally, in this embodiment, the cost function is:

[0089]

[0090] Among them, Np is the prediction step size; X k is the vehicle state matrix at the kth prediction step; X ref_k The reference path trajectory is on the X k The state matrix of the reference point closest to the position; W1 is X k With X ref_k The weight matrix; Nc is the control step size; W2 is the vehicle control input matrix U k The weight matrix of y obs is the horizontal coordinate of the obstacle, y obs_k y obs Up and X k The horizontal coordinate of the nearest obstacle at the location; y k -y obs_k +a is the lateral deviation between the reference point's lateral coordinate and the obstacle's at the kth prediction step; a is a calibration constant; and W3 is the weight matrix for the deviation between the vehicle's predicted position and the nearest obstacle ahead. Optionally, the value of Nc can be the same as or different from Np, depending on actual needs and is not specifically defined here. Optionally, Np = 20, or other values ​​are possible, and are not specifically defined here.

[0091] As a method, in order to match the optimal solution with the vehicle's current speed, W1, W2, and W3 can be determined based on the vehicle's current speed. Optionally, a speed threshold can be set. If the vehicle's current speed is not greater than the speed threshold, W1 = 10 W2 = W3; if the vehicle's current speed is greater than the speed threshold, W1 = 5 W2 = W3. The speed threshold can be 30 km / h or other speed values, and can be set according to actual needs. It is not specifically limited here. Optionally, the matrix corresponding to W1 can be set in advance, and W2 and W3 can be determined based on the vehicle's current speed.

[0092] Optionally, the state matrix X of the reference path trajectory can be determined in advance based on the reference path trajectory. ref ,Right now, where β ref is the sideslip angle of the center of mass corresponding to each path point on the reference path trajectory; is the yaw angular velocity corresponding to each path point on the reference path trajectory; ref is the longitudinal displacement corresponding to each path point on the reference path trajectory; ref is the lateral displacement corresponding to each path point on the reference path trajectory, optional, β ref =0; According to X ref Corresponding to determine X ref_k .

[0093] Step 2533: If the vehicle has a state variable that makes the cost function have a minimum value, it is determined that the vehicle dynamics model has an optimal solution.

[0094] As a way, when there is a U k When the cost function has a minimum value, it can be determined that the vehicle dynamics model has an optimal solution, and the optimal solution is U k .

[0095] In some embodiments, as Figure 7 As shown, step 253 includes:

[0096] Step 254 : Determine a first constraint condition based on the current driving information and the reference path trajectory.

[0097] As a way, when determining whether there is an optimal solution to the vehicle dynamics model, the vehicle needs to perform avoidance processing according to the optimal solution of the vehicle dynamics model, so it is necessary to set a first constraint condition to determine the optimal solution that enables the vehicle to perform safe avoidance, and then enable the vehicle to perform safe avoidance according to the target path trajectory corresponding to the optimal solution.

[0098] As a method, the first constraint condition may include: the side slip angle of the center of mass required by the vehicle during the avoidance process does not exceed the instability boundary, that is, The yaw rate of the vehicle during the avoidance process does not exceed the instability boundary, that is, The lateral displacement of the vehicle during the avoidance process does not exceed the width of a lane, that is, 0≤y k ≤3.75, k=1, 2, 3…Np; the front wheel turning angle of the vehicle during the avoidance process does not exceed the physical limit and the instability boundary, that is, 0≤δ k ≤δ max , k=1, 2, 3...Np. Where u is the road adhesion coefficient, which can be determined from the vehicle parameter identification module; optionally, g=9.8N / m 2 , b is a calibration constant, optional b=1, which can be set according to actual needs and is not specifically limited here.

[0099] As a way, δ max It can be determined based on the current speed of the vehicle. Optionally, the mapping relationship between the vehicle speed and the front wheel angle can be pre-set, and δ can be determined based on the current speed of the vehicle and the mapping relationship between the vehicle speed and the front wheel angle. max Optionally, the mapping relationship between vehicle speed and front wheel angle can be that the vehicle speed corresponds to a δ in different ranges. max Alternatively, a speed range corresponds to a maximum value range of the front wheel angle. For example, when the speed range is 0≤v≤30km / h, the corresponding δ max The value range is 3°-24°.

