Unmanned vehicle obstacle avoidance method and system

Abstract

The invention discloses an unmanned vehicle obstacle avoidance method and system, and the method comprises the steps: determining a current tracking target position based on a tracking path according to the driving information of an unmanned vehicle, segmenting a prior static map based on the driving information and the current tracking target position if an obstacle exists, and obtaining sub-maps, the method comprises the following steps: acquiring a sub-map, mapping an obstacle into the sub-map to obtain an obstacle distance information map, performing path planning by adopting a mixed A star path planning method based on the obstacle distance information map to obtain an obstacle avoidance path, and performing subsequent path planning in the range of the sub-map when the obstacle is detected, thereby greatly improving the efficiency of path planning. According to the invention, a proper path can be more quickly planned for the vehicle, and the obstacle avoidance path can be flexibly planned according to the specific position and distance information of the obstacle, so that the vehicle can better adapt to a complex and changeable driving environment, and the real-time performance of obstacle avoidance of the unmanned vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned driving technology, and in particular to an unmanned vehicle obstacle avoidance method and system. Background Art

[0002] Currently, autonomous vehicles can follow a pre-set tracking path. This tracking path is typically collected in advance or planned directly on the vehicle monitoring map interface of the command and control platform with a mouse click, and then transmitted to the autonomous vehicle. During the actual tracking process, obstacles may appear on the tracking path due to environmental changes, necessitating an obstacle avoidance algorithm to ensure the vehicle can circumvent them and continue tracking. Existing path planning algorithms are primarily global path planning adapted to static maps, and thus cannot guarantee real-time performance. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and system for unmanned vehicle obstacle avoidance, which can improve the real-time performance of unmanned vehicle obstacle avoidance.

[0004] In order to solve the above technical problems, a technical solution adopted by the present invention is: A method for avoiding obstacles for an unmanned vehicle, comprising the steps of: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

[0005] In order to solve the above technical problems, another technical solution adopted by the present invention is: An unmanned vehicle obstacle avoidance system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

[0006] The beneficial effects of the present invention are: based on the tracking path, the current tracking target position is determined according to the driving information of the unmanned vehicle. If there is an obstacle in front of the unmanned vehicle, the prior static map is segmented based on the driving information and the current tracking target position to obtain a sub-map, and the obstacle is mapped to the sub-map to obtain an obstacle distance information map. Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path. When the unmanned vehicle detects an obstacle, the prior static map is segmented to obtain a sub-map, and subsequent path planning is performed within the sub-map range, which greatly improves the efficiency of path planning and can plan a suitable path for the vehicle more quickly. Based on the obstacle distance information map, a hybrid A-star path planning method is used for path planning, which can flexibly plan the obstacle avoidance path according to the specific position and distance information of the obstacle, so that the vehicle can better adapt to the complex and changeable driving environment, and can respond to sudden obstacles in time, thereby improving the real-time performance of the unmanned vehicle in avoiding obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a flowchart of the steps of a method for avoiding obstacles for an unmanned vehicle according to an embodiment of the present invention; Figure 2 This is a schematic structural diagram of an obstacle avoidance system for an unmanned vehicle according to an embodiment of the present invention; Figure 3 A schematic diagram of sub-map segmentation in an obstacle avoidance method for an unmanned vehicle according to an embodiment of the present invention; Figure 4 This is a flowchart of obstacle avoidance planning in an obstacle avoidance method for an unmanned vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0008] To illustrate the technical content, achieved objectives and effects of the present invention in detail, the following description is given in conjunction with the embodiments and accompanying drawings.

[0009] Please refer to Figure 1 , a method for unmanned vehicle to avoid obstacles, comprising the steps of: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

[0010] From the above description, it can be seen that the beneficial effects of the present invention are: based on the tracking path, the current tracking target position is determined according to the driving information of the unmanned vehicle. If there is an obstacle in front of the unmanned vehicle, the prior static map is segmented based on the driving information and the current tracking target position to obtain a sub-map, and the obstacle is mapped to the sub-map to obtain an obstacle distance information map. Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path. When the unmanned vehicle detects an obstacle, the prior static map is segmented to obtain a sub-map, and subsequent path planning is performed within the sub-map range, which greatly improves the efficiency of path planning and can plan a suitable path for the vehicle more quickly. Based on the obstacle distance information map, a hybrid A-star path planning method is used for path planning, which can flexibly plan the obstacle avoidance path according to the specific position and distance information of the obstacle, so that the vehicle can better adapt to the complex and changeable driving environment, and can respond to sudden obstacles in time, thereby improving the real-time performance of the unmanned vehicle to avoid obstacles.

