Improved A-satellite intelligent vehicle obstacle avoidance path searching method and device, vehicle and storage medium

Abstract

The invention discloses an improved A-star intelligent vehicle obstacle avoidance path searching method and device, a vehicle and a storage medium, and relates to the technical field of vehicle path planning, and the method comprises the steps: obtaining a preset node list and a to-be-checked node list; sequentially calculating the track cost of each to-be-checked node, and selecting the to-be-checked node with the minimum track cost as a current node; traversing the preset node list, and updating the to-be-checked node list and the track information of each preset node; if the current node is not the path planning end point, removing the current node from the to-be-checked node list; and if the to-be-checked node list is empty, starting to query the father node from the path planning end point, then querying the father node of the father node, and so on, and generating a path according to the queried node. On the premise that obstacle avoidance is completed, the calculation load of a traditional search method is reduced, the path search efficiency is improved, meanwhile, the acceleration change rate of the planned trajectory can be restrained, and the control comfort is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of automobile path planning, and in particular to an improved A-star intelligent automobile obstacle avoidance path search method, device, vehicle and storage medium. Background Art

[0002] In recent years, the trend of automobile electrification, intelligence and networking has become more and more obvious. However, automobile safety remains an important topic now and in the future. According to statistics from the World Health Organization, about 1.3 million people die in road traffic accidents each year. In addition, more than 50 million people are injured in traffic accidents, and human factors account for more than 55% of road traffic accidents. Automobile active safety, as an important part of the automobile safety system, can effectively reduce traffic accidents caused by human errors, and has increasingly become a focus of major automobile companies and research institutions. Active safety functions, such as emergency lane keeping and emergency steering assist, all require lateral control in a very short time to complete emergency obstacle avoidance.

[0003] At present, the complex obstacle avoidance path planning methods mainly include fitting-based methods, such as Bezier curves, quintic polynomial curve fitting, etc. In addition, there are also search-based methods, such as A-star, D-star, etc. The fitting-based method is simpler to calculate, but it involves obstacle avoidance and requires setting dynamic constraints, especially in complex scenes, and requires frequent updates of the planned trajectory. The traditional search-based method requires the layout of a large number of search points in space, which is complex to calculate and has high load requirements.

[0004] Therefore, how to efficiently plan a stable trajectory is a problem that needs to be solved urgently.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide an improved A-star intelligent car obstacle avoidance path search method, device, vehicle and storage medium, aiming to solve the technical problem of how to efficiently plan a stable trajectory.

[0007] To achieve the above objectives, the present application proposes an improved A-star intelligent vehicle obstacle avoidance path search method, the method comprising:

[0008] Obtaining a preset node list and a list of nodes to be checked, wherein the preset node list includes the path planning starting point and the obstacle intersection point, and the nodes to be checked include the path nodes that have not been searched;

[0009] Calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory;

[0010] Based on the current node, traverse the preset node list, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost;

[0011] If the current node is not the end point of the path planning, removing the current node from the list of nodes to be checked;

[0012] If it is detected that the list of nodes to be checked is empty, the parent node is queried starting from the end point of the path planning, and then the parent node of the parent node is queried, and so on, until the starting point of the path planning is found, and a path is generated according to the queried nodes.

[0013] In one embodiment, obtaining the preset node list includes:

[0014] Based on the vehicle coordinate system, obtain vehicle information and target information, wherein the vehicle information includes the longitudinal position point coordinates, lateral position point coordinates, longitudinal speed, lateral speed, longitudinal acceleration, lateral acceleration and the length of the front and rear ends of the vehicle relative to the center of mass of the vehicle at the prediction time, and the target information includes the longitudinal distance, lateral distance, longitudinal acceleration of the target relative to the vehicle, longitudinal speed of the target relative to the vehicle, target longitudinal speed, target lateral speed, target longitudinal acceleration and target lateral acceleration of the target at the initial prediction time;

[0015] Obtaining a vehicle point and four corner points of the target based on the vehicle information and the target information;

[0016] Based on the vehicle coordinate system, a reference line is set, wherein the reference line is represented by a cubic polynomial;

[0017] Based on the cubic polynomial representation of the ego vehicle, four corner points of the target and the reference line, a lateral overlap point between the ego vehicle and the target is obtained;

[0018] Get the starting point of path planning;

[0019] A preset node list is generated according to the overlapping point and the path planning starting point.

[0020] In one embodiment, obtaining the vehicle point and four corner points of the target based on the vehicle information and the target information includes:

[0021] Based on the longitudinal direction, according to the longitudinal acceleration of the target relative to the ego vehicle, the longitudinal speed of the target relative to the ego vehicle, and the longitudinal distance of the target at the initial prediction time, calculating the overlap time between the ego vehicle and the target;

[0022] Calculating the lateral coordinate of the vehicle at the overlapping moment according to the lateral velocity of the vehicle, the lateral acceleration of the vehicle and the overlapping moment;

[0023] Calculating the target lateral coordinate at the overlapping time according to the lateral distance of the target at the prediction initial time, the target lateral speed, the target lateral acceleration and the overlapping time;

[0024] The overlapping moment and the lateral coordinate are combined to obtain the vehicle point and the four corner points of the target.

[0025] In one embodiment, obtaining the lateral overlapping point between the ego vehicle and the target based on the cubic polynomial representation of the ego vehicle, the four corner points of the target and the reference line includes:

[0026] If the ego vehicle point and the corner point overlap in the horizontal direction, the position of the ego vehicle relative to the reference line is calculated;

[0027] Calculating the longitudinal coordinate of the vehicle at the overlapping moment according to the longitudinal velocity of the vehicle, the longitudinal acceleration of the vehicle and the overlapping moment;

[0028] Calculating the longitudinal coordinate of the target at the overlapping time according to the longitudinal distance of the target at the initial prediction time, the longitudinal speed of the target, the longitudinal acceleration of the target and the overlapping time;

[0029] Substituting the longitudinal coordinate of the vehicle and the longitudinal coordinate of the target into the cubic polynomial of the reference line to obtain the lateral distance of the vehicle relative to the reference line and the lateral distance of the target relative to the reference line;

[0030] Combining the overlap moment, the lateral distance of the ego vehicle relative to the reference line, and the lateral distance of the target relative to the reference line to obtain a lateral overlap point of the ego vehicle and the target;

[0031] A minimum convex hull set is generated according to the lateral overlapping points.

