Intelligent automobile obstacle avoidance path planning method and system

Abstract

The application provides a kind of intelligent automobile obstacle avoidance path planning method and system, method includes obtaining 5G-V2X position signal and determines the uncertainty of 5G-V2X position signal, according to the uncertainty of 5G-V2X position signal determines minimum safety distance;Position uncertainty is considered based on minimum safety distance and constructs obstacle avoidance planning map;Based on the obstacle avoidance planning map, a rapid collision detection strategy is designed;Design the destination-oriented guided sampling strategy, and the destination-oriented guided sampling strategy, random sampling strategy and end sampling strategy are fused to obtain a planning node;Based on the rapid collision detection strategy and the planning node, an obstacle avoidance path is determined.The present application can effectively solve the problems of 5G-V2X position signal uncertainty interference, blind search during obstacle avoidance planning, poor safety of planning results, etc.

Description

Technical Field

[0001] This invention belongs to the technical field of intelligent energy management and motion control, specifically relating to an intelligent vehicle obstacle avoidance path planning method and system. Background Technology

[0002] With the continuous advancement of automotive technologies and the maturation of the automotive industry chain, automobiles, as a convenient means of transportation, have gradually entered countless households, and global car ownership has experienced explosive growth in the past decade. While the increase in car ownership has improved people's quality of life, it has also brought about numerous social problems. For example, congested traffic has led to a continuous rise in traffic accident rates, and the pressure on road traffic safety is increasing daily.

[0003] To alleviate road traffic safety pressures and reduce traffic accident rates, technologies and products related to intelligent vehicles are constantly being developed. As a key technology for realizing intelligent vehicles, obstacle avoidance planning is responsible for generating paths that allow the vehicle to avoid obstacles in road traffic based on environmental perception information. When the intelligent vehicle travels along this path, it can maintain a safe distance from obstacles in road traffic and avoid collisions. However, environmental perception information is subject to uncertainty due to factors such as tree shade and fog interference, especially the uncertainty in obstacle location detection. Furthermore, the blind search characteristic of traditional planning methods can easily lead to planned paths that fail to avoid obstacles, hindering the rapid movement of intelligent vehicles and actually exacerbating traffic congestion.

[0004] Therefore, how to take into account the uncertainties of environmental perception and reduce the blind expansion of planned paths, and how to make them as close as possible to the destination that the vehicle wants to reach, are problems that urgently need to be solved by those skilled in the art. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an intelligent vehicle obstacle avoidance path planning method and system, which solves the technical problems in the prior art.

[0006] On the one hand, the present invention provides the following technical solution: an intelligent vehicle obstacle avoidance path planning method, comprising:

[0007] Acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals;

[0008] An obstacle avoidance planning map considering location uncertainty is constructed based on the minimum safe distance;

[0009] Design a rapid collision detection strategy based on the aforementioned obstacle avoidance planning map;

[0010] Design a destination-biased guided sampling strategy, and integrate the destination-biased guided sampling strategy, random sampling strategy, and endpoint sampling strategy to obtain the planned nodes;

[0011] The obstacle avoidance path is determined based on the fast collision detection strategy and the planning nodes.

[0012] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention can convert the uncertain information of 5G-V2X sensors into quantitative certain information. Based on the user-defined safety confidence level, it calculates the minimum safe distance that the intelligent vehicle should maintain from obstacles, thereby suppressing the interference of uncertain position signals. Then, a fast collision detection strategy is designed to quickly detect the effectiveness of planning nodes, improve the real-time performance of the overall algorithm, and thus improve the safety of planning. Finally, a destination-biased guided sampling strategy is designed to reduce blind search in planning, accelerate the planning algorithm to search for driving paths to the destination, improve the real-time performance of planning, and further improve the safety of planning.

[0013] Preferably, the step of acquiring the 5G-V2X location signal and determining the uncertainty of the 5G-V2X location signal, and determining the minimum safe distance based on the uncertainty of the 5G-V2X location signal includes:

[0014] The 5G-V2X location signal is acquired, and the acquired 5G-V2X location signal follows a normal distribution. Calculate obstacle position signals in 5G-V2X position signals neighborhood confidence level :

[0015] ;

[0016] In the formula, This is the obstacle location signal. For probability, For intelligent vehicle location signals;

[0017] Based on the confidence level Determine the distance judgment formula:

[0018] ;

[0019] In the formula, Set confidence levels for users;

[0020] Determine the smallest distance that satisfies the given distance judgment formula. To obtain the minimum safe distance .