[0100] Step 255 : determining the target path trajectory according to the first constraint condition, the current driving information, the optimal solution, and the vehicle dynamics model.

[0101] As one approach, based on the first constraint, the vehicle's current driving information, the vehicle dynamics model, and the optimal solution of the vehicle dynamics model are optimized using the open-source library QPOASES to determine the target path trajectory. Alternatively, other optimization methods can be used. The optimization algorithm can be selected based on actual needs and is not specifically limited here.

[0102] In this embodiment, the first constraint condition is added to perform optimization and solution, so that the determined target path trajectory is more accurate.

[0103] In some embodiments, the current driving information includes the current vehicle speed, such as Figure 8 As shown, step 255 includes:

[0104] Step 2551: Determine the first parameter and the second parameter of the discrete state equation according to the first key parameter and the second key parameter.

[0105] As a way, in order to determine the target path trajectory, it is necessary to determine the first parameter A according to the first key parameter, the second key parameter and the current speed of the vehicle. d and the second parameter B d .

[0106] Step 2552: Determine the target path trajectory based on the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution, and the discrete state equation.

[0107] As a method, the first parameter, the second parameter, the first constraint, the current vehicle speed and the optimal solution can be substituted into the discrete state equation for solution, and the Np predicted quantities of the vehicle state matrix can be determined, namely: X (k+1) =A d X k +B d U k +C d , k = 1, 2, 3...Np, and then determine the target path trajectory based on the position information of the Np predicted quantities of the vehicle's state matrix.

[0108] Optionally, after determining Np predicted quantities of the vehicle's state matrix, multiple predicted path points can be determined based on the lateral displacement and longitudinal displacement in the Np predicted quantities, and then the target trajectory path can be determined based on the multiple predicted points.

[0109] In some embodiments, as Figure 9 As shown, step 2552 includes:

[0110] Step 25521: Determine multiple predicted path point sequences based on the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution, and the discrete state equation.

[0111] As a way, the first parameter, the second parameter, the first constraint, the current vehicle speed and the optimal solution are substituted into the discrete state equation for solution. (k+1) The lateral displacement y (k+1) and longitudinal displacement x (k+1) , determine multiple predicted path point sequences, where multiple predicted path point sequences are Y (k+1) =[θ (k+1) x (k+1) y (k+1) ] T , where θ is the heading angle corresponding to each predicted path point, and θ is optional. (k+1) According to x(k+1) and y (k+1) The corresponding curvature can be calculated according to X (k+1) The vehicle's center of mass sideslip angle and the vehicle's yaw angle are determined.

[0112] Step 25522: If the multiple path point sequences meet the second constraint condition, determine the target path trajectory based on the multiple predicted path point sequences.

[0113] As a method, in order to enable the vehicle to safely avoid the target path trajectory determined by the optimal solution, it is necessary to verify the multiple predicted path point sequences. Optionally, the multiple predicted path point sequences can be verified by determining whether the multiple predicted point sequences meet the second constraint condition.

[0114] Optionally, the second constraint condition can be that the difference in lateral coordinates between the coordinates of each predicted path point and the nearest point on the reference path trajectory is within a preset lateral coordinate error range, or that the heading angle error between the heading angle corresponding to each predicted path point and the heading angle corresponding to the nearest point on the reference path trajectory is within a heading angle error range, wherein the preset lateral coordinate error range and the heading angle error range can be set according to actual needs and are not specifically limited here.

[0115] As another approach, if multiple path point sequences do not satisfy the second constraint, in order to prevent the vehicle from being unable to perform safe avoidance during the avoidance process, the reference path trajectory is used as the target path trajectory, and the vehicle can perform safe avoidance according to the reference path trajectory.

[0116] In this embodiment, by verifying multiple path point sequences, it is further determined whether the target path trajectory determined based on the multiple path point sequences can enable the vehicle to safely avoid obstacles, thereby improving the vehicle's avoidance effect and ensuring the safety of the driver.

[0117] In some embodiments, as Figure 10 As shown, before step 25522, the following steps are also included:

[0118] Step 25523: Determine multiple reference path points based on the multiple predicted path point sequences and the reference path trajectory, and determine the reference heading angle corresponding to each reference path point in the multiple reference path points, where the reference path point is the point in the reference path trajectory that is closest to the predicted path point.