[0011] Furthermore, the driving information includes vehicle position and driving direction; Determining the current tracking target position based on the tracking path and the driving information of the unmanned vehicle includes: Obtaining a preview distance of the unmanned vehicle; A current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path according to the vehicle position and the driving direction of the unmanned vehicle.

[0012] As can be seen from the above description, the tracking path itself is composed of a series of path points. There may be duplicate points or too densely concentrated between these path points. The current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path based on the vehicle position and driving direction of the unmanned vehicle, so that the vehicle has enough time to perceive the road conditions ahead and make corresponding decisions. For example, when an obstacle is detected ahead within the preview distance, the vehicle can plan an obstacle avoidance path in advance or slow down to avoid it, avoiding collision accidents due to untimely response, thereby improving the vehicle's driving safety in complex road conditions.

[0013] Furthermore, the segmenting of the prior static map based on the driving information and the current tracking target position to obtain submaps includes: Determining a road section to be traveled according to the vehicle position and the current tracking target position; determining a drivable area based on the road section to be traveled; The drivable area is segmented from the prior static map to obtain a submap.

[0014] As can be seen from the above description, by segmenting the drivable area from the prior static map to obtain a submap, and only processing the part of the map related to the current driving task, the amount of data that needs to be processed is greatly reduced, and the computing efficiency is improved. In addition, the reduced amount of data processing means that the system can complete operations such as map analysis and path planning more quickly, thereby improving the vehicle's response speed, enabling the vehicle to react more promptly to road conditions and potential obstacles ahead, and enhancing the vehicle's adaptability and safety in dynamic environments.

[0015] Furthermore, mapping the obstacle into the sub-map to obtain the obstacle distance information map includes: Discretizing the submap to obtain a two-dimensional grid map, where each grid in the grid map represents a node; Mapping the obstacles into the grid map to obtain an obstacle distance information map; The method of performing path planning for the unmanned vehicle based on the obstacle distance information map using a hybrid A-star path planning method to obtain an obstacle avoidance path includes: Acquire an initial node search set from the obstacle distance information map, the node search set including the node at the vehicle position; Calculating a cost value for each node in the node search set, and determining a node with a minimum cost value from the node search set according to the cost value; Adding the node with the minimum cost value to the trajectory point set; generating a plurality of expansion nodes according to the node with the minimum cost value based on vehicle kinematics; For each of the expansion nodes, determining whether the expansion node is located in the area of ​​the obstacle or has been added to the trajectory point set, if so, not processing the expansion node, if not, calculating the cost value of the expansion node; If the extended node has been added to the node search set, determining whether the calculated cost value of the extended node is less than the cost value of the extended node in the node search set, and if so, updating the cost value of the extended node in the node search set; If the extended node is not added to the node search set, adding the extended node to the node search set; Determine whether the node with the current minimum cost value is the node of the current tracking target position. If so, generate an obstacle avoidance path based on the trajectory point set. If not, return to execute the step of determining the node with the minimum cost value from the node search set based on the cost value.

[0016] As can be seen from the above description, each iteration selects the node with the smallest current cost value for expansion, which helps to quickly find a more optimal path from the current vehicle position to the target position, reduces the time required for path planning, and meets the real-time requirements of unmanned vehicles. The final obstacle avoidance path is obtained based on multiple factors such as obstacles, vehicle kinematics, and path cost value. It has high quality and can enable the vehicle to avoid obstacles in the best way possible while ensuring safety and continue to drive along the tracking path.

[0017] Furthermore, calculating the cost value of each node in the node search set includes: ; ; ; Where f(n) represents the cost value of node n, g(n) represents the cost value from the node at the vehicle position to node n, h(n) represents the expected value from node n to the node at the current tracking target position, g(n-1) represents the cost value from the node at the vehicle position to the previous node n-1, and L n-1,n Indicates the travel distance from the previous node n-1 to node n, addcosts indicates the penalty factor cost, represents the first weight coefficient, represents the second weight coefficient, Represents the third weight coefficient, L E L represents the Euclidean distance from node n to the current tracking target location without considering environmental obstacles. D L represents the Dubin curve path length of node n to the current tracking target position without considering environmental obstacles,O Represents the reciprocal of the shortest distance between node n and the obstacle.