[0032] In one embodiment, the traversing the preset node list based on the current node and updating the list of nodes to be checked and the trajectory information of each preset node includes:

[0033] Select a node from the preset node list as an intermediate node;

[0034] Generate a first trajectory segment from the current node to the intermediate node and a second trajectory segment from the intermediate node to a path planning end point;

[0035] If it is detected that there is no collision risk in the first trajectory segment and the intermediate node does not belong to the list of nodes to be checked, updating the trajectory information of the intermediate node and adding the intermediate node to the list of nodes to be checked;

[0036] or,

[0037] If it is detected that there is no collision risk in the first trajectory segment and the trajectory cost of the first trajectory segment is less than the minimum trajectory cost of the intermediate node, updating the trajectory information of the intermediate node;

[0038] Repeat the above steps until the traversal of the preset node list is completed.

[0039] In one embodiment, the calculation of the trajectory cost includes:

[0040] Get the start node and end node of the trajectory segment to be generated;

[0041] Substituting the start node and the end node into a two-segment quintic polynomial to establish a constraint condition for the trajectory segment;

[0042] Obtaining a lateral acceleration change rate of the trajectory segment;

[0043] Establishing a cost function based on the acceleration change rate;

[0044] Construct a cost function that integrates constraints;

[0045] Based on the cost function of the fusion constraint condition, the trajectory cost of the start node and the end node is calculated.

[0046] In addition, to achieve the above purpose, the present application also proposes an improved A-star intelligent car obstacle avoidance path search device, the improved A-star intelligent car obstacle avoidance path search device comprising:

[0047] An acquisition module, used to acquire a preset node list and a list of nodes to be checked, wherein the preset node list includes a path planning starting point and an obstacle intersection point, and the nodes to be checked include path nodes that have not been searched;

[0048] A selection module, used for calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory;

[0049] A maintenance module, configured to traverse the preset node list based on the current node, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; if the current node is not the end point of the path planning, remove the current node from the list of nodes to be checked;

[0050] The output module is used to query the parent node from the path planning end point if it is detected that the list of nodes to be checked is empty, and then query the parent node of the parent node, and so on, until the path planning starting point is found, and generate a path according to the queried nodes.

[0051] In addition, to achieve the above-mentioned purpose, the present application also proposes an improved A-star smart car obstacle avoidance path search device, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the improved A-star smart car obstacle avoidance path search method as described above.

[0052] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of improving the obstacle avoidance path search method of the A-star smart car are implemented as described above.

[0053] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of improving the obstacle avoidance path search method of the A-star smart car as described above.

[0054] One or more technical solutions proposed in this application have at least the following technical effects:

[0055] The node information in the path search process is stored in a preset node list, and the trajectory cost of the nodes in the node list to be checked is calculated based on the acceleration change rate of the trajectory. The node with the smallest trajectory cost is used as the current node, and then the preset node list is traversed. According to the information of the current node, the trajectory information of the node list to be checked and the preset node are updated. When it is detected that the list to be checked is empty, the parent node is queried starting from the end point of the path planning, and then the parent node of the parent node is queried, and so on, until the starting point of the path planning is found, and the path is generated according to the queried nodes to complete the path search. On the premise of completing obstacle avoidance, this application can reduce the computational load of the traditional search method, improve the path search efficiency, and at the same time constrain the acceleration change rate of the planned trajectory to ensure the comfort of control. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0058] Figure 1 A flowchart diagram of the first embodiment of the improved A-star intelligent vehicle obstacle avoidance path search method provided in this application;

[0059] Figure 2 Improve the node graph of the obstacle avoidance path search method of A-star smart car for this application;

[0060] Figure 3 This is an example diagram of the path search for improving the A-star smart car obstacle avoidance path search method for this application;

[0061] Figure 4 A flowchart diagram of the second embodiment of the improved A-star intelligent vehicle obstacle avoidance path search method provided in this application;

[0062] Figure 5 A schematic diagram of the module structure of the improved A-star intelligent vehicle obstacle avoidance path search device according to the embodiment of the present application;

[0063] Figure 6 This is a schematic diagram of the device structure of the hardware operating environment involved in improving the A-star smart car obstacle avoidance path search method in the embodiment of the present application.

[0064] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0066] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0067] The main solution of the embodiment of the present application is: obtaining a preset node list and obtaining a list of nodes to be checked, wherein the preset node list includes the path planning starting point, obstacle overlapping points, and the nodes to be checked include path nodes that have not been searched; calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory; based on the current node, traversing the preset node list, updating the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; if the current node is not the end point of the path planning, removing the current node from the list of nodes to be checked; if it is detected that the list of nodes to be checked is empty, querying the parent node from the end point of the path planning, and then querying the parent node of the parent node, and so on, until the path planning starting point is found, and a path is generated according to the queried nodes.

[0068] In the prior art, path planning needs to ensure safety, and the complex obstacle avoidance path planning methods mainly include fitting-based methods and search-based methods. The fitting-based method is simpler to calculate, but it requires dynamic constraints to be set when it comes to obstacle avoidance, especially in complex scenes, and requires frequent updates of the planned trajectory. The traditional search-based method requires a large number of search points to be arranged in space, which is complex to calculate and has high requirements for load. Therefore, how to efficiently plan a stable trajectory is an urgent problem to be solved.