[0119] As one approach, a Euclidean distance can be calculated based on the lateral and longitudinal displacements of each predicted pathpoint, and the reference pathpoint can be determined based on the Euclidean distance. Alternatively, the reference heading angle corresponding to each reference pathpoint can be calculated based on the position information of each reference pathpoint in the reference path trajectory.

[0120] Step 25524: Determine a mean square error value based on the reference heading angle corresponding to each reference path point and the predicted heading angle corresponding to each predicted path point.

[0121] As a way, in order to avoid the error between the predicted path point and the reference path point being too large, which will lead to the error between the path trajectory determined by multiple predicted path points and the reference path trajectory being too large, and then causing the vehicle to collide with the obstacle during the avoidance process, the mean square error value of the heading angle can be determined by determining the heading angle error between the reference heading angle corresponding to each reference path point and the predicted heading angle corresponding to each predicted path point, and based on the mean square error value of the heading angle, it is determined whether the predicted heading angle meets the second constraint condition.

[0122] Optionally, you can use the formula To calculate the military error value of the heading angle; where θ k The corresponding heading angle for the kth predicted path point among multiple predicted path points; θ ref_k is the heading angle corresponding to the reference path point on the reference path trajectory that is closest to the k-th predicted path point.

[0123] Step 25525: If the mean square error value is not greater than the preset mean square error value, determine that the multiple path point sequences meet the second constraint condition.

[0124] As a way, a preset mean square error value can be set. When the mean square error value of the heading angle determined by the heading angle error between the reference heading angle corresponding to each reference path point and the predicted heading angle corresponding to each predicted path point is not greater than the preset mean square error value, that is, When , it is determined that a path point sequence satisfies the second constraint condition, where c can be 0.25rad or other values, which can be set according to actual needs and is not specifically limited here.

[0125] In this embodiment, by determining the reference heading angles corresponding to multiple reference predicted path points in the multiple predicted path points that are closest to the reference path trajectory, and whether the heading angle errors between the predicted heading angles corresponding to the multiple predicted path points meet a preset range, it is determined whether the multiple path point sequences meet the second constraint condition, so that the final target path trajectory will not be deformed, and thus the vehicle can safely avoid according to the target driving trajectory.

[0126] In some other embodiments, the plurality of predicted path point sequences include predicted coordinates corresponding to each of the plurality of predicted path points, such as Figure 11 As shown, before step 2552, the following steps are also included:

[0127] Step 25526: Determine multiple reference path points based on the multiple predicted path point sequences and the target point, and determine the reference coordinates corresponding to each reference path point in the multiple predicted path points, wherein the reference path point is the point in the multiple predicted path points that is closest to the target point.

[0128] As a way to avoid the large error between the predicted path points and the reference path points, which may lead to a large error between the path trajectory determined by multiple predicted path points and the reference path trajectory, and thus cause the vehicle to collide with an obstacle during the avoidance process, it can be determined whether the multiple predicted path points meet the second constraint condition by whether the coordinates of the point closest to the target point in the predicted path points are within a preset range.

[0129] Step 25527, determining whether the reference coordinates corresponding to each of the reference path points are within a preset range.

[0130] As a method, the preset range can be that the lateral displacement corresponding to the reference path point is greater than the lateral displacement of the target point and less than a lateral displacement threshold, that is, y ref_目标点 <y j <3.75, where y j is the lateral displacement of each reference path point.

[0131] Step 25528: If it is determined that the reference coordinates corresponding to each of the reference path points are within a preset range, it is determined that the plurality of path point sequences satisfy the second constraint condition.

[0132] As a method, if the reference coordinates corresponding to each reference path point in each reference path point are not within a preset range, it can be determined that the plurality of path point sequences do not satisfy the second constraint condition.

[0133] In this embodiment, whether a plurality of path point sequences satisfy the second constraint condition is determined by determining whether the reference coordinates of a plurality of reference predicted path points that are closest to the target point in the reference path trajectory among the plurality of predicted path points satisfy a preset range, so that the target path trajectory finally determined will not be distorted, and thus the vehicle can safely avoid according to the target driving trajectory.

[0134] In some embodiments, as Figure 12 As shown, before step 220, the method further includes:

[0135] Step 310 : determining a collision distance between the vehicle and the obstacle based on the current driving information and the attribute information, and determining a collision duration based on the current vehicle speed and the collision distance.