[0018] From the above description, we can see that the cost value of each node consists of two parts, namely the historical cost value (g(n)) and the expected cost value (h(n)). In order to take the smoothest route possible, a penalty factor cost addcosts is added to the calculation of the historical cost value. The expected cost value is calculated by the heuristic cost function. The heuristic cost function consists of three parts, and the cost weights of the three parts can be adjusted. That is, increasing the third weight coefficient will make the search path as far away from obstacles as possible, increasing the first weight coefficient will make the search path tend to the shortest path, and increasing the second weight coefficient will make the search path more consistent with the vehicle's kinematic trajectory, thereby ensuring the reliability of the obstacle avoidance path.

[0019] Please refer to Figure 2 , an unmanned vehicle obstacle avoidance system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the following steps: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

[0020] From the above description, it can be seen that the beneficial effects of the present invention are: based on the tracking path, the current tracking target position is determined according to the driving information of the unmanned vehicle. If there is an obstacle in front of the unmanned vehicle, the prior static map is segmented based on the driving information and the current tracking target position to obtain a sub-map, and the obstacle is mapped to the sub-map to obtain an obstacle distance information map. Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path. When the unmanned vehicle detects an obstacle, the prior static map is segmented to obtain a sub-map, and subsequent path planning is performed within the sub-map range, which greatly improves the efficiency of path planning and can plan a suitable path for the vehicle more quickly. Based on the obstacle distance information map, a hybrid A-star path planning method is used for path planning, which can flexibly plan the obstacle avoidance path according to the specific position and distance information of the obstacle, so that the vehicle can better adapt to the complex and changeable driving environment, and can respond to sudden obstacles in time, thereby improving the real-time performance of the unmanned vehicle to avoid obstacles.

[0021] Furthermore, the driving information includes vehicle position and driving direction; Determining the current tracking target position based on the tracking path and the driving information of the unmanned vehicle includes: Obtaining a preview distance of the unmanned vehicle; A current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path according to the vehicle position and the driving direction of the unmanned vehicle.

[0022] As can be seen from the above description, the tracking path itself is composed of a series of path points. There may be duplicate points or too densely concentrated between these path points. The current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path based on the vehicle position and driving direction of the unmanned vehicle, so that the vehicle has enough time to perceive the road conditions ahead and make corresponding decisions. For example, when an obstacle is detected ahead within the preview distance, the vehicle can plan an obstacle avoidance path in advance or slow down to avoid it, avoiding collision accidents due to untimely response, thereby improving the vehicle's driving safety in complex road conditions.

[0023] Furthermore, the segmenting of the prior static map based on the driving information and the current tracking target position to obtain submaps includes: Determining a road section to be traveled according to the vehicle position and the current tracking target position; determining a drivable area based on the road section to be traveled; The drivable area is segmented from the prior static map to obtain a submap.

[0024] As can be seen from the above description, by segmenting the drivable area from the prior static map to obtain a submap, and only processing the part of the map related to the current driving task, the amount of data that needs to be processed is greatly reduced, and the computing efficiency is improved. In addition, the reduced amount of data processing means that the system can complete operations such as map analysis and path planning more quickly, thereby improving the vehicle's response speed, enabling the vehicle to react more promptly to road conditions and potential obstacles ahead, and enhancing the vehicle's adaptability and safety in dynamic environments.

[0025] Furthermore, mapping the obstacle into the sub-map to obtain the obstacle distance information map includes: Discretizing the submap to obtain a two-dimensional grid map, where each grid in the grid map represents a node; Mapping the obstacles into the grid map to obtain an obstacle distance information map; The method of performing path planning for the unmanned vehicle based on the obstacle distance information map using a hybrid A-star path planning method to obtain an obstacle avoidance path includes: Acquire an initial node search set from the obstacle distance information map, the node search set including the node at the vehicle position; Calculating a cost value for each node in the node search set, and determining a node with a minimum cost value from the node search set according to the cost value; Adding the node with the minimum cost value to the trajectory point set; generating a plurality of expansion nodes according to the node with the minimum cost value based on vehicle kinematics; For each of the expansion nodes, determining whether the expansion node is located in the area of ​​the obstacle or has been added to the trajectory point set, if so, not processing the expansion node, if not, calculating the cost value of the expansion node; If the extended node has been added to the node search set, determining whether the calculated cost value of the extended node is less than the cost value of the extended node in the node search set, and if so, updating the cost value of the extended node in the node search set; If the extended node is not added to the node search set, adding the extended node to the node search set; Determine whether the node with the current minimum cost value is the node of the current tracking target position. If so, generate an obstacle avoidance path based on the trajectory point set. If not, return to execute the step of determining the node with the minimum cost value from the node search set based on the cost value.