[0069] It can be seen from the above embodiments that the present application stores the node information in the path search process through a preset node list, calculates the trajectory cost of the nodes in the node list to be checked based on the acceleration change rate of the trajectory, and uses the node with the smallest trajectory cost as the current node. Then, the preset node list is traversed, and the trajectory information of the node list to be checked and the preset node are updated according to the information of the current node. When it is detected that the list to be checked is empty, the parent node is queried starting from the end point of the path planning, and then the parent node of the parent node is queried, and so on, until the starting point of the path planning is found, and a path is generated according to the queried nodes to complete the path search. On the premise of completing obstacle avoidance, the present application reduces the computational load of the traditional search method, improves the path search efficiency, and at the same time constrains the acceleration change rate of the planned trajectory to ensure the comfort of control.

[0070] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes a mobile phone as an example to illustrate this embodiment and the following embodiments.

[0071] Based on this, the embodiment of the present application provides an improved A-star intelligent car obstacle avoidance path search method, referring to Figure 1 , Figure 1 This is a flow chart showing the improvement of the first embodiment of the obstacle avoidance path search method for the A-star smart car in this application.

[0072] In this embodiment, the improved A-star intelligent vehicle obstacle avoidance path search method includes steps S10 to S50:

[0073] Step S10, obtaining a preset node list and a list of nodes to be checked, wherein the preset node list includes a path planning starting point and an obstacle intersection point, and the nodes to be checked include path nodes that have not been searched;

[0074] It should be noted that the preset node can be the intersection point of the ego vehicle and the target, or the starting point of the path planning, that is, the position of the ego vehicle. The target can be a static obstacle such as a lane line, a road edge, or a vehicle near the ego vehicle in the driving path. The list of nodes to be checked stores all the nodes to be searched. In the A-star search algorithm, each time the node with the smallest trajectory cost is selected from the list of nodes to be checked as the next node to be searched, and the trajectory cost is the criterion for selecting the trajectory.

[0075] It is understandable that it is necessary to determine the target data on the driving path of the vehicle in order to perform path search, so step S10 is performed to improve the efficiency of path search.

[0076] In a feasible implementation, step S10 may include steps A01 to A12:

[0077] Step A01, obtaining vehicle information and target information based on the vehicle coordinate system;

[0078] It should be noted that it is assumed that the vehicle is moving in a straight line with uniform acceleration in both the horizontal and vertical directions. Figure 2 As shown, the vehicle information includes x ego ,y ego , v x-ego , v y-ego , a x-ego , a y-ego , respectively, are the longitudinal position coordinates, lateral position coordinates, longitudinal velocity, lateral velocity, longitudinal acceleration, lateral acceleration, and the length L of the front and rear ends of the vehicle relative to the center of mass at the prediction time f , L r The target vehicle is characterized by four corner points, where Δx, Δy, a x-rel , v x-rel , v x-object , v y-object , a x-obj , a y-objThey are respectively the longitudinal distance at the initial moment of prediction, the lateral distance, the longitudinal acceleration of the target relative to the vehicle, the longitudinal speed of the target relative to the vehicle, the target longitudinal speed, the target lateral speed, the target longitudinal acceleration, and the target lateral acceleration. In addition, the width and length of the target vehicle are L obj , W obj .

[0079] Step A02, based on the longitudinal direction, according to the longitudinal acceleration of the target relative to the vehicle, the longitudinal speed of the target relative to the vehicle, and the longitudinal distance of the target at the initial prediction time, calculating the overlap time between the vehicle and the target;

[0080] It should be noted that the longitudinal direction may be the direction in which the vehicle is moving, the predicted initial moment may be the start time of path planning, the longitudinal acceleration of the target relative to the own vehicle may be the rate of change of the speed of the target vehicle relative to the own vehicle in the longitudinal direction, the longitudinal speed of the target relative to the own vehicle may be the speed difference between the target (such as the vehicle in front) and the own vehicle in the direction in which the vehicle is moving, and the overlapping moment is the time point when the positions of the own vehicle and the target overlap or are close.

[0081] like Figure 2 , in the longitudinal direction, calculate the moment when the vehicle overlaps with the target point, that is:

[0082]

[0083] Among them, t overlap is the longitudinal overlap time between the ego vehicle and the target.

[0084] Step A03, calculating the lateral coordinate of the vehicle at the overlapping moment according to the lateral velocity of the vehicle, the lateral acceleration of the vehicle and the overlapping moment;

[0085] It should be noted that the lateral direction is perpendicular to the longitudinal direction, and refers to the direction of the vehicle width, that is, the direction of the left and right sides of the vehicle. The lateral speed of the vehicle can be the speed of the vehicle in the lateral direction. The lateral acceleration of the vehicle can be the rate of change of the lateral speed of the vehicle, that is, how fast the vehicle accelerates or decelerates in the lateral direction. The lateral coordinate of the vehicle can be the position of the vehicle in the lateral direction at the moment of overlap.

[0086] like Figure 2 , execute step A03 according to the formula:

[0087]

[0088] Step A04, calculating the target lateral coordinates at the overlap time according to the lateral distance of the target at the initial prediction time, the target lateral velocity, the target lateral acceleration and the overlap time, that is, (t overlap ,y ego-overlap );

[0089] It should be noted that the lateral distance of the target at the initial prediction moment can be the distance between the target and the ego vehicle in the lateral direction. This distance can be positive or negative, depending on the lateral position of the target relative to the ego vehicle.

[0090] like Figure 2 , execute step A04 according to the formula:

[0091]

[0092] Step A05, combining the overlap time and the lateral coordinate to obtain the vehicle point and the four corner points of the target, namely (t overlap ,y obj-overlap ).

