Method and device for determining U-turn path of autonomous vehicle

Abstract

The invention discloses a method and a device for determining a U-turn path of an autonomous vehicle. The method comprises the following steps: generating a reference line of a planned path according to lane data provided by a preset map and a starting point and an ending point of the preset planned path; converting the reference line into a grid map capable of indicating a road occupation state, and determining a passable area and a starting point and an ending point of a turn-around road section based on the grid map; and performing path search in the passable area according to the starting point and the ending point of the U-turn road section to obtain a U-turn path, and performing vehicle adaptive navigation based on the U-turn path.

Description

Technical Field

[0001] The present invention relates to the field of planning and control technology for autonomous driving, and more specifically, to a method and device for determining a U-turn path for an autonomous driving vehicle. Background Art

[0002] Trajectory planning is an important research area in autonomous driving. The planning module needs to plan a safe and stable trajectory for the vehicle based on the received perception and map information.

[0003] The most common autonomous driving planning algorithm at present is the horizontal and vertical decoupled planning algorithm. Since the path planning of an autonomous driving vehicle requires the path of the vehicle and the corresponding vehicle motion state in the future, such as the vehicle heading angle, speed, etc., and has high real-time requirements, it is difficult to ensure computational efficiency by directly solving the trajectory in three-dimensional space. Therefore, compared with direct planning in three-dimensional space, a more common approach is to decouple the horizontal and vertical directions, and use the Frenet coordinate system to divide the path planning into a horizontal and vertical serial process, thereby reducing the complexity of the path planning problem.

[0004] The existing horizontal and vertical decoupled path planning framework needs to be optimized based on map information to generate a smooth reference line to transform the Cartesian coordinates into the Frenet coordinate system to achieve horizontal and vertical decoupled planning. However, in scenarios such as U-turns with large curvature, the generated reference line cannot guarantee that the kinematic constraints of the vehicle are met. Planning directly based on the reference line may lead to planning failure, the vehicle being unable to track the trajectory, or even collision. Therefore, horizontal and vertical decoupled path planning based on Frenet coordinates is not suitable for large curvature environments such as U-turns. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method and device for determining a U-turn path for an autonomous driving vehicle.

[0006] According to one aspect of the present invention, a method for determining a U-turn path of an autonomous driving vehicle is provided, comprising:

[0007] Generate a reference line of the planned path according to the lane data provided by the preset map and the starting point and end point of the preset planned path;

[0008] Convert the reference line into a grid map that can indicate the road occupancy status, and determine the start and end points of the passable area and the U-turn section based on the grid map; and

[0009] In the passable area, a path search is performed according to the starting point and end point of the U-turn section, the U-turn path is obtained, and the vehicle adaptive navigation is performed based on the U-turn path.

[0010] Optionally, generating a reference line of the planned path according to lane data provided by a preset map and a start point and an end point of a preset planned path includes:

[0011] Generate a preliminary drivable path based on the lane data provided by the preset map and the starting and ending points of the set planned path; and

[0012] The preliminary traversable path is optimized and solved by a quadratic programming algorithm to generate a reference line consisting of multiple discrete points of the planned path.

[0013] Optionally, the path search is performed based on an improved HybridA* search algorithm, and the improved HybridA* search algorithm includes: RS curve search and collision detection.

[0014] Optionally, the node cost calculation formula of the improved HybridA* search algorithm is:

[0015] f(n)=g(n)+h(n)

[0016] Among them, f(n) is the total cost from the initial state to the target state in the state space; g(n) is the cost from the initial state to the current state in the state space, and h(n) is the heuristic cost from the nth state in the state space to the target state.

[0017] Optionally, performing a path search according to the starting point and the end point of the U-turn section in the passable area to obtain the U-turn path includes:

[0018] In the improved HybridA* search algorithm, the collision-free RS curve from the current reference point in the passable area to the end point of the U-turn section is obtained in sequence through RS curve search starting from the starting point of the U-turn section;

[0019] A collision detection of the vehicle rectangular boundary sampling is performed on each reference point of the collision-free RS curve, and a U-turn path is obtained according to the detection result of the collision detection.