[0026] As can be seen from the above description, each iteration selects the node with the smallest current cost value for expansion, which helps to quickly find a more optimal path from the current vehicle position to the target position, reduces the time required for path planning, and meets the real-time requirements of unmanned vehicles. The final obstacle avoidance path is obtained based on multiple factors such as obstacles, vehicle kinematics, and path cost value. It has high quality and can enable the vehicle to avoid obstacles in the best way possible while ensuring safety and continue to drive along the tracking path.

[0027] Furthermore, calculating the cost value of each node in the node search set includes: ; ; ; Where f(n) represents the cost value of node n, g(n) represents the cost value from the node at the vehicle position to node n, h(n) represents the expected value from node n to the node at the current tracking target position, g(n-1) represents the cost value from the node at the vehicle position to the previous node n-1, and L n-1,n Indicates the travel distance from the previous node n-1 to node n, addcosts indicates the penalty factor cost, represents the first weight coefficient, represents the second weight coefficient, Represents the third weight coefficient, L E L represents the Euclidean distance from node n to the current tracking target location without considering environmental obstacles. D L represents the Dubin curve path length of node n to the current tracking target position without considering environmental obstacles, O Represents the reciprocal of the shortest distance between node n and the obstacle.

[0028] From the above description, we can see that the cost value of each node consists of two parts, namely the historical cost value (g(n)) and the expected cost value (h(n)). In order to take the smoothest route possible, a penalty factor cost addcosts is added to the calculation of the historical cost value. The expected cost value is calculated by the heuristic cost function. The heuristic cost function consists of three parts, and the cost weights of the three parts can be adjusted. That is, increasing the third weight coefficient will make the search path as far away from obstacles as possible, increasing the first weight coefficient will make the search path tend to the shortest path, and increasing the second weight coefficient will make the search path more consistent with the vehicle's kinematic trajectory, thereby ensuring the reliability of the obstacle avoidance path.

[0029] The above-mentioned unmanned vehicle obstacle avoidance method and system of the present invention can be applied to unmanned vehicles, and are described below through specific implementation methods: Please refer to Figure 1 、 Figure 3 and Figure 4 , embodiment 1 of the present invention is: A method for avoiding obstacles for an unmanned vehicle, comprising the steps of: S1. Receive a priori static map of an unmanned vehicle and a tracking path on the priori static map.

[0030] S2. Determine the current tracking target position based on the tracking path and the driving information of the unmanned vehicle, such as Figure 4 As shown, specifically including S21-S22: The driving information includes the vehicle position and driving direction.

[0031] S21. Obtaining a preview distance of the unmanned vehicle.

[0032] S22: Determine a current tracking target position in the tracking path that is at the preview distance from the unmanned vehicle according to the vehicle position and the driving direction of the unmanned vehicle.

[0033] S3. Determine whether there is an obstacle in front of the unmanned vehicle. If so, execute S31-S32. If not, do not perform obstacle avoidance planning, continue tracking to the current tracking target position, and return to execute S2.

[0034] In an optional embodiment, a millimeter-wave radar or a laser radar carried by the unmanned vehicle is used to detect whether there is an obstacle ahead. If so, S31-S32 are executed.

[0035] like Figure 4 As shown, in another optional embodiment, it is determined whether there is an obstacle in front of the unmanned vehicle. If so, it is determined whether the distance between the current position of the unmanned vehicle and the last planned position exceeds the length of the unmanned vehicle. If so, S31-S32 are executed. If not, it is determined whether the last planned path is not empty and there are no obstacles on the path. If it is not empty and there are no obstacles, obstacle avoidance planning is not performed and the last planned path is used. Otherwise, S31-S32 are executed. In this way, repetitive planning is avoided. If the vehicle body movement distance is short and there is no obstacle intrusion in the last planned path, the last planned result can be continued to be used to avoid planning uncertainty and instability due to slow vehicle movement, ensuring that the route can be stable within a certain moving distance. In addition, the calculation amount of determining whether there is an obstacle on the old path is smaller, and the calculation amount of replanning is larger, which can reduce the calculation amount.