[0093] Step A06, setting a reference line based on the vehicle coordinate system, wherein the reference line is represented by a cubic polynomial;

[0094] It should be noted that based on the vehicle coordinate system, the expression of the reference line is as follows, y represents the horizontal coordinate, x represents the vertical coordinate, c0, c1, c2, c3 are unknown coefficients, that is, real numbers

[0095] y=c0+c1x+c2x 2 +c3x 3

[0096] Step A07, if the ego vehicle point and the corner point overlap in the horizontal direction, then calculating the position of the ego vehicle relative to the reference line at this time;

[0097] It can be understood that the existence of lateral overlap means that the lateral coordinate of the vehicle is within the range of the lateral coordinates of the four corner points of the target.

[0098] Step A08, calculating the longitudinal coordinate of the vehicle at the overlapping moment according to the longitudinal velocity of the vehicle, the longitudinal acceleration of the vehicle and the overlapping moment;

[0099] It should be noted that the longitudinal velocity of the vehicle may be the velocity of the vehicle in the longitudinal direction, the longitudinal acceleration of the vehicle may be the rate of change of the longitudinal velocity of the vehicle, that is, how fast the vehicle accelerates or decelerates in the longitudinal direction, and the longitudinal coordinate of the vehicle may be the position of the vehicle in the longitudinal direction at the moment of overlap.

[0100] The longitudinal coordinate of the ego vehicle at the time of overlap is:

[0101]

[0102] Step A09, calculating the longitudinal coordinate of the target at the overlapping time according to the longitudinal distance of the target at the initial prediction time, the longitudinal speed of the target, the longitudinal acceleration of the target and the overlapping time;

[0103] It should be noted that the target longitudinal velocity may be the velocity of the target in the longitudinal direction, the target longitudinal acceleration may be the rate of change of the longitudinal velocity of the vehicle, that is, how fast the target accelerates or decelerates in the longitudinal direction, and the target longitudinal coordinate may be the position of the target in the longitudinal direction at the moment of overlap.

[0104] The vertical coordinate of the target at the time of overlap is:

[0105]

[0106] Step A10, substituting the longitudinal coordinate of the vehicle and the longitudinal coordinate of the target into the cubic polynomial of the reference line to obtain the lateral distance of the vehicle relative to the reference line and the lateral distance of the target relative to the reference line;

[0107] The lateral distance of the vehicle relative to the reference line at the moment of overlap:

[0108]

[0109] The lateral distance of the target relative to the reference line at the moment of overlap is:

[0110]

[0111] Step A11, combining the overlapping moment, the lateral distance of the ego vehicle relative to the reference line, and the lateral distance of the target relative to the reference line to obtain a lateral overlapping point of the ego vehicle and the target;

[0112] It should be noted that both the ego vehicle and the target vehicle are represented by multiple points, so the lateral distances of the overlapping points at the obtained overlapping moments are different. The lateral overlapping point structure is as follows:

[0113] (t overlap ,y ego-to-center ), (t overlap ,y obj-to-center )

[0114] Step A12: generating a minimum convex hull set according to the horizontal overlapping points.

[0115] It should be noted that if Figure 2 As shown, the minimum convex hull set can be used as the boundary of path planning.

[0116] In this implementation, the overlapping time and the overlapping point are predicted by using the vehicle information and the target information, thereby reducing the computational load of the traditional search method.

[0117] Step S20, calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory;

[0118] It should be noted that the trajectory cost may be the cost of a trajectory from the starting point of path planning, through the current node, to the end point of path planning, and is obtained through a cost function based on the acceleration change rate of the trajectory.

[0119] It can be understood that the next node to be searched (current node) is determined according to the trajectory cost of the node to be checked, so as to ensure the stability and reliability of the generated trajectory.

[0120] In a feasible implementation, if the list of nodes to be checked is empty, the starting point of the path planning is used as the current node; or, if the list of nodes to be checked is not empty, a node is selected from the list of nodes to be checked; based on the trajectory information, a trajectory segment to be checked passing through the node is generated; if there is no intersection between the trajectory segment to be checked and the nodes in the preset node list, the trajectory cost of the trajectory segment to be checked is calculated; repeat the above steps and use the node with the smallest trajectory cost as the current node.

[0121] It should be noted that the starting point of path planning is the position of the vehicle obtained based on the vehicle coordinate system. The trajectory information can be the parent node of the node and the minimum trajectory cost. The parent node can be the previous node of the node on this trajectory, and the current node can be the next node to be searched.

[0122] According to the current node information, the corresponding overlapping point coordinates:

[0123] (t overlap , Δy, y obj-to-center )

[0124] At the same time, it is assumed that the lateral motion of the vehicle is uniformly accelerated linear motion, that is, within the prediction time, the lateral distance of the vehicle is:

[0125]

[0126] W represents the width of the vehicle. If y estimated-ego +0.5W If there are multiple target overlapping points within the coverage area, it is considered that there is a collision risk.

[0127] For example, Figure 3, in the list of nodes to be checked, for a certain node A, use the above method to generate the trajectory of S->A, A->E, and E is the end point of the entire path planning. Perform collision detection on the generated trajectory. If the obtained trajectory has an intersection with the overlapping point corresponding to the node, it is considered that there is still a risk of collision when driving along the generated trajectory. At this time, set the cost of the path to infinity. If there is no intersection, it is considered that obstacle avoidance can be achieved by driving along the generated trajectory, and finally obtain the node A1 with the smallest trajectory cost in the list of nodes to be checked.

[0128] Step S30, based on the current node, traverse the preset node list, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost;

[0129] In a feasible implementation, a node is selected from the preset node list as an intermediate node; a first trajectory segment from the current node to the intermediate node and a second trajectory segment from the intermediate node to the path planning end point are generated; if it is detected that there is no collision risk in the first trajectory segment and the intermediate node does not belong to the list of nodes to be checked, the trajectory information of the intermediate node is updated and the intermediate node is added to the list of nodes to be checked; or, if it is detected that there is no collision risk in the first trajectory segment and the trajectory cost of the first trajectory segment is less than the minimum trajectory cost of the intermediate node, the trajectory information of the intermediate node is updated; and the above steps are repeated until the traversal of the preset node list is completed.