[0136] In some embodiments, it is necessary to determine the collision time required for the vehicle to collide with an obstacle at the current speed, so that it can be determined whether the vehicle needs to be alarmed or emergency braked directly according to the collision time.

[0137] In some embodiments, the vehicle may include a distance detection device and a visual sensing device. The distance detection device may be a millimeter-wave radar detector, a laser ranging sensor, or the like, and the visual sensing device may be a camera sensor or other visual sensing device, without limitation herein. Optionally, the visual sensing device may be used to determine whether there are obstacles in front of or behind the vehicle. When the visual sensor detects an obstacle in front of or behind the vehicle, the distance detection device detects the collision distance between the vehicle and the obstacle.

[0138] As a method, the obstacle is stationary, and at this time only the current speed of the vehicle needs to be considered. The formula can be used: TTC = D / V0, where TTC is the collision time; D is the current distance between the vehicle and the obstacle; V0 is the current speed of the vehicle.

[0139] As another approach, if the obstacle is movable, the obstacle's moving speed needs to be considered. Furthermore, the collision time required for the vehicle at its current speed to collide with the obstacle at its current moving speed can be determined. Optionally, the formula can be used: Among them, V a is the moving speed of the obstacle.

[0140] Step 320: Determine the braking duration based on the current vehicle speed and the maximum braking deceleration.

[0141] The braking time is the time it takes for the vehicle to decelerate from its current speed to the maximum braking deceleration. As a method, the maximum braking deceleration is pre-set. The braking deceleration refers to the maximum speed at which the vehicle can rapidly reduce its speed until it stops while driving. Optionally, the maximum braking deceleration can be set to 10m / s. 2 The maximum braking deceleration can also be set to other values. This is only an example and is not limited to any specific value.

[0142] As a way, the braking duration can be calculated based on the maximum braking deceleration threshold and the current vehicle speed, using the formula: Among them, t is the braking time; del max is the maximum braking deceleration; v rel is the speed difference between the vehicle and the obstacle in front, T delay Delay duration, optional, T delay It can be 0.2s or other values, which are only given as examples and are not specifically limited.

[0143] Step 330: If the collision duration is not greater than the braking duration and the steering wheel torque of the vehicle is not less than the torque threshold, the target point is determined according to the current driving information and the attribute information, and the endpoint is determined according to the target point.

[0144] As one approach, when the collision duration is less than the braking duration, it can be determined that the vehicle will not collide with the obstacle if it continues traveling at its current speed. When the vehicle's steering wheel torque is not less than a torque threshold, it can be determined that the vehicle currently requires an avoidance maneuver. Step 220 and subsequent steps can then be executed to enable the vehicle to safely maneuver. Optionally, the torque threshold can be any value between 2 and 15 Nm, or another preset torque value, and can be set based on actual needs and is not specifically limited herein.

[0145] In this embodiment, whether the vehicle will collide with the obstacle is determined based on the vehicle's current driving information and the obstacle's attribute information, and whether the vehicle will avoid the obstacle is determined based on the vehicle's steering wheel torque, thereby making the vehicle's avoidance processing more accurate.

[0146] See also Figure 13 , Figure 13 The module block diagram of the path determination device provided in one embodiment of the present application is shown. The path determination device 400 is applied to the above-mentioned electronic device, and the path determination device 400 includes: an acquisition module 410, a first determination module 420, a reference path trajectory determination module 430, a second determination module 440, a target path trajectory first determination module 450, and a target path trajectory second determination module 460, wherein:

[0147] An acquisition module 410 is used to obtain attribute information of obstacles and current driving information of the vehicle; a first determination module 420 is used to determine a target point based on the current driving information and the attribute information, and to determine an endpoint based on the target point; a reference path trajectory determination module 430 is used to determine a reference path trajectory of the vehicle based on the starting point, the endpoint and the target point of the vehicle; a second determination module 440 is used to determine whether an optimal solution exists for a vehicle dynamics model based on the current driving information; a first target path trajectory determination module 450 is used to determine a target path trajectory of the vehicle based on the optimal solution if an optimal solution exists for the vehicle dynamics model; or a second target path trajectory determination module 460 is used to determine the reference path trajectory as the target path trajectory if an optimal solution does not exist for the vehicle dynamics model.