[0021] Preferably, the step of constructing an obstacle avoidance planning map considering location uncertainty based on the minimum safe distance includes:

[0022] Plan the starting point based on the user-defined starting point. and the planned endpoint To depict the boundaries of a two-dimensional planar map;

[0023] Align the X-axis and Y-axis in the two-dimensional planar map with the X-axis and Y-axis defined by the positioning system;

[0024] Based on 5G-V2X location signals, the boundaries of obstacles are shifted outwards by a minimum safe distance. To obtain the confidence barrier;

[0025] The believed obstacles are projected onto the two-dimensional plane map to obtain an obstacle avoidance planning map.

[0026] Preferably, in the step of designing a fast collision detection strategy based on the obstacle avoidance planning map, the fast collision detection strategy is:

[0027] Calculate any node in the obstacle avoidance planning map The sum of the interior angles of the triangle constructed with all sides of the confidence obstacle , determine the interior angle sum Is it greater than 360°? , if the sum of the interior angles Greater than 360° Then determine the node No collision occurred with the believed obstacle, if the sum of the interior angles No more than 360° Then determine the node Collision with a believed obstacle, among which, Set a security threshold for the user; if the node If no collision occurs with any believed obstacles, then the node... Security, if node If a node collides with a certain believed obstacle, then... Unsafe, where the interior angles and... for:

[0028] ;

[0029] In the formula, It is the first confidence barrier The first corner point on the edge, It represents the total number of edges that are confidence obstacles. It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time The Euclidean length.

[0030] Preferably, in the step of designing a destination-biased guided sampling strategy, the destination-biased guided sampling strategy includes:

[0031] For the transition nodes in the obstacle avoidance planning map and transition nodes nearest node Construct a system that is biased towards the planning endpoint energy field Based on the energy field Determine the initial planning nodes :

[0032] ;

[0033] In the formula, , Representing points respectively Point of view ,point Point of view The vector.

[0034] Preferably, the step of fusing the destination-biased guided sampling strategy, the random sampling strategy, and the endpoint sampling strategy to obtain the planned nodes includes:

[0035] In each planned sampling, a random number in the range [0,1] is randomly generated. ,when At that time, a random sampling strategy is used to generate planning nodes. ;when At this time, a random sampling strategy is first used to generate transition nodes. Then, a destination-biased guided sampling strategy is adopted to generate planning nodes. ;when At that time, directly set the planned destination. As a planning node :

[0036] ;

[0037] In the formula, These represent the maximum and minimum boundaries on the X-axis of the obstacle avoidance planning map, respectively. These represent the maximum and minimum boundaries along the Y-axis of the obstacle avoidance planning map. , Representing points respectively Point of view ,point Point of view The vector, As a transition node, To and The nearest node, These are the first set sampling constant and the second set sampling constant, respectively.

[0038] Preferably, the step of determining the obstacle avoidance path based on the fast collision detection strategy and the planned nodes includes:

[0039] Determine the planning starting point based on the aforementioned fast collision detection strategy. and the planned endpoint Is it safe? If the starting point is planned... and the planned endpoint If it is unsafe, stop the planning and set up the planning marker. flag Marking it as 0 ends the planning process and returns an empty path; if the planning starting point is... and the planned endpoint For safety, set the current sampling count to [number]. And set the maximum number of samples. and will plan the starting point As the root node, it is stored in the planning tree. T middle;

[0040] If the current sampling count And planning signage flag If the value is 0, then let the current sampling count be... From the planning tree T Searching and planning nodes using the method of minimizing Euclidean distance The nearest node ,right Line segments at set intervals Perform equidistant dispersion to obtain a discrete node set. , ,in, This represents the number of nodes in the discrete node set. It is a rounding function. for Euclidean length of line segment;

[0041] If the current sampling count Planning signage flagIf the value is 0, the planning ends and an empty path is returned. If the current sampling count is 0... And planning signage flag If the value is not 0, the safety status of all nodes in the discrete node set is identified using a fast collision detection strategy. If there are unsafe nodes in the discrete node set, sampling continues. If there are no unsafe nodes in the discrete node set, the planning node is calculated. With the planned endpoint Euclidean distance between If Euclidean distance Then the planning nodes will be Store in planning tree T In the middle, the marker node For planning nodes The parent node continues sampling, if the Euclidean distance is... Then the destination will be planned. Store in planning tree T In the middle, mark the planning nodes. For planning nodes The parent node is used to backtrack from the planning tree. T Find the link planning starting point and the planned endpoint path Path, In order to obtain an obstacle avoidance path.

