Path planning method and device for automatic driving system, equipment and medium

Abstract

The invention relates to a path planning method, device and equipment for an automatic driving system and a medium, and relates to the technical field of automatic driving, and the method comprises the steps: determining boundary points and pose points through a laser radar; determining a global path according to the boundary points; determining a local path according to the pose point; and obtaining a driving path according to the local path and the global path, wherein the priority of the local path is greater than that of the global path. The method has excellent real-time monitoring performance, and can better adapt to transportation scenes with complex transportation road conditions and multiple changes in mining areas.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a path planning method, device, equipment and medium for an autonomous driving system. Background Art

[0002] Autonomous driving vehicles avoid obstacles through path planning. Traditional route planning methods include A* algorithm, Dijkstra method, random roadmap (PRM) algorithm, rapidly expanding random tree (RRT) algorithm and the latest intelligent bionic path planning method.

[0003] The transportation road conditions in mining areas are complex, prone to false detection and missed detection, and the detection accuracy needs to be improved. Multi-sensor data fusion will increase the amount of calculation, making the algorithm time complex and the operating efficiency low, resulting in poor real-time operation of the mine truck perception system. The above route planning method cannot meet the transportation road conditions in mining areas. Summary of the invention

[0004] The present invention provides a path planning method for an automatic driving system to solve the problem that traditional route planning methods cannot meet the transportation road conditions in mining areas.

[0005] In a first aspect, the present invention provides a path planning method for an autonomous driving system, the method comprising: Determine boundary points and pose points through LiDAR; determining a global path according to the boundary points; Determine a local path according to the pose points; A driving route is determined according to the local route and the global route, and the priority of the local route is greater than the priority of the global route.

[0006] In a second aspect, the present invention provides a path planning device for an automatic driving system, comprising: A first determination unit, used to determine boundary points and pose points by laser radar; A second determining unit, configured to determine a global path according to the boundary points; A third determining unit, configured to determine a local path according to the pose points; The fourth determining unit is used to determine a driving path according to the local path and the global path, and the priority of the local path is greater than the priority of the global path.

[0007] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the path planning method for an autonomous driving system described in any one of the embodiments of the first aspect when executing the program stored in the memory.

[0008] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method for an autonomous driving system as described in any embodiment of the first aspect are implemented.

[0009] The above technical solution provided by the embodiment of the present invention has the following advantages compared with the prior art: The local path is used to adjust the vehicle's steering and slow down its movement, effectively avoiding the vehicle from becoming stuck due to the close distance between the walls or obstacles on both sides. It has excellent real-time monitoring capabilities and can better adapt to the complex and changing transportation scenarios in mining areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0011] In order to more clearly illustrate the embodiments of the present invention 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.

[0012] Figure 1 A schematic diagram of a flow chart of a path planning method for an autonomous driving system provided by an embodiment of the present invention; Figure 2 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention; Figure 3 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention; Figure 4 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of a path planning device for an automatic driving system provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention; Figure 7 An example diagram of the relationship between radar rays and curb height provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] Example 1 Figure 1 The present invention provides a flow chart of a path planning method for an autonomous driving system. The present invention provides a path planning method for an autonomous driving system. Specifically, see Figure 1 , the path planning method for the autonomous driving system includes the following steps S101-S104.

[0015] S101, determine boundary points and pose points through laser radar.

[0016] In specific implementation, when the laser beam emitted by the LiDAR hits the ground, a point cloud is generated at a circle. The distances from these point clouds to the LiDAR on the same circle are almost the same. The LiDAR identifies the height difference of the curb and uses the point cloud with the height difference as the boundary point. The LiDAR identifies the outline of the vehicle and uses the outer outline of the vehicle as the pose point.

[0017] In one embodiment, see Figure 2 , Figure 2 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention. The above step S101 includes steps S201-S203: S201, obtaining point cloud features of the road surface and contour features of the vehicle through a laser radar.

[0018] In the specific implementation, the point cloud features of the road surface are obtained through laser radar, and the point cloud features of the road surface are segmented using a grid unit-based method. The height difference of continuous compartments of the point cloud features is compared to determine the ground height, supplemented by consistency check and median filtering to complete the segmentation of flat terrain and retain the road surface contour. The laser radar emits light to the surface of the vehicle, and the vehicle reflects the light to obtain the vehicle's contour features.

[0019] S202: Determine the boundary point according to the point cloud feature.