[0036] S31, based on the driving information and the current tracking target position, the prior static map is segmented to obtain sub-maps, and the obstacles are mapped into the sub-maps to obtain an obstacle distance information map, specifically including S311-S315: S311. Determine a road section to be traveled according to the vehicle position and the current tracking target position.

[0037] Specifically, the vehicle position is used as the starting point of the road section to be traveled, and the current tracking target position is used as the end point of the road section to be traveled, thereby obtaining the road section to be traveled.

[0038] S312: Determine a drivable area based on the road section to be traveled.

[0039] In an optional implementation, the vehicle position in the road section to be traveled is extended backward by a vehicle body distance, and the current tracking target position in the road section to be traveled is extended forward by a vehicle body distance to obtain a drivable area.

[0040] S313, segmenting the drivable area from the prior static map to obtain a submap, such as Figure 3 shown.

[0041] S314 , discretizing the sub-map to obtain a two-dimensional grid map, where each grid in the grid map represents a node, and a node represents a possible travel trajectory point.

[0042] S315: Map the obstacles into the grid map to obtain an obstacle distance information map.

[0043] By mapping obstacles into a grid map, the closest distance between each node and the obstacle can be determined.

[0044] S32, based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path, such as Figure 4 As shown, specifically including S321-S328: S321. Acquire an initial node search set from the obstacle distance information map, where the node search set includes the node at the vehicle position.

[0045] S322: Calculate the cost value of each node in the node search set, and determine the node with the minimum cost value from the node search set according to the cost value.

[0046] The step of calculating the cost of each node in the node search set includes: ; ; ; Where f(n) represents the cost value of node n, g(n) represents the cost value from the node at the vehicle position to node n, that is, the travel distance from the node at the vehicle position to node n, that is, the historical cost value, h(n) represents the expected value from node n to the node at the current tracking target position, that is, the estimated distance from node n to the node at the current tracking target position, that is, the expected cost value, which is used to guide the search direction, g(n-1) represents the cost value from the node at the vehicle position to the previous node n-1, L n-1,n Indicates the driving distance from the previous node n-1 to node n, addcosts indicates the penalty factor cost, including the penalty for switching forward and reverse driving, reversing penalty, and penalty for inconsistent steering wheel angle with the previous node. Represents the first weight coefficient, which makes the search path biased towards the shortest path. Represents the second weight coefficient, which makes the search path more consistent with the vehicle kinematic trajectory. Represents the third weight coefficient, which makes the search path as far away from obstacles as possible, L E L represents the Euclidean distance from node n to the current tracking target location without considering environmental obstacles. D L represents the Dubins curve path length of the node n to the current tracking target position without considering environmental obstacles, E and L D Not affected by obstacles, subject to space and motion constraints, L O Represents the reciprocal of the closest distance between node n and the obstacle. Node n can be understood as the number of planned steps or grid steps. Starting from grid 0, the cost of the grids surrounding grid 0 is calculated, and the lowest cost grid is found. To calculate the current grid cost at node n, the cost of the previous (n-1) grids is used. Each cost step is calculated, and the cost is the sequence number of the grid selected at each step. It can also be understood as the planned grid distance, dividing the planning of a path into the selection of each grid, with each selected grid being a step.

[0047] S323: Add the node with the minimum cost value to the trajectory point set.

[0048] S324 : Generate multiple expansion nodes based on the node with the minimum cost value based on vehicle kinematics.

[0049] The node with the minimum cost value is the parent node, and the multiple extended nodes are child nodes.

[0050] S325 . For each of the extended nodes, determine whether the extended node is located in the obstacle area or has been added to the trajectory point set. If so, do not process the extended node. If not, calculate the cost of the extended node.

[0051] The calculation method used for calculating the cost value of the extended node is the same as the calculation method used for calculating the cost value of each node in the node search set, and will not be repeated here.

[0052] S326: If the extended node has been added to the node search set, determine whether the calculated cost of the extended node is less than the cost of the extended node in the node search set. If so, update the cost of the extended node in the node search set. If so, skip the extended node and search for other nodes. If no other nodes are found, path planning fails.

[0053] In an optional implementation, while updating the cost value of the expanded node in the node search set, the index of the parent node is also updated.

[0054] S327: If the extended node is not added to the node search set, add the extended node to the node search set.