[0042] Secondly, the present invention provides the following technical solution: an intelligent vehicle obstacle avoidance path planning system, the system comprising:

[0043] The distance module is used to acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals;

[0044] The map module is used to construct an obstacle avoidance planning map that takes into account location uncertainties based on the minimum safe distance;

[0045] The strategy module is used to design a fast collision detection strategy based on the obstacle avoidance planning map;

[0046] The node module is used to design a destination-biased guided sampling strategy and to fuse the destination-biased guided sampling strategy, random sampling strategy and endpoint sampling strategy to obtain the planned nodes.

[0047] The path module is used to determine the obstacle avoidance path based on the fast collision detection strategy and the planning nodes.

[0048] Thirdly, the present invention provides the following technical solution: a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent vehicle obstacle avoidance path planning method as described above.

[0049] Fourthly, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the intelligent vehicle obstacle avoidance path planning method as described above. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A flowchart of the intelligent vehicle obstacle avoidance path planning method provided in Embodiment 1 of the present invention;

[0052] Figure 2 A schematic diagram of obstacle avoidance paths planned using traditional methods;

[0053] Figure 3 This is a schematic diagram of the obstacle avoidance path planned by the method of the present invention;

[0054] Figure 4 This is a structural block diagram of the intelligent vehicle obstacle avoidance path planning system provided in Embodiment 2 of the present invention;

[0055] Figure 5 This is a schematic diagram of the hardware structure of a computer provided for another embodiment of the present invention.

[0056] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Detailed Implementation

[0057] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain embodiments of the present invention, and should not be construed as limiting the present invention.

[0058] Example 1

[0059] In Embodiment 1 of the present invention, as Figure 1 As shown, an intelligent vehicle obstacle avoidance path planning method includes:

[0060] S1. Acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals;

[0061] Step S1 includes:

[0062] S11. Acquire 5G-V2X location signal, wherein the acquired 5G-V2X location signal follows a normal distribution. Calculate obstacle position signals in 5G-V2X position signals neighborhood confidence level :

[0063] ;

[0064] In the formula, This is the obstacle location signal. For probability, For intelligent vehicle location signals;

[0065] Specifically, for the right side of the above equation, it is as follows: Follows a standard normal distribution The probability of.

[0066] S12, Based on the confidence level Determine the distance judgment formula:

[0067] ;

[0068] In the formula, Set confidence levels for users.

[0069] S13. Determine the smallest distance that satisfies the distance judgment formula. To obtain the minimum safe distance .

[0070] S2. Construct an obstacle avoidance planning map that considers location uncertainty based on the minimum safe distance;

[0071] Step S2 includes:

[0072] S21. Plan the starting point based on the user-defined starting point. and the planned endpoint To depict the boundaries of a two-dimensional plane map.

[0073] S22. Align the X-axis and Y-axis in the two-dimensional planar map with the X-axis and Y-axis defined by the positioning system;

[0074] Specifically, the positioning system here is the BeiDou satellite positioning system.

[0075] S23. Based on the 5G-V2X location signal, shift the boundaries of all obstacles outwards by a minimum safe distance. In order to obtain the confidence barrier.

[0076] S24. Project the believed obstacle onto the two-dimensional plane map to obtain an obstacle avoidance planning map.

[0077] S3. Design a fast collision detection strategy based on the obstacle avoidance planning map;

[0078] The fast collision detection strategy is as follows:

[0079] Calculate any node in the obstacle avoidance planning map The sum of the interior angles of the triangle constructed with all sides of the confidence obstacle , determine the interior angle sum Is it greater than 360°? , if the sum of the interior angles Greater than 360° Then determine the node No collision occurred with the believed obstacle, if the sum of the interior angles No more than 360° Then determine the node Collision with a believed obstacle, among which, Set a security threshold for the user; if the node If no collision occurs with any believed obstacles, then the node... Security, if node If a node collides with a certain believed obstacle, then... Unsafe, where the interior angles and... for:

[0080] ;

[0081] In the formula, It is the first confidence barrier The first corner point on the edge, It represents the total number of edges that are confidence obstacles. It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time The Euclidean length.