[0148] In some embodiments, the second determination module 4240 includes: a discretization processing submodule, used to determine the state equation of the vehicle dynamics model based on the current driving information, and discretize the state equation to obtain a discrete state equation; a first acquisition submodule, used to obtain a first key parameter of the vehicle and a second key parameter of the vehicle, wherein the first key parameter is the front wheel lateral stiffness of the vehicle, and the second key parameter is the rear wheel lateral stiffness of the vehicle; a first determination submodule, used to determine whether there is an optimal solution to the vehicle dynamics model based on the discrete state equation, the first key parameter and the second key parameter.

[0149] In some embodiments, the first determination submodule includes: a position information determination unit, used to determine the position information of a reference point, wherein the reference point is the point at which the vehicle is closest to the reference path trajectory; a cost function determination unit, used to determine the cost function based on the position information of the reference point, the current position information, the current vehicle speed, the discrete state, the first key parameter, and the second key parameter; and a determination unit, used to determine that the vehicle dynamics model has an optimal solution if there is a state quantity of the vehicle that makes the cost function have a minimum value.

[0150] In some embodiments, the target path trajectory first determination module 450 includes: a first constraint condition determination submodule, used to determine the first constraint condition based on the current driving information and the reference path trajectory; a target path trajectory determination submodule, used to determine the target path trajectory based on the first constraint condition, the current driving information, the optimal solution and the vehicle dynamics model.

[0151] In some embodiments, the target path trajectory determination submodule includes: a parameter determination unit, used to determine the first parameter and the second parameter of the discrete state equation based on the first key parameter and the second key parameter; a target path trajectory determination unit, used to determine the target path trajectory based on the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution and the discrete state equation.

[0152] In some embodiments, the target path trajectory determination unit includes: a predicted path point sequence determination subunit, used to determine multiple predicted path point sequences based on the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution and the discrete state equation; a target path trajectory determination subunit, used to determine the target path trajectory based on the multiple predicted path point sequences if the multiple path point sequences meet the second constraint.

[0153] In some embodiments, the multiple predicted path point sequences include a predicted heading angle corresponding to each predicted path point in the multiple predicted path points, and the target path trajectory determination unit further includes: a first determination subunit, used to determine multiple reference path points based on the multiple predicted path point sequences and the reference path trajectory, and determine the reference heading angle corresponding to each reference path point in the multiple reference path points, wherein the reference path point is the point in the reference path trajectory that is closest to the predicted path point; a mean square error value determination subunit, used to determine a mean square error value based on the reference heading angle corresponding to each reference path point and the predicted heading angle corresponding to each predicted path point; and a second determination subunit, used to determine that the multiple path point sequences satisfy the second constraint condition if the mean square error value is not less than a preset mean square error value.

[0154] In some embodiments, the multiple predicted path point sequences include predicted coordinates corresponding to each predicted path point in the multiple predicted path points, and the target path trajectory determination unit also includes: a third determination subunit, used to determine multiple reference path points based on the multiple predicted path point sequences and the target point, and determine the reference coordinates corresponding to each reference path point in the multiple predicted path points, wherein the reference path point is the point closest to the target point in the multiple predicted path points; a fourth determination subunit, used to determine whether the reference coordinates corresponding to each reference path point in the reference path points are within a preset range; and a fifth determination subunit, used to determine that the multiple path point sequences satisfy the second constraint condition if it is determined that the reference coordinates corresponding to each reference path point in the reference path points are within a preset range.

[0155] In some embodiments, the attribute information of the obstacle includes the width of the obstacle and the position information of the obstacle, and the first determination module 420 includes: a first distance determination submodule, used to determine a first distance based on the width information of the vehicle and the front overhang distance of the vehicle, wherein the first distance is the distance from the center of the front axle of the vehicle to the vertex of the vehicle; a fourth distance determination submodule, used to determine the fourth distance based on the first distance, the width of the obstacle, the second distance and the third distance, wherein the second distance is the distance between the center of mass of the vehicle and the obstacle, and the third distance is the distance between the center of mass of the vehicle and the center of the front axle of the vehicle; a target point determination submodule, used to determine the target point based on the current driving information, the position information of the obstacle and the fourth distance; an endpoint determination submodule, used to determine the endpoint based on the target point, the length of the vehicle and the width of the vehicle.