[0055] S328. Determine whether the node with the current minimum cost value is the node of the current tracking target position. If so, generate an obstacle avoidance path based on the trajectory point set. If not, return to execute the step in S322 of determining the node with the minimum cost value from the node search set based on the cost value.

[0056] In an optional embodiment, the method further includes: after the unmanned vehicle completes driving along the obstacle avoidance path, returning to execute S2.

[0057] Please refer to Figure 2 , the second embodiment of the present invention is: An unmanned vehicle obstacle avoidance system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, each step of the unmanned vehicle obstacle avoidance method in Example 1 is implemented.

[0058] In summary, the present invention provides a method and system for unmanned vehicle obstacle avoidance, which determines the current tracking target position based on the tracking path according to the driving information of the unmanned vehicle. If there is an obstacle in front of the unmanned vehicle, the prior static map is segmented based on the driving information and the current tracking target position to obtain a sub-map, and the obstacle is mapped to the sub-map to obtain an obstacle distance information map. Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path. When the unmanned vehicle detects an obstacle, the prior static map is segmented to obtain a sub-map, and subsequent path planning is performed within the sub-map range, which greatly improves the efficiency of path planning and can plan a suitable path for the vehicle more quickly. Based on the obstacle distance information map, a hybrid A-star path planning method is used for path planning, which can flexibly plan the obstacle avoidance path according to the specific position and distance information of the obstacle, so that the vehicle can better adapt to the complex and changeable driving environment, and can respond to sudden obstacles in time, thereby improving the real-time performance of the unmanned vehicle obstacle avoidance. In addition, during obstacle avoidance planning, the node with the smallest current cost value is selected for expansion in each iteration, which helps to quickly find the optimal path from the current vehicle position to the target position, reducing the time required for path planning and meeting the real-time requirements of unmanned vehicles. The final obstacle avoidance path is obtained based on multiple factors such as obstacles, vehicle kinematics, and path cost value. It has high quality and can enable the vehicle to avoid obstacles in the best possible way while ensuring safety and continue to drive along the tracking path.

[0059] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's description and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for unmanned vehicle to avoid obstacles, characterized in that: Including steps: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

2. The method for avoiding obstacles for an unmanned vehicle according to claim 1, characterized in that: The driving information includes vehicle position and driving direction; Determining the current tracking target position based on the tracking path and the driving information of the unmanned vehicle includes: Obtaining a preview distance of the unmanned vehicle; A current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path according to the vehicle position and the driving direction of the unmanned vehicle.

3. The method for avoiding obstacles for an unmanned vehicle according to claim 2, characterized in that: The segmenting of the prior static map based on the driving information and the current tracking target position to obtain submaps includes: Determining a road section to be traveled according to the vehicle position and the current tracking target position; determining a drivable area based on the road section to be traveled; The drivable area is segmented from the prior static map to obtain a submap.

4. The method for avoiding obstacles for an unmanned vehicle according to claim 2, characterized in that: Mapping the obstacle into the sub-map to obtain an obstacle distance information map includes: Discretizing the submap to obtain a two-dimensional grid map, where each grid in the grid map represents a node; Mapping the obstacles into the grid map to obtain an obstacle distance information map; The method of performing path planning for the unmanned vehicle based on the obstacle distance information map using a hybrid A-star path planning method to obtain an obstacle avoidance path includes: Acquire an initial node search set from the obstacle distance information map, the node search set including the node at the vehicle position; Calculating a cost value for each node in the node search set, and determining a node with a minimum cost value from the node search set according to the cost value; Adding the node with the minimum cost value to the trajectory point set; generating a plurality of expansion nodes according to the node with the minimum cost value based on vehicle kinematics; For each of the expansion nodes, determining whether the expansion node is located in the area of ​​the obstacle or has been added to the trajectory point set, if so, not processing the expansion node, if not, calculating the cost value of the expansion node; If the extended node has been added to the node search set, determining whether the calculated cost value of the extended node is less than the cost value of the extended node in the node search set, and if so, updating the cost value of the extended node in the node search set; If the extended node is not added to the node search set, adding the extended node to the node search set; Determine whether the node with the current minimum cost value is the node of the current tracking target position. If so, generate an obstacle avoidance path based on the trajectory point set. If not, return to execute the step of determining the node with the minimum cost value from the node search set based on the cost value.