[0082] S4. Design a destination-biased guided sampling strategy, and integrate the destination-biased guided sampling strategy, random sampling strategy and endpoint sampling strategy to obtain the planned nodes;

[0083] The destination-biased guided sampling strategy includes:

[0084] For the transition nodes in the obstacle avoidance planning map and transition nodes nearest node Construct a system that is biased towards the planning endpoint energy field Based on the energy field Determine the initial planning nodes :

[0085] ;

[0086] In the formula, , Representing points respectively Point of view ,point Point of view The vector.

[0087] Specifically, step S4 is as follows:

[0088] In each planned sampling, a random number in the range [0,1] is randomly generated. ,when At that time, a random sampling strategy is used to generate planning nodes. ;when At this time, a random sampling strategy is first used to generate transition nodes. Then, a destination-biased guided sampling strategy is adopted to generate planning nodes. ;when At that time, directly set the planned destination. As a planning node :

[0089] ;

[0090] In the formula, These represent the maximum and minimum boundaries on the X-axis of the obstacle avoidance planning map, respectively. These represent the maximum and minimum boundaries along the Y-axis of the obstacle avoidance planning map. , Representing points respectively Point of view ,point Point of view The vector, As a transition node, To and The nearest node, These are the first set sampling constant and the second set sampling constant, respectively.

[0091] Specifically, the above process is a multimodal sampling fusion process, in which different nodes are selected to determine strategies based on the range of random numbers.

[0092] S5. Determine the obstacle avoidance path based on the fast collision detection strategy and the planned nodes.

[0093] Step S5 includes:

[0094] S51. Determine the planning starting point based on the aforementioned fast collision detection strategy. and the planned endpoint Is it safe? If the starting point is planned... and the planned endpoint If it is unsafe, stop the planning and set up the planning marker. flag Marking it as 0 ends the planning process and returns an empty path; if the planning starting point is... and the planned endpoint For safety, set the current sampling count to [number]. And set the maximum number of samples. and will plan the starting point As the root node, it is stored in the planning tree. T middle;

[0095] S52, if the current sampling count And planning signage flag If the value is 0, then let the current sampling count be... From the planning tree T Searching and planning nodes using the method of minimizing Euclidean distance The nearest node ,right Line segments at set intervals Perform equal-distance dispersion to obtain a discrete node set. , ,in, This represents the number of nodes in the discrete node set. It is a rounding function. for Euclidean length of line segment;

[0096] S53, if the current sampling count Planning signage flag If the value is 0, the planning ends and an empty path is returned. If the current sampling count is 0... And planning signage flag If the value is not 0, the safety status of all nodes in the discrete node set is identified using a fast collision detection strategy. If there are unsafe nodes in the discrete node set, sampling continues. If there are no unsafe nodes in the discrete node set, the planning node is calculated. With the planned endpoint Euclidean distance between If Euclidean distance Then the planning nodes will be Store in planning tree T In the middle, the marker node For planning nodes The parent node continues sampling, if the Euclidean distance is... Then the destination will be planned. Store in planning tree T In the middle, mark the planning nodes. For planning nodes The parent node is used to backtrack from the planning tree. T Find the link planning starting point and the planned endpoint path Path, In order to obtain an obstacle avoidance path.

[0097] Specifically, to further verify the effectiveness of this application, an experimental case is provided below, setting up a 3-lane, 3-obstacle avoidance scenario as follows: Figure 2 and Figure 3 As shown, Figure 2 Obstacle avoidance paths planned using traditional methods Figure 3 The obstacle avoidance path planned by the method of this invention, from Figure 2 It can be seen that the traditional planning tree contains many nodes that are blindly searched, while from... Figure 3 It can be seen that the nodes in the planning tree of the method of the present invention are all biased towards the target point, and there are relatively few nodes. This indicates that the method of the present invention can significantly reduce the blind search during obstacle avoidance planning; at the same time, from Figure 2 and Figure 3 It can be seen that the obstacle avoidance path planned by the method of the present invention is significantly shorter than that of the traditional method. Data shows that it is about 5 meters shorter and involves less detours. In contrast, the traditional method involves continuously changing lanes from the slow lane to the middle lane, then changing lanes to the fast lane, and then changing lanes back to the middle lane. This indicates that the obstacle avoidance path planned by the method of the present invention is safer than that of the traditional method.