[0130] It should be noted that the intermediate node belongs to the preset node list and can be an obstacle intersection point. It can also be the end point of path planning. The trajectory segment can be the trajectory generated from the current node to the intermediate node. To update the trajectory information of the intermediate node, it is necessary to set the parent node of the intermediate node to the current node, calculate the cost of the trajectory from the path planning starting point, passing through the current node, to the intermediate node, and set the minimum trajectory cost of the intermediate node to the cost of the trajectory from the path planning starting point, passing through the current node, to the intermediate node.

[0131] According to the preset node information, that is, the corresponding overlap point coordinates and the lateral distance Δy of the target relative to the vehicle at the initial moment:

[0132] (t overlap , Δy, y obj-to-center )

[0133] At the same time, it is assumed that the lateral motion of the vehicle is uniformly accelerated linear motion, that is, within the prediction time, the lateral distance of the vehicle is:

[0134]

[0135] W represents the width of the vehicle. If y estimated-egoIf +0.5W is within the coverage range of multiple overlapping points, a collision risk is considered to exist.

[0136] Exemplarily, check all nodes to determine all nodes adjacent to A1. The determination of adjacent nodes is as follows: Also use the above trajectory generation, that is, generate the trajectory from A1 to its adjacent point B. First, the cost of A1->B is not infinite, and B is not in the list of nodes to be checked or the path cost g_score_temp from the path planning start point to B is less than its historical trajectory cost g_score saved in the trajectory information, that is: g_score_temp < g_score. If the above conditions are met, B is considered an adjacent node of A1, then update the g_score of B to the cost g_score_temp calculated at this time, that is, g_score = g_score_temp. At the same time, calculate the trajectory from B to the path planning end point and its cost according to the above method, and calculate the total trajectory cost h_score_temp, that is: the trajectory cost of S->A1->B->E, update it as the parent node of B, and record the total trajectory cost.

[0137] It can be understood that it is necessary to query the adjacent nodes (intermediate nodes) of the current node, and update the trajectory information of the node in a timely manner, and maintain the list of nodes to be checked. Therefore, performing step S30 ensures the accuracy of path search.

[0138] Step S40, if the current node is not the path planning end point, remove the current node from the list of nodes to be checked;

[0139] It should be noted that the path planning end point can set the lateral speed and lateral acceleration of the end point to 0, and the node information is (t e , y e-lower , y e-upper , v lower , v upper , v deviation , 0), where y e-lower , y e-upper are the lower limit value and upper limit value of the lateral position of the end point, and v lower , v upper , v deviation are the lower limit value, upper limit value and acceptable deviation of the lateral speed of the end point.

[0140] It can be understood that by removing the node from the list of nodes to be checked, duplicate processing of the node is avoided, which is beneficial to improving the search efficiency.

[0141] Step S50, if it is detected that the list of nodes to be checked is empty, query the parent node starting from the path planning end point, then query the parent node of the parent node, and so on, until the path planning starting point is found, and generate a path according to the queried nodes.

[0142] The present embodiment provides an improved A-star intelligent car obstacle avoidance path search method, which stores node information in the path search process through a preset node list, calculates the trajectory cost of the nodes in the node list to be checked based on the acceleration change rate of the trajectory, and uses the node with the smallest trajectory cost as the current node. Then, the preset node list is traversed, and the trajectory information of the node list to be checked and the preset node are updated according to the information of the current node. When it is detected that the list to be checked is empty, the parent node is queried starting from the path planning end point, and then the parent node of the parent node is queried, and so on, until the path planning starting point is found, and a path is generated according to the queried nodes to complete the path search. Under the premise of completing obstacle avoidance, the present application reduces the computational load of the traditional search method, improves the path search efficiency, and can constrain the acceleration change rate of the planned trajectory to ensure the comfort of control.

[0143] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 , step S30 and step S40, the improved A-star intelligent car obstacle avoidance path search method also includes steps B01 to B06:

[0144] Step B01, obtaining the start node and the end node of the trajectory segment to be generated;

[0145] It should be noted that the trajectory segment to be generated may be a trajectory generated when the trajectory cost is involved in executing step 30 and step 40, the start node may be the starting point of the trajectory, the end point may be the end point of the trajectory, and the start node and the end node may be the following three node types:

[0146] Node type 1 is an overlapping point, and its node information is the calculated overlapping convex hull set, that is, (t overlap ,y obj-to-center ) and (t overlap ,y ego-to-center ), and set its lateral velocity and lateral acceleration to 0, that is: (t overlap ,y obj-to-center , 0, 0) and (t overlap ,y ego-to-center , 0, 0);

[0147] Node type 2 is the starting point of path planning, and its node information is (t s ,y s , as );

[0148] Node type 3 is the end point of path planning. The lateral velocity and lateral acceleration of the end point are set to 0. Its node information is (t e ,y e-lower ,y e-upper , v lower , v upper , v deviation , 0), where y e-lower ,y e-upper are the lower and upper limits of the end point’s lateral position, v lower , v upper , v deviation The lower limit and upper limit of the lateral speed at the end point and the acceptable deviation.