[0020] Optionally, the RS curve search includes an SLS curve search and a non-SLS curve search.

[0021] Optionally, in the improved HybridA* search algorithm, a collision-free RS curve from a current reference point in the passable area to an end point of the U-turn section is sequentially obtained from the starting point of the U-turn section through RS curve search, including:

[0022] In the improved HybridA* search algorithm, it is determined whether a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search;

[0023] If a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search, the collision-free SLS curve obtained through the SLS curve search is used as the collision-free RS curve;

[0024] If the SLS curve search cannot obtain a collision-free SLS curve from the current reference point to the end point of the U-turn section, then a non-SLS curve search is used to obtain a collision-free RS curve from the current reference point to the end point of the U-turn section, and the collision-free RS curve obtained by the non-SLS curve search is used as the collision-free RS curve.

[0025] Optionally, determining whether a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search includes:

[0026] Acquire line segments of various curvatures of the U-turn section including the current reference point through SLS curve search;

[0027] Connect line segments of various curvatures in descending order of curvature to the end points of the U-turn section to obtain multiple SLS curves, and determine whether there is an SLS curve among the multiple SLS curves that does not collide with the rectangular boundary of the vehicle. If so, determine that a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search; if not, determine that a collision-free SLS curve from the current reference point to the end point of the U-turn section cannot be obtained through the SLS curve search.

[0028] Optionally, if a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search, the collision-free SLS curve obtained through the SLS curve search is used as the collision-free RS curve, including:

[0029] Acquire line segments of various curvatures of the U-turn section including the current reference point through SLS curve search;

[0030] The line segments with various curvatures are connected to the end points of the U-turn section in descending order of curvature to obtain the SLS curve, and the first SLS curve detected without collision with the vehicle rectangular boundary is used as the collision-free RS curve.

[0031] Optionally, the collision detection based on the sampling of the rectangular boundary of the vehicle body is performed based on a preset number of sampling points on the lateral sideline and the longitudinal sideline of the vehicle.

[0032] According to another aspect of the present invention, a device for determining a U-turn path of an autonomous driving vehicle is provided, comprising:

[0033] A generation module, used to generate a reference line of the planned path according to the lane data provided by the preset map and the starting point and end point of the preset planned path;

[0034] a determination module, configured to convert the reference line into a grid map capable of indicating the road occupancy status, and determine the start and end points of the passable area and the U-turn section based on the grid map; and

[0035] The acquisition module is used to search for a path according to the starting point and the end point of the U-turn section in the passable area, obtain the U-turn path, and perform vehicle adaptive navigation based on the U-turn path.

[0036] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0037] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0038] Therefore, the present invention proposes a method for determining the U-turn path of an autonomous driving vehicle based on the improved hybridA* algorithm. Compared with the existing autonomous driving planning algorithm under frenet coordinates, the method proposed by the present invention can combine the information of the structural road to generate a smooth path that can meet the curvature constraint of the vehicle, and allows reversing to adjust its own posture in sections that cannot be passed in one go. At the same time, based on the information such as the curvature of the U-turn lane, an SLS curve is designed, which can find a curve that directly reaches the end point after each step of the hybrid A* search. Compared with calculating the RS curve, the SLS curve is calculated for only one case each time, which greatly reduces the solution time. In addition, a collision detection method for sampling the vehicle body boundary is designed, which improves the planning success rate in narrow spaces while reducing the calculation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0040] Figure 1 is a flow chart of a method for determining a U-turn path of an autonomous driving vehicle provided by an exemplary embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of the improved HybridA* search process provided by an exemplary embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of an SLS curve provided by an exemplary embodiment of the present invention;

[0043] Figure 4 It is a schematic diagram of collision detection for a vehicle body frame provided by an exemplary embodiment of the present invention;

[0044] Figure 5 is a schematic diagram of the structure of a device for determining a U-turn path of an autonomous driving vehicle provided by an exemplary embodiment of the present invention;

[0045] Figure 6 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0046] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0047] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0048] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0049] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0050] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0051] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0052] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0053] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0054] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0055] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0056] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0057] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0058] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0059] Exemplary Methods

[0060] Figure 1 FIG. 1 is a flow chart of a method for determining a U-turn path of an autonomous driving vehicle provided by an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the method 100 for determining a U-turn path of an autonomous driving vehicle includes the following steps:

[0061] Step 101 : Generate a reference line of the planned path according to lane data provided by a preset map and a start point and an end point of a preset planned path.