[0098] The intelligent vehicle obstacle avoidance path planning method provided in Embodiment 1 of this invention can convert the uncertain information from 5G-V2X sensors into quantitative certain information. Based on the user-defined safety confidence level, it calculates the minimum safe distance that the intelligent vehicle should maintain from obstacles, thereby suppressing the interference of uncertain position signals. Then, a fast collision detection strategy is designed to quickly detect the effectiveness of planning nodes, improving the real-time performance of the overall algorithm and thus enhancing the safety of the planning. Finally, a destination-biased guided sampling strategy is designed to reduce blind searching in the planning process, accelerate the planning algorithm to search for a driving path to the destination, improve the real-time performance of the planning, and further enhance the safety of the planning.

[0099] Example 2

[0100] like Figure 4 As shown, in Embodiment 2 of the present invention, an intelligent vehicle obstacle avoidance path planning system is provided, the system comprising:

[0101] Distance module 1 is used to acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals;

[0102] Map module 2 is used to construct an obstacle avoidance planning map that takes into account location uncertainty based on the minimum safe distance;

[0103] Strategy module 3 is used to design a fast collision detection strategy based on the obstacle avoidance planning map;

[0104] Node module 4 is used to design a destination-biased guided sampling strategy and to integrate the destination-biased guided sampling strategy, random sampling strategy and endpoint sampling strategy to obtain the planned node;

[0105] Path module 5 is used to determine an obstacle avoidance path based on the fast collision detection strategy and the planning nodes;

[0106] The distance module 1 includes:

[0107] The confidence submodule is used to acquire 5G-V2X location signals, wherein the acquired 5G-V2X location signals follow a normal distribution. Calculate obstacle position signals in 5G-V2X position signals neighborhood confidence level :

[0108] ;

[0109] In the formula, This is the obstacle location signal. For probability, For intelligent vehicle location signals;

[0110] The judgment submodule is used to determine the confidence level. Determine the distance judgment formula:

[0111] ;

[0112] In the formula, Set confidence levels for users;

[0113] The distance submodule is used to determine the smallest distance that satisfies the distance judgment formula. To obtain the minimum safe distance .

[0114] The map module 2 includes:

[0115] The map submodule is used to plan the starting point based on a user-defined starting point. and the planned endpoint To depict the boundaries of a two-dimensional planar map;

[0116] The overlap submodule is used to overlap the X-axis and Y-axis in the two-dimensional planar map with the X-axis and Y-axis defined by the positioning system.

[0117] The translation submodule is used to translate the boundaries of obstacles outward by a minimum safe distance based on the 5G-V2X position signal. To obtain the confidence barrier;

[0118] The projection submodule is used to project the believed obstacle onto the two-dimensional plane map to obtain an obstacle avoidance planning map.

[0119] The node module 4 is used for:

[0120] In each planned sampling, a random number in the range [0,1] is randomly generated. ,when At that time, a random sampling strategy is used to generate planning nodes. ;when At this time, a random sampling strategy is first used to generate transition nodes. Then, a destination-biased guided sampling strategy is adopted to generate planning nodes. ;when At that time, directly set the planned destination. As a planning node :

[0121] ;

[0122] In the formula, These represent the maximum and minimum boundaries on the X-axis of the obstacle avoidance planning map, respectively. These represent the maximum and minimum boundaries along the Y-axis of the obstacle avoidance planning map. , Representing points respectively Point of view ,point Point of view The vector, As a transition node, To and The nearest node, These are the first set sampling constant and the second set sampling constant, respectively.

[0123] The path module 5 includes:

[0124] The first planning submodule is used to determine the planning starting point based on the fast collision detection strategy. and the planned endpoint Is it safe? If the starting point is planned... and the planned endpoint If it is unsafe, stop the planning and set up the planning marker. flag Marking it as 0 ends the planning process and returns an empty path; if the planning starting point is... and the planned endpoint For safety, set the current sampling count to [number]. And set the maximum number of samples. and will plan the starting point As the root node, it is stored in the planning tree. T middle;

[0125] The second planning submodule is used to determine the current sampling count. And planning signage flag If the value is 0, then let the current sampling count be... From the planning tree T Searching and planning nodes using the method of minimizing Euclidean distance The nearest node ,right Line segments at set intervals Perform equidistant dispersion to obtain a discrete node set. , ,in, This represents the number of nodes in the discrete node set. It is a rounding function. for Euclidean length of line segment;