[0149] Step B02, substituting the start node and the end node into a two-segment quintic polynomial to establish a constraint condition for the trajectory segment;

[0150] It should be noted that the form of the two-segment quintic polynomial is as follows, namely:

[0151] y1=c0t 5 +c1t 4 +c2t 3 +c3t 2 +c4t+c5,t s ≤t≤t k ;

[0152] y2=c′0t 5 +c′1t 4 +c′2t 3 +c′3t 2 +c′4t+c′5,t k ≤t≤t e ;

[0153] Substituting the start node and the end node into the two-segment quintic polynomial, the constraints are:

[0154] At the start time t s :

[0155]

[0156] At the end point in time t e :

[0157]

[0158]

[0159] At the time t when the two trajectories overlapk :

[0160]

[0161] There are 13 unknown parameters in total, namely: c0, c1, c2, c3, c4, c5, c′0, c′1, c2, c′3, c ′4 , c′5,t k ,

[0162] Step B03, obtaining the lateral acceleration change rate of the trajectory segment;

[0163] It should be noted that the acceleration rate of change can be the rate at which acceleration changes over time, that is, how fast the speed changes. If the acceleration rate of change is large, it means that the speed of the object is changing rapidly, which is used to measure the smoothness of the motion.

[0164] Step B04, establishing a cost function based on the acceleration change rate;

[0165] It should be noted that the cost function can be used to calculate the trajectory cost;

[0166] The acceleration rate of the two-stage trajectory is in parabolic form, and the cost function is established by the sum of the squares of the lateral acceleration rate of the trajectory:

[0167]

[0168] Step B05, constructing a cost function of the fusion constraint conditions;

[0169] The above constraints can be written as follows:

[0170] h i (w)=0, w=(c0, c1, c2, c3, c4, c5, c′0, c′1, c′2, c′3, c′4, c′5, t k ), i = 1, 2, 3, ..., 12

[0171] Construct the cost function of the fusion constraint:

[0172]

[0173] Step B06, calculating the trajectory costs of the start node and the end node based on the cost function of the fusion constraint condition.

[0174] It should be noted that the solution of the above trajectory is transformed into finding the minimum value:

[0175] min w L

[0176] According to the Lagrange multiplier method:

[0177]

[0178] There are 25 unknown parameters in total, including 25 equations that can be solved to obtain the unknown parameters.

[0179] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the present application's improved A-star smart car obstacle avoidance path search method. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0180] This application also provides an improved A-star intelligent car obstacle avoidance path search device, please refer to Figure 5 The improved A-star intelligent vehicle obstacle avoidance path search device comprises:

[0181] An acquisition module 10 is used to acquire a preset node list and a list of nodes to be checked, wherein the preset node list includes a path planning starting point and an obstacle intersection point, and the nodes to be checked include path nodes that have not been searched;

[0182] A selection module 20, configured to calculate the trajectory cost of each of the nodes to be checked in turn, and select the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory;

[0183] A maintenance module 30 is used to traverse the preset node list based on the current node, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; if the current node is not the end point of the path planning, remove the current node from the list of nodes to be checked;

[0184] The output module 40 is used to query the parent node from the path planning end point if it is detected that the list of nodes to be checked is empty, and then query the parent node of the parent node, and so on, until the path planning starting point is found, and a path is generated according to the queried nodes.

[0185] The improved A-star intelligent car obstacle avoidance path search device provided by the present application adopts the improved A-star intelligent car obstacle avoidance path search method in the above embodiment, which can solve the technical problem of improving the A-star intelligent car obstacle avoidance path search. Compared with the prior art, the beneficial effects of the improved A-star intelligent car obstacle avoidance path search device provided by the present application are the same as the beneficial effects of the improved A-star intelligent car obstacle avoidance path search method provided by the above embodiment, and the other technical features in the improved A-star intelligent car obstacle avoidance path search device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0186] In one embodiment, the acquisition module 10 is further used to acquire self-vehicle information and target information based on the self-vehicle coordinate system, wherein the self-vehicle information includes the longitudinal position point coordinates, lateral position point coordinates, longitudinal speed, lateral speed, longitudinal acceleration, lateral acceleration and the length of the front and rear ends of the self-vehicle relative to the center of mass of the self-vehicle at the prediction time, and the target information includes the longitudinal distance, lateral distance, longitudinal acceleration of the target relative to the self-vehicle, longitudinal speed of the target relative to the self-vehicle, target longitudinal speed, target lateral speed, target longitudinal acceleration and target lateral acceleration of the target at the initial prediction time; based on the self-vehicle information and the target information, the self-vehicle point and the four corner points of the target are obtained; based on the self-vehicle coordinate system, a reference line is set, and the reference line is represented by a cubic polynomial; based on the self-vehicle, the four corner points of the target and the cubic polynomial representation of the reference line, the lateral overlapping point of the self-vehicle and the target is obtained; the path planning starting point is obtained; and a preset node list is generated according to the overlapping point and the path planning starting point.

[0187] In one embodiment, the acquisition module 10 is further used to calculate the overlapping moment of the self-vehicle and the target based on the longitudinal direction according to the longitudinal acceleration of the target relative to the self-vehicle, the longitudinal speed of the target relative to the self-vehicle and the longitudinal distance of the target at the predicted initial moment; calculate the lateral coordinates of the self-vehicle at the overlapping moment according to the lateral speed of the self-vehicle, the lateral acceleration of the self-vehicle and the overlapping moment; calculate the lateral coordinates of the target at the overlapping moment according to the lateral distance of the target at the predicted initial moment, the lateral speed of the target, the lateral acceleration of the target and the overlapping moment; combine the overlapping moment and the lateral coordinates to obtain the four corner points of the self-vehicle point and the target.

[0188] In one embodiment, the acquisition module 10 is further used to calculate the position of the self-vehicle relative to the reference line at this time if the self-vehicle point and the corner point overlap in the lateral direction; calculate the longitudinal coordinates of the self-vehicle at the overlapping time according to the longitudinal speed of the self-vehicle, the longitudinal acceleration of the self-vehicle and the overlapping time; calculate the longitudinal coordinates of the target at the overlapping time according to the longitudinal distance of the target at the initial prediction time, the longitudinal speed of the target, the longitudinal acceleration of the target and the overlapping time; substitute the longitudinal coordinates of the self-vehicle and the longitudinal coordinates of the target into the cubic polynomial of the reference line to obtain the lateral distance of the self-vehicle relative to the reference line and the lateral distance of the target relative to the reference line; combine the overlapping time, the lateral distance of the self-vehicle relative to the reference line and the lateral distance of the target relative to the reference line to obtain the lateral overlapping point of the self-vehicle and the target; generate a minimum convex hull set according to the lateral overlapping point.