[0062] Specifically, there are vehicle U-turn routes during the autonomous driving path planning process. The reference line generation in the path planning of the present invention is based on the lane data provided by the high-precision map. After the navigation start and end points are set, a preliminary passable path is generated. Then, after further optimizing this passable path through the quadratic planning algorithm, a line segment composed of a series of discrete reference points is generated as a reference line. The reference line proposed in the present invention can simplify the path planning problem, and express road information intuitively and concisely, and includes information such as lane lines, intersections, and curvature. Therefore, the computational complexity of subsequent path search is reduced by generating reference lines, simplifying the path planning problem.

[0063] Step 102: convert the reference line into a grid map that can indicate the road occupancy status, and determine the start and end points of the passable area and the U-turn section based on the grid map.

[0064] Specifically, the reference line will cause the shape of the vehicle and obstacles to be distorted in the case of large curvature, and it cannot guarantee the generation of a path that satisfies the curvature constraints and collision constraints. Therefore, after generating the reference line, the present invention uses the first and last reference points of the vehicle turnaround in the path planning in the high-precision map as the starting point and end point of the improved HybridA* search, and converts the structured road information under the frenet coordinates of the high-precision map into an occupancy grid map (unit size is 0.1*0.1m) to obtain the passable area of ​​the improved HybridA* search. The passable area includes the road planned by the path and the data information within a predetermined range near the road. Therefore, the present invention solves the problem of shape distortion of the navigation vehicle and obstacles in the reference line through the generation of the passable area, and ensures that the shapes of the navigation vehicle and obstacles are clear.

[0065] Step 103 , performing a path search in the passable area according to the starting point and the end point of the U-turn section, obtaining a U-turn path, and performing vehicle adaptive navigation based on the U-turn path.

[0066] Specifically, the present application performs path search in the path planning process by using an improved HybridA* search algorithm, wherein:

[0067] 1) Improved Hybrid A* search: The difference between the Hybrid A* algorithm and the ordinary A* search algorithm is that the Hybrid A* algorithm generates child nodes based on the vehicle's kinematics to ensure that the generated path can satisfy the vehicle's dynamic constraints. This introduces the state quantity vehicle position θ, which is then converted into a search problem in three-dimensional space (x, y, θ). The search process of Hybrid A* is as follows: Figure 2 shown.

[0068] Similar to the A* algorithm, the Hybrid A* algorithm also calculates the node cost:

[0069] f(n)=g(n)+h(n)

[0070] Among them, f(n) is the total cost from the initial state to the target state; g(n) is the cost from the initial state to the current state in the state space, and h(n) is the heuristic cost from state n to the target state.

[0071] 2) RS curve search: After several searches in the improved Hybrid A* search, it will try to find a collision-free RS curve connecting the current point to the end point based on the maximum turning curvature of the vehicle to accelerate the path search. max It can be calculated based on vehicle kinematics. The maximum front wheel turning angle of the autonomous vehicle is δf max When the vehicle turns with the minimum turning radius ρ min Performing circular motion, the vehicle bicycle model can be obtained:

[0072]

[0073]

[0074] Where L is the wheelbase of the autonomous vehicle.

[0075] Furthermore, the RS curve is a curve that allows the vehicle to move in the opposite direction based on the Dubins curve. It can be proved that when the vehicle moves in the opposite direction with a fixed curvature, the shortest path G from the starting point S to the end point G must be one of the 48 RS curves. The set of RS curves can be expressed as follows:

[0076] CCC←{C|C|C,C|CC,CC|C,Cc u |C u C,C|C u C u |C}

[0077] CSC←{CSC,C|C π / 2 SC,CSC π / 2 |C,C|C π / 2 SC π / 2 |C}

[0078] Among them, the letter C represents an arc, including the left-turning arc L and the right-turning arc R; the letter S represents a straight line; the vertical line “|” represents forward and backward reversal, and the right subscript represents the corresponding arc length.