[0156] In some embodiments, the first determination module 420 further includes: a collision duration determination submodule, for determining the collision distance between the vehicle and the obstacle based on the current driving information and the attribute information, and determining the collision duration based on the current vehicle speed and the collision distance; a braking duration determination submodule, for determining the braking duration based on the current vehicle speed and the maximum braking deceleration; a judgment submodule, for determining the target point based on the current driving information and the attribute information, and determining the endpoint based on the target point if the collision duration is not greater than the braking duration and the steering wheel torque of the vehicle is not less than a torque threshold.

[0157] According to one aspect of the embodiments of the present application, an electronic device is also provided, such as Figure 14 As shown, the electronic device 500 includes a processor 510 and one or more memories 520. The one or more memories 520 are used to store program instructions executed by the processor 510. When the processor 510 executes the program instructions, the above-mentioned object recognition method is implemented.

[0158] Furthermore, the processor 510 may include one or more processing cores. The processor 510 runs or executes instructions, programs, code sets or instruction sets stored in the memory 520, and calls data stored in the memory 520. Optionally, the processor 510 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 510 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to handle wireless communications. It is understandable that the above-mentioned modem may not be integrated into the processor, but may be implemented separately through a communication chip.

[0159] According to one aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being incorporated into the electronic device. The computer-readable storage medium carries computer-readable instructions. When the computer-readable storage instructions are executed by a processor, the method of any of the above embodiments is implemented.

[0160] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0161] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0162] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0163] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0164] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0165] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining a path, characterized in that: The method comprises: Obtaining attribute information of the obstacle and current driving information of the vehicle, wherein the current driving information includes current position information and current vehicle speed; determining a target point based on the current driving information and the attribute information, and determining an endpoint based on the target point; Determining a reference path trajectory of the vehicle according to the starting point, the endpoint, and the target point of the vehicle; Determining a state equation of the vehicle dynamics model based on the current driving information, and discretizing the state equation to obtain a discrete state equation; Acquiring a first key parameter of the vehicle and a second key parameter of the vehicle, wherein the first key parameter is a front wheel cornering stiffness of the vehicle, and the second key parameter is a rear wheel cornering stiffness of the vehicle; Determining position information of a reference point, wherein the reference point is the point at which the vehicle is closest to the reference path trajectory; determining a cost function according to the position information of the reference point, the current position information, the current vehicle speed, the discrete state equation, the first key parameter, and the second key parameter; If the vehicle has a state quantity that makes the cost function have a minimum value, then determining that the vehicle dynamics model has an optimal solution; If an optimal solution exists for the vehicle dynamics model, determining a target path trajectory of the vehicle according to the optimal solution; or If the vehicle dynamics model does not have an optimal solution, the reference path trajectory is determined as the target path trajectory.

2. The method according to claim 1, characterized in that If the vehicle dynamics model has an optimal solution, determining the target path trajectory of the vehicle according to the optimal solution includes: determining a first constraint condition based on the current driving information and the reference path trajectory; The target path trajectory is determined according to the first constraint condition, the current driving information, the optimal solution and the vehicle dynamics model.

3. The method according to claim 2, characterized in that The current driving information includes a current vehicle speed, and determining the target path trajectory according to the first constraint condition, the current driving information, the optimal solution, and the vehicle dynamics model includes: Determining a first parameter and a second parameter of the discrete state equation according to the first key parameter and the second key parameter; The target path trajectory is determined according to the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution and the discrete state equation.

4. The method according to claim 3, characterized in that The determining the target path trajectory according to the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution, and the discrete state equation includes: determining a plurality of predicted path point sequences based on the first parameter, the second parameter, the first constraint, the current vehicle speed, the optimal solution, and the discrete state equation; If the plurality of predicted path point sequences satisfy a second constraint condition, the target path trajectory is determined according to the plurality of predicted path point sequences.