[0020] In specific implementations, the ground height is determined based on the height difference between continuous intervals of point cloud features. For example, when the ground outside the road edge is lower than the road surface, the outermost point cloud features in the continuous point cloud features can be determined as boundary points. Another example is when the ground outside the road edge is higher than the road surface, the higher the bulge on the edge of the road, the smaller the distance from the corresponding point cloud feature to the laser radar, and the higher the bulge height, the larger the reflection angle. When there are multiple point cloud features with a smaller distance to the laser radar at the same time, it can be determined that these point cloud features are located on the raised curb.

[0021] In one embodiment, see Figure 3 , Figure 3 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention. The above step S202 includes steps S301-S303: S301, obtaining point cloud features with a reflection angle greater than a preset angle threshold as curb points; In a specific implementation, when the ground outside the edge of the road surface is higher than the road surface, the higher the height of the protrusion, the larger the reflection angle. By presetting the point cloud features with a reflection angle greater than a preset angle threshold as the curb point, the curb that is higher than the road surface can be quickly identified.

[0022] S302, obtaining vector information of the roadside point by using the laser radar; In a specific implementation, the point where the laser radar is projected to the ground coordinates is defined as the center point O, and the vector information of the curb point includes the distance from the curb point to the laser radar and the direction from the laser radar to the curb point.

[0023] S303: Determine whether the roadside points are continuous according to the vector information, and use the continuous roadside points as the boundary points.

[0024] In the specific implementation, Figure 7 , Figure 7 This is an example diagram of the relationship between the radar ray and the curb height provided in an embodiment of the present invention. In the laser radar point cloud, three adjacent points A, B, and C are selected on a circle with the same radius, and d is defined. OA ,d OB ,d OC They represent the distances between the three adjacent points and the center point O. Taking point B on the curb as the research object, the tangential neighborhood radius ratio is constructed to quantify the sudden change of the curb point. B The characteristic calculation formula is: , according to this point R B Features can determine the jump point, for example: R B The larger the value, the higher the jump degree, that is, the continuous points have a larger mutation, which can be judged that point B is on the curb, R B The smaller the value, the lower the jump degree, that is, the continuous points have smaller mutations, which can determine that point B is not on the curb.

[0025] In one embodiment, see Figure 4 , Figure 4 A schematic diagram of a sub-process of a path planning method for an autonomous driving system provided by an embodiment of the present invention. The above step S303 includes steps S401-S404: S401, selecting a point along the way as a target point.

[0026] In a specific implementation, the selected roadside point is recorded as a target point, and the target point is used to execute subsequent steps S402-S404.

[0027] S402, obtaining neighboring points of the target point by using a KD-Tree algorithm.

[0028] In a specific implementation, kd-tree is short for k-dimensional tree, which is a data structure for space partitioning and is often used for searches in high-dimensional space, such as range search and nearest neighbor search. In this embodiment, the KD-Tree algorithm is used to search for roadside points of the target point's neighbors, and the roadside points of the target point's neighbors are recorded as neighboring points. It should be noted that the number of roadside points of the target point's neighbors can be multiple.

[0029] S403: Determine a tangential distance according to the vector information of the target point and the vector information of the neighboring points, and judge whether the tangential distance is less than a preset second distance threshold.

[0030] In a specific implementation, it is determined in turn whether the distance from the target point to the neighboring point is less than a set second distance threshold.

[0031] S404, if yes, cluster the neighboring points into a point set, the point set includes the boundary point, select the next path point of the target point as a new target point, and execute the step of obtaining the neighboring points of the target point by using the KD-Tree algorithm.

[0032] In a specific implementation, the neighboring points and roadside points other than the target point are taken as new target points, and steps S402-S403 are repeatedly executed until no neighboring points are detected, or until steps S402-S403 are executed for all roadside points.

[0033] If not, it is determined that the roadside points are discontinuous.

[0034] In a specific implementation, discontinuous roadside points are likely to be misdetected foreign objects.

[0035] S203, determining a circular ring according to the contour feature, where the circular ring is a collection of the pose points.

[0036] In the specific implementation, a point on the contour feature farthest from the laser radar is selected, the distance from the point to the laser radar is used as the radius, and the point O projected by the laser radar to the ground is used as the center of the circle to obtain a ring, which is a collection of posture points.

[0037] S102: Determine a global path according to the boundary points.

[0038] In a specific implementation, the boundary points are connected to obtain a boundary line. In one embodiment, when the number of boundary lines is one, the global path is on one side of the boundary line. For example, the boundary point is on the left side of the vehicle. The boundary points are connected to obtain a boundary line, and the global path is on the right side of the boundary line.