[0079] 3) SLS curve search: There are 48 forms of RS curves. If RS curves are used to search and determine collisions at every step, it will obviously consume a lot of time. Based on the geometric characteristics of the U-turn section and referring to the calculation method of RS curves, an SLS curve is designed to generate a path through the U-turn, such as Figure 3 As shown, the SLS curve is a special form of the RS curve. Each time the SLS curve is searched first and then other forms of RS curves are searched, the path search time can be reduced. Among them, "S" represents straight driving and "L" represents left turning. After each step of the improved Hybrid A* search, only one form of the SLS curve needs to be calculated, which can greatly improve the success rate of the improved Hybrid A* search. Therefore, in the process of generating the curve at each step, the curvature of the U-turn section obtained from the reference line is sampled at ±0.05, and three SLS curves with different curvatures (k-0.05, k, k+0.05) directly connected to the end point are tried, that is, according to the size of the curvature, it is connected to the end point from large to small, and the curvature line segment that is successfully connected for the first time is used as the collision-free curve of the U-turn path.

[0080] 4) Collision detection: Traditional collision detection methods include axis-aligned bounding box (AABB), oriented bounding box (OBB) and spherical bounding box. However, for vehicle U-turn scenarios, the shape of lane boundaries is often a smooth arc with large curvature, and it is easy to misjudge using conventional collision judgment methods. Therefore, for U-turn environments, the present invention develops a method of sampling the rectangular boundary of the vehicle body to judge collisions, such as Figure 4 As shown in the figure, the geometry of the vehicle body is expanded to maintain a safe distance from the curb. This can improve the judgment accuracy while reducing the collision judgment time. Specifically, 10 / 5 sampling points are sampled on the horizontal and vertical edges of the vehicle body respectively, and collision detection is first performed on the four corner points of the vehicle body, and then collision detection is performed on each sampling point on the boundary of the vehicle body separately. This method can accurately determine whether the autonomous driving vehicle collides with the road boundary in the U-turn section, while greatly reducing the probability of false detection and improving the running time efficiency.

[0081] Therefore, the present invention proposes a method for determining the U-turn path of an autonomous driving vehicle based on the improved hybridA* algorithm. Compared with the existing autonomous driving planning algorithm under frenet coordinates, the method proposed in the present invention can combine the information of the structural road to generate a smooth path that can meet the curvature constraint of the vehicle, and allows reversing to adjust its own posture in sections that cannot be passed in one go. At the same time, based on the information such as the curvature of the U-turn lane, an SLS curve is designed, which can find a curve that directly reaches the end point after each step of the hybrid A* search. Compared with calculating the RS curve, the SLS curve calculation only has one case each time, which greatly reduces the solution time. In addition, a collision detection method for sampling the vehicle body boundary is designed, which improves the planning success rate in narrow spaces while reducing the calculation time. Finally, it shows good passability in narrow U-turn sections.

[0082] Exemplary Devices

[0083] Figure 5 FIG. 1 is a schematic diagram of a structure of a device for determining a U-turn path of an autonomous driving vehicle provided by an exemplary embodiment of the present invention. Figure 5 As shown, the device 500 includes:

[0084] A generation module 510, for generating a reference line of the planned path according to lane data provided by a preset map and a start point and an end point of a preset planned path;

[0085] A determination module 520, configured to convert the reference line into a grid map capable of indicating the road occupancy status, and determine the start and end points of the passable area and the U-turn section based on the grid map;

[0086] The acquisition module 530 is used to perform a path search according to the starting point and the end point of the U-turn section in the passable area, obtain the U-turn path, and perform vehicle adaptive navigation based on the U-turn path.

[0087] Optionally, the generating module 510 includes:

[0088] A first generation submodule, for generating a preliminary passable path according to lane data provided by a preset map and a start point and an end point of a set planned path; and

[0089] The second generation submodule is used to optimize and solve the preliminary navigable path through a quadratic programming algorithm to generate a reference line composed of multiple discrete points of the planned path.