[0189] In one embodiment, the selection module 20 is further used to, if the list of nodes to be checked is empty, use the path planning starting point as the current node; or, if the list of nodes to be checked is not empty, select a node from the list of nodes to be checked; based on the trajectory information, generate a trajectory segment to be checked that passes through the node; if there is no intersection between the trajectory segment to be checked and the nodes in the preset node list, calculate the trajectory cost of the trajectory segment to be checked; repeat the above steps and use the node with the smallest trajectory cost as the current node.

[0190] In one embodiment, the maintenance module 30 is also used to select a node from the preset node list as an intermediate node; generate a first trajectory segment from the current node to the intermediate node and a second trajectory segment from the intermediate node to the path planning end point; if it is detected that there is no collision risk in the first trajectory segment and the intermediate node does not belong to the list of nodes to be checked, then update the trajectory information of the intermediate node and add the intermediate node to the list of nodes to be checked; or, if it is detected that there is no collision risk in the first trajectory segment and the trajectory cost of the first trajectory segment is less than the minimum trajectory cost of the intermediate node, then update the trajectory information of the intermediate node; repeat the above steps until the traversal of the preset node list is completed.

[0191] In one embodiment, the output module 40 is also used to obtain the start node and the end node of the trajectory segment to be generated; substitute the start node and the end node into a two-segment quintic polynomial to establish the constraint conditions of the trajectory segment; obtain the lateral acceleration change rate of the trajectory segment; establish a cost function based on the acceleration change rate; construct a cost function of the fusion constraint conditions; and calculate the trajectory costs of the start node and the end node based on the cost function of the fusion constraint conditions.

[0192] The present application provides an improved A-star smart car obstacle avoidance path search device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the improved A-star smart car obstacle avoidance path search method in the above-mentioned embodiment one.

[0193] Reference below Figure 6, which shows a schematic diagram of the structure of an improved A-star intelligent automobile obstacle avoidance path search device suitable for implementing the embodiment of the present application. The improved A-star intelligent automobile obstacle avoidance path search device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The improved A-star smart car obstacle avoidance path search device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0194] like Figure 6 As shown, the improved A-star intelligent car obstacle avoidance path search device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the improved A-star intelligent car obstacle avoidance path search device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the improved A-star intelligent automobile obstacle avoidance path search device to communicate wirelessly or wired with other devices to exchange data. Although the improved A-star intelligent automobile obstacle avoidance path search device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0195] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0196] The improved A-star intelligent car obstacle avoidance path search device provided by the present application adopts the improved A-star intelligent car obstacle avoidance path search method in the above embodiment, which can solve the technical problem of improving the A-star intelligent car obstacle avoidance path search. Compared with the prior art, the beneficial effects of the improved A-star intelligent car obstacle avoidance path search device provided by the present application are the same as the beneficial effects of the improved A-star intelligent car obstacle avoidance path search method provided by the above embodiment, and the other technical features in the improved A-star intelligent car obstacle avoidance path search device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0197] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0198] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0199] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the improved A-star smart car obstacle avoidance path search method in the above-mentioned embodiment.

[0200] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may 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 or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0201] The above-mentioned computer-readable storage medium may be included in the improved A-star intelligent car obstacle avoidance path search device; or it may exist independently without being assembled into the improved A-star intelligent car obstacle avoidance path search device.

[0202] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the improved A-star intelligent automobile obstacle avoidance path search device, the improved A-star intelligent automobile obstacle avoidance path search device: obtains a preset node list and a list of nodes to be checked, wherein the preset node list includes the path planning starting point, the obstacle overlapping point, and the nodes to be checked include the path nodes that have not been searched; calculates the trajectory cost of each of the nodes to be checked in turn, and selects the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory; based on the current node, traverses the preset node list, updates the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; if the current node is not the end point of the path planning, removes the current node from the list of nodes to be checked; if it is detected that the list of nodes to be checked is empty, queries the parent node from the end point of the path planning, and then queries the parent node of the parent node, and so on, until the path planning starting point is found, and a path is generated according to the queried nodes.

[0203] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0204] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0205] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0206] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned improved A-star smart car obstacle avoidance path search method, and can solve the technical problem of improving the A-star smart car obstacle avoidance path search. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the improved A-star smart car obstacle avoidance path search method provided by the above-mentioned embodiment, and will not be repeated here.

[0207] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the improved A-star smart car obstacle avoidance path search method as described above.

[0208] The computer program product provided by this application can solve the technical problem of improving the A-star smart car obstacle avoidance path search. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the improved A-star smart car obstacle avoidance path search method provided by the above embodiment, which will not be repeated here.

[0209] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An improved A-star intelligent car obstacle avoidance path search method, characterized in that: The method includes: Obtaining a preset node list and a list of nodes to be checked, wherein the preset node list includes the path planning starting point and the obstacle intersection point, and the nodes to be checked include the path nodes that have not been searched; Calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory; Based on the current node, traverse the preset node list, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; If the current node is not the end point of the path planning, removing the current node from the list of nodes to be checked; If it is detected that the list of nodes to be checked is empty, the parent node is queried starting from the end point of the path planning, and then the parent node of the parent node is queried, and so on, until the starting point of the path planning is found, and a path is generated according to the queried nodes.