[0039] In one embodiment, the above step S102 includes the steps of: fitting the boundary points based on the least squares method to obtain a first roadside boundary line and a second roadside boundary line; and the global path is between the first roadside boundary line and the second roadside boundary line.

[0040] In a specific implementation, the least square method is used to fit the line segment. In this embodiment, the boundary points are fitted by the least square method, and the boundary points on the left and right sides of the vehicle are respectively fitted to obtain the first roadside boundary line and the second roadside boundary line. The boundary points are fitted by the least square method to determine the road edge. The global path is between the first roadside boundary line and the second roadside boundary line, so that the vehicle can run better along the global route.

[0041] S103: Determine a local path according to the position and posture points.

[0042] In a specific implementation, the pose points are used to indicate the length / width of the vehicle, and the width of the local path is smaller than the global path.

[0043] In one embodiment, the above step S103 includes the steps of: determining whether the distance from the posture point to the boundary line of the global path is less than a preset first distance threshold; if so, determining a turning path according to a speed constraint relationship, and the local path includes the turning path.

[0044] In a specific implementation, whether the distance from the posture point to the boundary line of the global path is less than a preset first distance threshold is used to determine whether the surrounding obstacles appear within the relative collision range of the vehicle when the vehicle automatically drives in the direction of the global path. If the distance from the posture point to the boundary line of the global path is less than the preset first distance threshold, it is determined that the driving vehicle and the obstacle will collide in the future. The speed constraint relationship includes an angular velocity relationship and a linear velocity relationship. In one embodiment, the linear velocity relationship is , the angular velocity relationship is The method of slowing down the vehicle when it comes into contact with the collision range and moving forward after the vehicle leaves the relative collision distance can achieve obstacle avoidance. The path in which the vehicle slows down and turns to avoid obstacles is a local path.

[0045] In one embodiment, the above step S103 also includes the steps of: determining a position constraint relationship based on the global path and the pose points; determining a TEB hypergraph based on the TEB algorithm and the position constraint relationship; determining a shortest path based on the TEB hypergraph, and the local path includes the shortest path.

[0046] In specific implementation, the TEB algorithm can effectively help the vehicle avoid deviating from the known global path when turning, thereby improving the vehicle's driving stability. When the distance between the vehicle and the walls or obstacles on both sides is too close, the TEB algorithm may cause the vehicle to fall into a frozen state, which seriously affects the vehicle's driving stability. The optimized TEB hypergraph is obtained by adding the position constraint relationship between the pose points and the global path. Considering the restrictions on the path endpoints between different poses, a shortest path is found to enable the vehicle to run better along the global route, effectively avoiding the vehicle from being frozen due to the close distance between the walls or obstacles on both sides.

[0047] S104, determining a driving path according to the local path and the global path, wherein the priority of the local path is greater than the priority of the global path.

[0048] In specific implementations, the local path is used to adjust the vehicle's steering and slow down its movement to achieve correction of the global path. The global path is used to indicate the approximate direction to prevent the vehicle from deviating.

[0049] The embodiments of the present invention can achieve the following advantages: The local path is used to adjust the vehicle's steering and slow down its movement, effectively avoiding the vehicle from becoming stuck due to the close distance between the walls or obstacles on both sides. It has excellent real-time monitoring capabilities and can better adapt to the complex and changing transportation scenarios in mining areas.

[0050] See also Figure 5 An embodiment of the present invention further provides a path planning device 400 for an autonomous driving system, which includes a first determination unit 401 , a second determination unit 402 , a third determination unit 403 and a fourth determination unit 404 .

[0051] The first determination unit 401 is used to determine boundary points and posture points through laser radar.

[0052] In one embodiment, the determining of boundary points and pose points by laser radar includes: Obtain point cloud features of the road surface and contour features of the vehicle through LiDAR; Determine the boundary point according to the point cloud feature; A circular ring is determined according to the contour feature, where the circular ring is a collection of the pose points.

[0053] In one embodiment, determining the boundary point according to the point cloud feature includes: Obtaining point cloud features with reflection angles greater than a preset angle threshold as roadside points; Acquire vector information of the roadside point by using the laser radar; Whether the roadside points are continuous is determined according to the vector information, and the continuous roadside points are used as the boundary points.

[0054] In one embodiment, judging whether the roadside points are continuous according to the vector information and taking the continuous roadside points as the boundary points includes: Select a point along the way as the target point; Obtaining neighboring points of the target point by using a KD-Tree algorithm; Determine a tangential distance according to the vector information of the target point and the vector information of the neighboring point, and judge whether the tangential distance is less than a preset second distance threshold; If so, cluster the neighboring points into a point set, the point set includes the boundary point, select the next path point of the target point as a new target point, and execute the step of obtaining the neighboring points of the target point by using the KD-Tree algorithm.