[0090] Optionally, the path search is performed based on an improved HybridA* search algorithm, and the improved HybridA* search algorithm includes: RS curve search and collision detection.

[0091] Optionally, the node cost calculation formula of the improved HybridA* search algorithm is:

[0092] f(n)=g(n)+h(n)

[0093] Among them, f(n) is the total cost from the initial state to the target state in the state space; g(n) is the cost from the initial state to the current state in the state space, and h(n) is the heuristic cost from the nth state in the state space to the target state.

[0094] Optionally, the acquisition module 530 includes:

[0095] A first acquisition submodule is used to sequentially acquire a collision-free RS curve from a current reference point in a passable area to an end point of the U-turn section through RS curve search starting from the starting point of the U-turn section in the improved HybridA* search algorithm;

[0096] The second acquisition submodule is used to perform collision detection of vehicle rectangular boundary sampling on each reference point of the collision-free RS curve, and acquire a U-turn path according to the detection result of the collision detection.

[0097] Optionally, the RS curve search includes an SLS curve search and a non-SLS curve search.

[0098] Optionally, the first acquisition submodule includes:

[0099] A determination unit, used to determine whether a collision-free SLS curve from a current reference point to an end point of the U-turn section can be obtained through an SLS curve search in the improved HybridA* search algorithm;

[0100] The first unit is used for, if a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search, using the collision-free SLS curve obtained through the SLS curve search as the collision-free RS curve;

[0101] The second unit is used for obtaining a collision-free RS curve from the current reference point to the end point of the U-turn section through a non-SLS curve search if a collision-free SLS curve from the current reference point to the end point of the U-turn section cannot be obtained through the SLS curve search, and the collision-free RS curve obtained through the non-SLS curve search is used as the collision-free RS curve.

[0102] Optionally, the determining unit includes:

[0103] A first acquisition subunit is used to acquire line segments of various curvatures of the U-turn section including the current reference point through SLS curve search;

[0104] The second acquisition sub-unit is used to connect the line segments of various curvatures in descending order of curvature to the end points of the U-turn section to obtain multiple SLS curves, and determine whether there is an SLS curve that does not collide with the rectangular boundary of the vehicle among the multiple SLS curves. If so, it is determined that a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search; if not, it is determined that a collision-free SLS curve from the current reference point to the end point of the U-turn section cannot be obtained through the SLS curve search.

[0105] Optionally, the first unit includes:

[0106] A third acquisition subunit is used to acquire line segments of various curvatures of the U-turn section including the current reference point through SLS curve search;

[0107] As a subunit, it is used to connect the end points of the U-turn section in descending order of curvature with line segments of various curvatures to obtain an SLS curve, and the first SLS curve detected without collision with the vehicle rectangular boundary is used as the collision-free RS curve.

[0108] Optionally, the collision detection based on the sampling of the rectangular boundary of the vehicle body is performed based on a preset number of sampling points on the lateral sideline and the longitudinal sideline of the vehicle.

[0109] Exemplary Electronic Devices

[0110] Figure 6 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 6 As shown, the electronic device 60 includes one or more processors 61 and a memory 62 .

[0111] The processor 61 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0112] The memory 62 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 61 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 63 and an output device 64, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0113] In addition, the input device 63 may also include, for example, a keyboard, a mouse, etc.

[0114] The output device 64 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0115] Of course, to simplify, Figure 6 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device may also include any other appropriate components.

[0116] Exemplary computer program products and computer-readable storage media

[0117] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0118] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0119] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0120] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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.

[0121] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0122] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0123] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0124] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0125] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0126] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for vehicle adaptive navigation based on path search, characterized in that: include: Generate a reference line of the planned path according to lane data provided by the preset map and the starting point and end point of the preset planned path; Converting the reference line into a grid map capable of indicating the road occupancy status, and determining the start and end points of the passable area and the U-turn section based on the grid map; as well as A path search is performed in the passable area according to the starting point and the end point of the U-turn section to obtain a U-turn path, and vehicle adaptive navigation is performed based on the U-turn path.