2. The method according to claim 1, characterized in that The step of obtaining a preset node list includes: Based on the vehicle coordinate system, obtain vehicle information and target information, wherein the vehicle information includes the longitudinal position point coordinates, lateral position point coordinates, longitudinal speed, lateral speed, longitudinal acceleration, lateral acceleration and the length of the front and rear ends of the vehicle relative to the center of mass of the vehicle at the prediction time, and the target information includes the longitudinal distance, lateral distance, longitudinal acceleration of the target relative to the vehicle, longitudinal speed of the target relative to the vehicle, target longitudinal speed, target lateral speed, target longitudinal acceleration and target lateral acceleration of the target at the initial prediction time; Obtaining a vehicle point and four corner points of the target based on the vehicle information and the target information; Based on the vehicle coordinate system, a reference line is set, wherein the reference line is represented by a cubic polynomial; Based on the cubic polynomial representation of the ego vehicle, four corner points of the target and the reference line, a lateral overlap point between the ego vehicle and the target is obtained; Get the starting point of path planning; A preset node list is generated according to the overlapping point and the path planning starting point.

3. The method according to claim 2, characterized in that The obtaining of the vehicle point and four corner points of the target based on the vehicle information and the target information includes: Based on the longitudinal direction, according to the longitudinal acceleration of the target relative to the ego vehicle, the longitudinal speed of the target relative to the ego vehicle, and the longitudinal distance of the target at the initial prediction time, calculating the overlap time between the ego vehicle and the target; Calculating the lateral coordinate of the vehicle at the overlapping moment according to the lateral velocity of the vehicle, the lateral acceleration of the vehicle and the overlapping moment; Calculating the target lateral coordinate at the overlapping time according to the lateral distance of the target at the prediction initial time, the target lateral speed, the target lateral acceleration and the overlapping time; The overlapping moment and the lateral coordinate are combined to obtain the vehicle point and the four corner points of the target.

4. The method according to claim 2, characterized in that The step of obtaining the lateral overlapping point between the vehicle and the target based on the cubic polynomial representation of the vehicle, the four corner points of the target and the reference line includes: If the ego vehicle point and the corner point overlap in the horizontal direction, the position of the ego vehicle relative to the reference line is calculated; Calculating the longitudinal coordinate of the vehicle at the overlapping moment according to the longitudinal velocity of the vehicle, the longitudinal acceleration of the vehicle and the overlapping moment; Calculating the longitudinal coordinate of the target at the overlapping time according to the longitudinal distance of the target at the initial prediction time, the longitudinal speed of the target, the longitudinal acceleration of the target and the overlapping time; Substituting the longitudinal coordinate of the vehicle and the longitudinal coordinate of the target into the cubic polynomial of the reference line to obtain the lateral distance of the vehicle relative to the reference line and the lateral distance of the target relative to the reference line; Combining the overlap moment, the lateral distance of the ego vehicle relative to the reference line, and the lateral distance of the target relative to the reference line to obtain a lateral overlap point of the ego vehicle and the target; A minimum convex hull set is generated according to the lateral overlapping points.

5. The method according to claim 1, characterized in that The step of sequentially calculating the trajectory costs of the nodes to be checked and selecting the node to be checked with the smallest trajectory cost as the current node includes: If the list of nodes to be checked is empty, the starting point of the path planning is used as the current node; or, If the list of nodes to be checked is not empty, select a node from the list of nodes to be checked; Based on the trajectory information, generating a to-be-checked trajectory segment passing through the node; If there is no intersection between the trajectory segment to be checked and the nodes in the preset node list, calculating the trajectory cost of the trajectory segment to be checked; Repeat the above steps and take the node with the smallest trajectory cost as the current node.

6. The method according to claim 1, characterized in that The step of traversing the preset node list based on the current node and updating the node list to be checked and the trajectory information of each preset node includes: Select a node from the preset node list as an intermediate node; Generate a first trajectory segment from the current node to the intermediate node and a second trajectory segment from the intermediate node to a path planning end point; If it is detected that there is no collision risk in the first trajectory segment and the intermediate node does not belong to the list of nodes to be checked, updating the trajectory information of the intermediate node and adding the intermediate node to the list of nodes to be checked; or, If it is detected that there is no collision risk in the first trajectory segment and the trajectory cost of the first trajectory segment is less than the minimum trajectory cost of the intermediate node, updating the trajectory information of the intermediate node; Repeat the above steps until the traversal of the preset node list is completed.

7. The method according to any one of claims 1 to 6, characterized in that The calculation of the trajectory cost includes: Get the start node and end node of the trajectory segment to be generated; Substituting the start node and the end node into a two-segment quintic polynomial to establish a constraint condition for the trajectory segment; Obtaining a lateral acceleration change rate of the trajectory segment; Establishing a cost function based on the acceleration change rate; Construct a cost function that integrates constraints; Based on the cost function of the fusion constraint condition, the trajectory cost of the start node and the end node is calculated.

8. An improved A-star intelligent car obstacle avoidance path search device, characterized in that: The device comprises: An acquisition module, used to acquire a preset node list and a list of nodes to be checked, wherein the preset node list includes a path planning starting point and an obstacle intersection point, and the nodes to be checked include path nodes that have not been searched; A selection module, used for calculating the trajectory cost of each of the nodes to be checked in turn, and selecting the node to be checked with the smallest trajectory cost as the current node, wherein the trajectory cost is obtained based on the acceleration change rate of the trajectory; A maintenance module, configured to traverse the preset node list based on the current node, update the list of nodes to be checked and the trajectory information of each preset node, wherein the trajectory information includes the parent node of the node and the minimum trajectory cost; if the current node is not the end point of the path planning, remove the current node from the list of nodes to be checked; The output module is used to query the parent node from the path planning end point if it is detected that the list of nodes to be checked is empty, and then query the parent node of the parent node, and so on, until the path planning starting point is found, and generate a path according to the queried nodes.

9. A vehicle, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the improved A-star smart car obstacle avoidance path search method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the improved A-star intelligent car obstacle avoidance path search method as described in any one of claims 1 to 7 are implemented.

Images