5. The method for avoiding obstacles for an unmanned vehicle according to claim 4, characterized in that: Calculating the cost value of each node in the node search set includes: ； ； ； Where f(n) represents the cost value of node n, g(n) represents the cost value from the node at the vehicle position to node n, h(n) represents the expected value from node n to the node at the current tracking target position, g(n-1) represents the cost value from the node at the vehicle position to the previous node n-1, and L n-1,n Indicates the travel distance from the previous node n-1 to node n, addcosts indicates the penalty factor cost, α represents the first weight coefficient, β represents the second weight coefficient, Represents the third weight coefficient, L E L represents the Euclidean distance from node n to the current tracking target location without considering environmental obstacles. D L represents the Dubin curve path length of node n to the current tracking target position without considering environmental obstacles, O Represents the reciprocal of the shortest distance between node n and the obstacle.

6. An unmanned vehicle obstacle avoidance system, 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, the following steps are implemented: Receiving a priori static map of the unmanned vehicle and a tracking path on the priori static map; determining a current tracking target position based on the tracking path and according to the driving information of the unmanned vehicle; determining whether there is an obstacle in front of the unmanned vehicle; if so, segmenting the prior static map based on the driving information and the current tracking target position to obtain submaps, and mapping the obstacle into the submaps to obtain an obstacle distance information map; Based on the obstacle distance information map, a hybrid A-star path planning method is used to plan the path of the unmanned vehicle to obtain an obstacle avoidance path.

7. The unmanned vehicle obstacle avoidance system according to claim 6, characterized in that: The driving information includes vehicle position and driving direction; Determining the current tracking target position based on the tracking path and the driving information of the unmanned vehicle includes: Obtaining a preview distance of the unmanned vehicle; A current tracking target position at the preview distance from the unmanned vehicle is determined in the tracking path according to the vehicle position and the driving direction of the unmanned vehicle.

8. The unmanned vehicle obstacle avoidance system according to claim 7, characterized in that: The segmenting of the prior static map based on the driving information and the current tracking target position to obtain submaps includes: Determining a road section to be traveled according to the vehicle position and the current tracking target position; determining a drivable area based on the road section to be traveled; The drivable area is segmented from the prior static map to obtain a submap.

9. The unmanned vehicle obstacle avoidance system according to claim 7, characterized in that: Mapping the obstacle into the sub-map to obtain an obstacle distance information map includes: Discretizing the submap to obtain a two-dimensional grid map, where each grid in the grid map represents a node; Mapping the obstacles into the grid map to obtain an obstacle distance information map; The method of performing path planning for the unmanned vehicle based on the obstacle distance information map using a hybrid A-star path planning method to obtain an obstacle avoidance path includes: Acquire an initial node search set from the obstacle distance information map, the node search set including the node at the vehicle position; Calculating a cost value for each node in the node search set, and determining a node with a minimum cost value from the node search set according to the cost value; Adding the node with the minimum cost value to the trajectory point set; generating a plurality of expansion nodes according to the node with the minimum cost value based on vehicle kinematics; For each of the expansion nodes, determining whether the expansion node is located in the area of ​​the obstacle or has been added to the trajectory point set, if so, not processing the expansion node, if not, calculating the cost value of the expansion node; If the extended node has been added to the node search set, determining whether the calculated cost value of the extended node is less than the cost value of the extended node in the node search set, and if so, updating the cost value of the extended node in the node search set; If the extended node is not added to the node search set, adding the extended node to the node search set; Determine whether the node with the current minimum cost value is the node of the current tracking target position. If so, generate an obstacle avoidance path based on the trajectory point set. If not, return to execute the step of determining the node with the minimum cost value from the node search set based on the cost value.

10. The unmanned vehicle obstacle avoidance system according to claim 9, characterized in that: Calculating the cost value of each node in the node search set includes: ； ； ； Where f(n) represents the cost value of node n, g(n) represents the cost value from the node at the vehicle position to node n, h(n) represents the expected value from node n to the node at the current tracking target position, g(n-1) represents the cost value from the node at the vehicle position to the previous node n-1, and L n-1,n Indicates the travel distance from the previous node n-1 to node n, addcosts indicates the penalty factor cost, represents the first weight coefficient, represents the second weight coefficient, Represents the third weight coefficient, L E L represents the Euclidean distance from node n to the current tracking target location without considering environmental obstacles. D L represents the Dubin curve path length of node n to the current tracking target position without considering environmental obstacles, O Represents the reciprocal of the shortest distance between node n and the obstacle.

Images