2. The method according to claim 1, characterized in that Generate a reference line of the planned path according to the lane data provided by the preset map and the starting point and the end point of the preset planned path, including: Generate a preliminary drivable path based on the lane data provided by the preset map and the starting and ending points of the set planned path; and The preliminary navigable path is optimized and solved by a quadratic programming algorithm to generate a reference line consisting of a plurality of discrete points of the planned path.

3. The method according to claim 1, characterized in that The path search is performed based on an improved HybridA* search algorithm, and the improved HybridA* search algorithm includes: RS curve search and collision detection.

4. The method according to claim 3, characterized in that The node cost calculation formula of the improved HybridA* search algorithm is: f(n)=g(n)+h(n) Among them, f(n) is the total cost from the initial state to the target state in the state space; g(n) is the cost from the initial state to the current state in the state space, and h(n) is the heuristic cost from the nth state in the state space to the target state.

5. The method according to claim 3, characterized in that: Performing a path search in the passable area according to the starting point and the end point of the U-turn section to obtain a U-turn path includes: In the improved HybridA* search algorithm, the collision-free RS curves from the current reference point in the passable area to the end point of the U-turn section are sequentially obtained from the starting point of the U-turn section through the RS curve search; A collision detection of vehicle rectangular boundary sampling is performed on each reference point of the collision-free RS curve, and the U-turn path is obtained according to the detection result of the collision detection.

6. The method according to claim 5, characterized in that The RS curve search includes an SLS curve search and a non-SLS curve search.

7. The method according to claim 6, characterized in that In the improved HybridA* search algorithm, the collision-free RS curves from the current reference point in the passable area to the end point of the U-turn section are sequentially obtained from the starting point of the U-turn section through the RS curve search, including: In the improved HybridA* search algorithm, determining whether a collision-free SLS curve from a current reference point to an end point of the U-turn section can be obtained through the SLS curve search; If a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search, the collision-free SLS curve obtained through the SLS curve search is used as the collision-free RS curve; If the SLS curve search cannot obtain a collision-free SLS curve from the current reference point to the end point of the U-turn section, then the non-SLS curve search is used to obtain the collision-free RS curve from the current reference point to the end point of the U-turn section, and the collision-free RS curve obtained by the non-SLS curve search is used as the collision-free RS curve.

8. The method according to claim 7, characterized in that Determining whether a collision-free SLS curve from a current reference point to an end point of the U-turn section can be obtained through the SLS curve search includes: Acquire line segments of various curvatures of the U-turn section including the current reference point through the SLS curve search; Connect line segments of various curvatures in descending order of curvature to the end points of the U-turn section to obtain multiple SLS curves, and determine whether there is an SLS curve that does not collide with the rectangular boundary of the vehicle among the multiple SLS curves. If so, determine that a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search; if not, determine that a collision-free SLS curve from the current reference point to the end point of the U-turn section cannot be obtained through the SLS curve search.

9. The method according to claim 7, characterized in that: If a collision-free SLS curve from the current reference point to the end point of the U-turn section can be obtained through the SLS curve search, the collision-free SLS curve obtained through the SLS curve search is used as the collision-free RS curve, including: Acquire line segments of various curvatures of the U-turn section including the current reference point through the SLS curve search; The line segments of various curvatures are sequentially connected to the end points of the U-turn section in descending order of curvature to obtain an SLS curve, and the first SLS curve detected that has no collision with the rectangular boundary of the vehicle is used as the collision-free RS curve.

10. The method according to claim 5, characterized in that The collision detection based on the rectangular boundary sampling of the vehicle body is performed based on a preset number of sampling points on the lateral sideline and the longitudinal sideline of the vehicle.

11. A device for determining a U-turn path of an autonomous driving vehicle, characterized in that: include: A generation module, used to generate a reference line of the planned path according to lane data provided by a preset map and a start point and an end point of a preset planned path; A determination module, configured to convert the reference line into a grid map capable of indicating the road occupancy status, and determine the start and end points of the passable area and the U-turn section based on the grid map; as well as The acquisition module is used to perform a path search according to the starting point and the end point of the U-turn section in the passable area, acquire the U-turn path, and perform vehicle adaptive navigation based on the U-turn path.

12. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 10.

13. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-10.

Images