5. The method according to claim 4, characterized in that The plurality of predicted path point sequences include a predicted heading angle corresponding to each of the plurality of predicted path point sequences, and before determining the target path trajectory according to the plurality of predicted path point sequences if the plurality of predicted path point sequences satisfy a second constraint condition, the method further includes: Determining, based on the plurality of predicted path point sequences and the reference path trajectory, a plurality of reference path points, and determining a reference heading angle corresponding to each of the plurality of reference path points, wherein the reference path point is a point in the reference path trajectory that is closest to the predicted path point; Determining a mean square error value based on the reference heading angle corresponding to each reference path point and the predicted heading angle corresponding to each predicted path point; If the mean square error value is greater than or equal to a preset mean square error value, it is determined that the plurality of predicted path point sequences meet the second constraint condition.

6. The method according to claim 4, characterized in that The plurality of predicted path point sequences include predicted coordinates corresponding to each of the plurality of predicted path points, and before determining the target path trajectory according to the plurality of predicted path point sequences if the plurality of predicted path point sequences satisfy the second constraint condition, the method further includes: Determining, based on the plurality of predicted pathpoint sequences and the target point, a plurality of reference pathpoints, and determining a reference coordinate corresponding to each reference pathpoint in the plurality of predicted pathpoints, wherein the reference pathpoint is a point in the plurality of predicted pathpoints that is closest to the target point; Determining whether a reference coordinate corresponding to each of the reference path points is within a preset range; If it is determined that the reference coordinates corresponding to each of the reference path points are within a preset range, it is determined that the multiple predicted path point sequences meet the second constraint condition.

7. The method according to any one of claims 1 to 6, characterized in that The attribute information of the obstacle includes the width of the obstacle and the position information of the obstacle. The determining of the target point based on the current driving information and the attribute information and determining the endpoint based on the target point include: Determining a first distance based on the width information of the vehicle and the front overhang of the vehicle, wherein the first distance is a distance from a center of a front axle of the vehicle to a vertex of the vehicle; determining a fourth distance based on the first distance, the width of the obstacle, a second distance, and a third distance, wherein the second distance is the distance between the center of mass of the vehicle and the obstacle, and the third distance is the distance between the center of mass of the vehicle and the center of a front axle of the vehicle; determining the target point according to the current driving information, the position information of the obstacle, and the fourth distance; The endpoint is determined based on the target point, the length of the vehicle, and the width of the vehicle.

8. The method according to any one of claims 1 to 6, characterized in that The current driving information includes a current vehicle speed, and determining a target point based on the current driving information and the attribute information and determining an endpoint based on the target point includes: determining a collision distance between the vehicle and the obstacle based on current driving information and the attribute information, and determining a collision duration based on the current vehicle speed and the collision distance; determining a braking duration according to the current vehicle speed and the maximum braking deceleration; If the braking duration is greater than the collision duration and the steering wheel torque of the vehicle is greater than or equal to a torque threshold, the target point is determined according to the current driving information and the attribute information, and the endpoint is determined according to the target point.

9. A path determination device, characterized in that: The device comprises: An acquisition module is used to acquire attribute information of obstacles and current driving information of the vehicle, wherein the current driving information includes current position information and current vehicle speed; A first determining module is configured to determine a target point based on the current driving information and the attribute information, and to determine an endpoint based on the target point; A reference path trajectory determination module, configured to determine a reference path trajectory of the vehicle based on the starting point, the end point, and the target point of the vehicle; a second determination module, configured to determine a state equation of the vehicle dynamics model based on the current driving information, and discretize the state equation to obtain a discrete state equation; obtain a first key parameter and a second key parameter of the vehicle, wherein the first key parameter is the cornering stiffness of the front wheels of the vehicle, and the second key parameter is the cornering stiffness of the rear wheels of the vehicle; determine position information of a reference point, wherein the reference point is the point at which the vehicle is closest to the reference path trajectory; determine a cost function based on the position information of the reference point, the current position information, the current vehicle speed, the discrete state equation, the first key parameter, and the second key parameter; and determine that an optimal solution exists for the vehicle dynamics model if a state quantity of the vehicle exists that minimizes the cost function; a first target path trajectory determination module, configured to determine the target path trajectory of the vehicle according to an optimal solution if an optimal solution exists for the vehicle dynamics model; or The target path trajectory second determination module is configured to determine the reference path trajectory as the target path trajectory if no optimal solution exists for the vehicle dynamics model.

10. An electronic device, characterized in that: The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program code, which can be called by a processor to execute the method according to any one of claims 1 to 8.

Images