[0126] The third planning submodule is used to determine the current sampling count. Planning signage flag If the value is 0, the planning ends and an empty path is returned. If the current sampling count is 0... And planning signage flagIf the value is not 0, the safety status of all nodes in the discrete node set is identified using a fast collision detection strategy. If there are unsafe nodes in the discrete node set, sampling continues. If there are no unsafe nodes in the discrete node set, the planning node is calculated. With the planned endpoint Euclidean distance between If Euclidean distance Then the planning nodes will be Store in planning tree T In the middle, the marker node For planning nodes The parent node continues sampling, if the Euclidean distance is... Then the destination will be planned. Store in planning tree T In the middle, mark the planning nodes. For planning nodes The parent node is used to backtrack from the planning tree. T Find the link planning starting point and the planned endpoint path Path, In order to obtain an obstacle avoidance path.

[0127] In other embodiments of the present invention, the present invention provides the following technical solution: a computer, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, wherein the processor 101 executes the computer program to implement the intelligent vehicle obstacle avoidance path planning method as described above.

[0128] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of the present invention.

[0129] The memory 102 may include a large-capacity memory for data or instructions. For example, and not limitingly, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include removable or non-removable (or fixed) media. Where appropriate, the memory 102 may be internal or external to a data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random Access Memory (FPMDRAM), Extended Data Out Dynamic Random Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0130] The memory 102 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101.

[0131] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned intelligent vehicle obstacle avoidance path planning method.

[0132] In some embodiments, the computer may further include a communication interface 103 and a bus 100. For example, Figure 5 As shown, the processor 101, memory 102, and communication interface 103 are connected through bus 100 and complete communication with each other.

[0133] The communication interface 103 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of the present invention. The communication interface 103 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0134] Bus 100 includes hardware, software, or both, that couples components of a computer device together. Bus 100 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although specific buses are described and illustrated in the embodiments of the present invention, the present invention is contemplated by any suitable bus or interconnect.

[0135] The computer can execute the intelligent vehicle obstacle avoidance path planning method of the present invention based on the intelligent vehicle obstacle avoidance path planning system, thereby realizing intelligent vehicle obstacle avoidance path planning.

[0136] In some further embodiments of the present invention, in conjunction with the above-described intelligent vehicle obstacle avoidance path planning method, the present invention provides the following technical solution: a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the above-described intelligent vehicle obstacle avoidance path planning method.

[0137] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0138] More specific examples of readable media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0139] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0140] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A method for intelligent vehicle obstacle avoidance path planning, characterized in that, include: Acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals; An obstacle avoidance planning map considering location uncertainty is constructed based on the minimum safe distance; Design a rapid collision detection strategy based on the aforementioned obstacle avoidance planning map; Design a destination-biased guided sampling strategy, and integrate the destination-biased guided sampling strategy, random sampling strategy, and endpoint sampling strategy to obtain the planned nodes; The obstacle avoidance path is determined based on the fast collision detection strategy and the planning nodes.

2. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, The steps of acquiring 5G-V2X location signals and determining the uncertainty of the 5G-V2X location signals, and determining the minimum safe distance based on the uncertainty of the 5G-V2X location signals, include: The 5G-V2X location signal is acquired, and the acquired 5G-V2X location signal follows a normal distribution. Calculate obstacle position signals in 5G-V2X position signals neighborhood confidence level : ； In the formula, This is the obstacle location signal. For probability, For intelligent vehicle location signals; Based on the confidence level Determine the distance judgment formula: ； In the formula, Set confidence levels for users; Determine the smallest value that satisfies the distance judgment formula. To obtain the minimum safe distance .

3. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, The steps for constructing an obstacle avoidance planning map that considers location uncertainty based on the minimum safe distance include: Plan the starting point based on the user-defined starting point. and the planned endpoint To depict the boundaries of a two-dimensional planar map; Align the X-axis and Y-axis in the two-dimensional planar map with the X-axis and Y-axis defined by the positioning system; Based on 5G-V2X location signals, the boundaries of obstacles are shifted outwards by a minimum safe distance. To obtain the confidence barrier; The believed obstacles are projected onto the two-dimensional plane map to obtain an obstacle avoidance planning map.

4. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, In the step of designing a fast collision detection strategy based on the obstacle avoidance planning map, the fast collision detection strategy is as follows: Calculate any node in the obstacle avoidance planning map The sum of the interior angles of the triangle constructed with all sides of the confidence obstacle , determine the interior angle sum Is it greater than 360°? , if the sum of the interior angles Greater than 360° Then determine the node No collision occurred with the believed obstacle, if the sum of the interior angles No more than 360° Then determine the node Collision with a believed obstacle, among which, Set a security threshold for the user; if the node If no collision occurs with any believed obstacles, then the node... Security, if node If a node collides with a certain believed obstacle, then... Unsafe, where the interior angles and... for: ； In the formula, It is the first confidence barrier The first corner point on the edge, It represents the total number of edges that are confidence obstacles. It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time Euclidean length, It is a guide Time The Euclidean length.

5. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, In the step of designing a destination-biased guided sampling strategy, the destination-biased guided sampling strategy includes: For the transition nodes in the obstacle avoidance planning map and transition nodes nearest node Construct a system that is biased towards the planning endpoint energy field Based on the energy field Determine the initial planning nodes : ； In the formula, , Representing points respectively Point of view ,point Point of view The vector.

6. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, The step of fusing the destination-biased guided sampling strategy, the random sampling strategy, and the endpoint sampling strategy to obtain the planned nodes includes: In each planned sampling, a random number in the range [0,1] is randomly generated. ,when At that time, a random sampling strategy is used to generate planning nodes. ;when At this time, a random sampling strategy is first used to generate transition nodes. Then, a destination-biased guided sampling strategy is adopted to generate planning nodes. ;when At that time, directly set the planned destination. As a planning node : ； In the formula, These represent the maximum and minimum boundaries on the X-axis of the obstacle avoidance planning map, respectively. These represent the maximum and minimum boundaries along the Y-axis of the obstacle avoidance planning map. , Representing points respectively Point of view ,point Point of view The vector, As a transition node, To and The nearest node, These are the first set sampling constant and the second set sampling constant, respectively.

7. The intelligent vehicle obstacle avoidance path planning method according to claim 1, characterized in that, The step of determining the obstacle avoidance path based on the fast collision detection strategy and the planning node includes: Determine the planning starting point based on the aforementioned fast collision detection strategy. and the planned endpoint Is it safe? If the starting point is planned... and the planned endpoint If it is unsafe, stop the planning and set up the planning marker. flag Marking it as 0 ends the planning process and returns an empty path; if the planning starting point is... and the planned endpoint For safety, set the current sampling count to [number]. And set the maximum number of samples. and will plan the starting point As the root node, it is stored in the planning tree. T middle; If the current sampling count And planning signage flag If the value is 0, then let the current sampling count be... From the planning tree T Searching and planning nodes using the method of minimizing Euclidean distance The nearest node ,right Line segments at set intervals Perform equidistant dispersion to obtain a discrete node set. , ,in, This represents the number of nodes in the discrete node set. It is a rounding function. for Euclidean length of line segment; If the current sampling count Planning signage flag If the value is 0, the planning ends and an empty path is returned. If the current sampling count is 0... And planning signage flag If the value is not 0, the safety status of all nodes in the discrete node set is identified using a fast collision detection strategy. If there are unsafe nodes in the discrete node set, sampling continues. If there are no unsafe nodes in the discrete node set, the planning node is calculated. With the planned endpoint Euclidean distance between If Euclidean distance Then the planning nodes will be Store in planning tree T In the middle, the marker node For planning nodes The parent node continues sampling, if the Euclidean distance is... Then the destination will be planned. Store in planning tree T In the middle, mark the planning nodes. For planning nodes The parent node is used to backtrack from the planning tree. T Find the link planning starting point and the planned endpoint path Path, In order to obtain an obstacle avoidance path.

8. An intelligent vehicle obstacle avoidance path planning system, characterized in that, The system includes: The distance module is used to acquire 5G-V2X location signals and determine the uncertainty of the 5G-V2X location signals, and determine the minimum safe distance based on the uncertainty of the 5G-V2X location signals; The map module is used to construct an obstacle avoidance planning map that takes into account location uncertainties based on the minimum safe distance; The strategy module is used to design a fast collision detection strategy based on the obstacle avoidance planning map; The node module is used to design a destination-biased guided sampling strategy and to fuse the destination-biased guided sampling strategy, random sampling strategy and endpoint sampling strategy to obtain the planned nodes. The path module is used to determine the obstacle avoidance path based on the fast collision detection strategy and the planning nodes.

9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the intelligent vehicle obstacle avoidance path planning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the intelligent vehicle obstacle avoidance path planning method as described in any one of claims 1 to 7.

Images