[0055] The second determining unit 402 is used to determine the global path according to the boundary point.

[0056] In one embodiment, determining the global path according to the boundary points includes: Fitting the boundary points based on the least square method to obtain a first roadside boundary line and a second roadside boundary line; The global path is between the first roadside boundary line and the second roadside boundary line.

[0057] The third determining unit 403 is used to determine a local path according to the pose points.

[0058] The determining of the local path according to the posture points comprises: Determine whether the distance from the pose point to the boundary line of the global path is less than a preset first distance threshold; If so, a turning path is determined according to the speed constraint relationship, and the local path includes the turning path.

[0059] The fourth determining unit 404 is used to determine a driving path according to the local path and the global path, and the priority of the local path is greater than the priority of the global path.

[0060] In one embodiment, determining the local path according to the pose points further includes: Determine a position constraint relationship according to the global path and the pose points; Determine a TEB hypergraph according to the TEB algorithm and the position constraint relationship; A shortest path is determined according to the TEB hypergraph, and the local path includes the shortest path.

[0061] like Figure 6 As shown, Figure 6 5 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0062] The computer device 500 includes a processor 502 , a memory, and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0063] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, the processor 502 may execute a path planning method for an autonomous driving system.

[0064] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0065] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a path planning method for an automatic driving system.

[0066] The network interface 505 is used to communicate with other devices over the network. Those skilled in the art will appreciate that the above structure is only a block diagram of a portion of the structure related to the present application solution, and does not constitute a limitation on the computer device 500 to which the present application solution is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0067] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0068] It is understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0069] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program.

[0070] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes. The computer-readable storage medium can be non-volatile or volatile.

[0071] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0072] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0073] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0074] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0077] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A path planning method for an automatic driving system, characterized in that: The method comprises: Determine boundary points and pose points through LiDAR; determining a global path according to the boundary points; Determine a local path according to the pose points; A driving route is determined according to the local route and the global route, and the priority of the local route is greater than the priority of the global route.

2. The method according to claim 1, characterized in that The step of determining the boundary points and the position points by using a laser radar includes: Obtain point cloud features of the road surface and contour features of the vehicle through LiDAR; Determine the boundary point according to the point cloud feature; A circular ring is determined according to the contour feature, where the circular ring is a collection of the pose points.

3. The method according to claim 2, characterized in that Determining the boundary point according to the point cloud feature includes: Obtaining point cloud features with reflection angles greater than a preset angle threshold as roadside points; Acquire vector information of the roadside point by using the laser radar; Whether the roadside points are continuous is determined according to the vector information, and the continuous roadside points are used as the boundary points.

4. The method according to claim 3, characterized in that The step of judging whether the roadside points are continuous according to the vector information and taking the continuous roadside points as the boundary points comprises: Select a point along the way as the target point; Obtaining neighboring points of the target point by using a KD-Tree algorithm; Determine a tangential distance according to the vector information of the target point and the vector information of the neighboring point, and judge whether the tangential distance is less than a preset second distance threshold; If so, cluster the neighboring points into a point set, the point set includes the boundary point, select the next path point of the target point as the new target point, and execute the step of obtaining the neighboring points of the target point by using the KD-Tree algorithm.

5. The method according to claim 1, characterized in that The determining of the global path according to the boundary points comprises: Fitting the boundary points based on the least square method to obtain a first roadside boundary line and a second roadside boundary line; The global path is between the first roadside boundary line and the second roadside boundary line.

6. The method according to claim 1, characterized in that The determining of the local path according to the posture points comprises: Determine whether the distance from the pose point to the boundary line of the global path is less than a preset first distance threshold; If so, a turning path is determined according to the speed constraint relationship, and the local path includes the turning path.

7. The method according to claim 1, characterized in that The determining of the local path according to the posture points further includes: Determine a position constraint relationship according to the global path and the pose points; Determine a TEB hypergraph according to the TEB algorithm and the position constraint relationship; A shortest path is determined according to the TEB hypergraph, and the local path includes the shortest path.

8. A path planning device for an automatic driving system, characterized in that: include: A first determination unit, used to determine boundary points and pose points by using a laser radar; A second determining unit, configured to determine a global path according to the boundary points; A third determining unit, configured to determine a local path according to the pose points; The fourth determining unit is used to determine a driving path according to the local path and the global path, and the priority of the local path is greater than the priority of the global path.

9. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the steps of the method described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images