Unmanned vehicle formation cooperative hunting method, device and equipment based on pilot following, and medium

Abstract

The invention discloses an unmanned vehicle formation cooperative hunting method, device and equipment based on pilot following, and a medium, and relates to the technical field of multi-agent control. The method comprises the following steps: determining role division of a leading vehicle and a following vehicle, planning a path by the leading vehicle through an improved fast random exploration tree algorithm, sending the path and a control strategy to the following vehicle in stages, dynamically adjusting the position and speed by the following vehicle according to an instruction, ensuring formation consistency and task execution, and realizing information sharing between unmanned vehicles through a communication network. The pilot vehicle broadcasts a path and a task instruction in real time, and the following vehicles receive and analyze the path and the task instruction and then dynamically adjust the motion trail, thereby ensuring the cooperative consistency of the formation and the efficient stability of information transmission; each vehicle executes a hunting task according to a task instruction and adjusts a motion track and speed in real time, the following vehicle keeps a formation according to a path instruction, the pilot vehicle dynamically adjusts a global path according to environment change and a target position, the instruction is updated in real time through a communication network, and finally effective hunting and capturing of a target are realized. The method is suitable for a target hunting task in a complex environment, and reliable technical support is provided for a multi-target complex scene.

Description

Technical Field

[0001] The present invention relates to the field of control and capture technology of multi-agent formations, and in particular to a method, device, equipment and medium for collaborative capture of unmanned vehicle formations based on piloting and following. Background Art

[0002] With the development of unmanned driving technology, multi-agent systems have shown great potential in collaborative task execution. Among them, the application prospects of multi-unmanned vehicle collaborative operations in military, rescue, monitoring and other fields are particularly broad. In complex environments, such as cities, forests and open fields, a single agent is difficult to effectively perform tasks due to the limitations of perception range and computing power. Therefore, the collaborative operation of multi-vehicle formations has become an effective means to cope with complex environments and task requirements.

[0003] In the prior art, the pilot-follower mode is widely used in unmanned vehicle formation systems. Through division of labor and cooperation, the pilot vehicle is responsible for path planning and decision-making, and the follower vehicle dynamically adjusts its position and speed according to the instructions of the pilot vehicle, thereby achieving the capture of the target. However, the prior art path planning method often cannot respond quickly when faced with dynamically changing environments and target positions, resulting in the failure of the capture mission. In addition, poor or delayed communication between vehicles may also lead to coordination failure. Therefore, there is a need for an unmanned vehicle formation method that can efficiently and stably perform capture missions in complex environments to meet practical application needs.

[0004] Based on the above, the present invention proposes a technical solution for collaborative capture of unmanned vehicle formations based on pilot following, so as to solve the problems of low path planning efficiency, low capture success rate and inconsistent capture progress existing in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device, equipment and medium for collaborative capture of an unmanned vehicle formation based on piloting and following, which can effectively solve the problems of low path planning efficiency, low capture success rate and inconsistent capture progress existing in the prior art.

[0006] The specific plan is as follows: In the first aspect, the present invention proposes a cooperative capture method of an unmanned vehicle formation based on piloting and following, and determines the role division of the pilot vehicle and the following vehicle; the pilot vehicle is equipped with a depth camera, and sends the path and control strategy to the following vehicle in stages by planning the path, and the following vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; Information sharing between unmanned vehicles is achieved through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the following vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; The lead vehicle and the follower vehicle perform the encirclement and capture mission according to the mission instructions, and adjust the motion trajectory and speed in real time. The follower vehicle maintains the formation according to the path instructions. The lead vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

[0007] Furthermore, during the mission execution phase, the unmanned vehicle carries out a roundup operation based on the instructions sent by the lead vehicle. The lead vehicle adjusts the global path based on real-time environmental perception data. The follower vehicle adjusts its own motion trajectory and speed in real time based on the latest path instructions sent by the lead vehicle, so as to ensure that it always remains in the predetermined formation and performs the mission in coordination with the lead vehicle.

[0008] Furthermore, the method for allocating the capture points of the capture operation is specifically as follows: The formation of the unmanned vehicle fleet is determined according to the location of the unmanned vehicle and the designed capture point. The capture point is set according to the target location, the number of unmanned vehicles and the expected encirclement formation. The intersection of the reverse direction of the target speed and the capture circle is used as the first capture point, and the second capture point is used as the second capture point. The capture point is determined based on the Euclidean distance between the initial position of each following unmanned vehicle and the initial capture point and the expected following distance in the body coordinate system of the leading unmanned vehicle; After the initial capture point is determined, it is assigned to each unmanned vehicle according to its initial position. The pilot unmanned vehicle is assigned to the first capture point, and the remaining capture points are assigned based on the principle of closest distance. Calculate the Euclidean distance between the initial position of each following unmanned vehicle and the initial capture point respectively; Allocate the initial capture point closest to each following unmanned vehicle to facilitate the determination of the formation and the position of each unmanned vehicle in the formation; When performing formation movement, the solution assumes that the default coordinate system is the world coordinate system. According to the expected position coordinates, the following unmanned vehicle calculates the expected speed and expected yaw rate to ensure the formation and maintenance of the formation.

[0009] Furthermore, the leading vehicle plans a path based on a fast random exploration tree algorithm and sends the path and control strategy to the following vehicle in stages.

[0010] Furthermore, the path planning based on the fast random exploration tree algorithm specifically includes: In the process of generating the sampling points, a probability value is randomly obtained according to the uniform probability distribution; The probability value is compared with a pre-set threshold. If the probability value is less than the threshold, the target point is directly selected as the sampling point; if the probability value is greater than the threshold, the original sampling method is continued to perform random sampling in the entire search space.

[0011] Furthermore, the original sampling method specifically includes: A spatial structure representing the map environment is created in the search space, defining the starting point, the target point, and the location of obstacles in the map; the path is gradually expanded from the starting point until a feasible path to the target point is found; A sampling point is randomly selected in the map space, and the distance between the sampling point and the nearest node in the currently generated path tree is calculated. The path is extended in a predetermined step length along the direction from the nearest node to the sampling point to generate a new path node. The new path node needs to undergo obstacle collision detection. If the new path node does not collide with any obstacle, it is included in the path tree and the path is further extended. Repeat the above steps of random sampling and path extension until the extended path covers the target point.

[0012] Furthermore, the following vehicle is equipped with an anti-collision function during the execution process, and uses an artificial potential field method to avoid collision with other vehicles by receiving position and speed information sent by other vehicles; the artificial potential field method includes: The overall artificial potential field is expressed as the sum of the gravitational potential field of the target point and the repulsive potential field of the obstacle; the total artificial potential field function is expressed as the sum of the repulsive potential field function generated by obstacles and other vehicles and the gravitational potential field of the target point; the gravitational potential field of the target point is used to guide the unmanned vehicle to move to the capture point; For obstacles and other vehicles that cannot be passed, they are processed based on the obstacle repulsion potential field and the speed repulsion potential field. The obstacle repulsion potential field is used to represent the repulsive force of the obstacle itself on the unmanned vehicle. If the distance between the unmanned vehicle and the obstacle is less than the action distance of the obstacle, the obstacle repulsion potential field will act on the unmanned vehicle to keep it away from the obstacle; otherwise, the obstacle repulsion potential field will not work; When an obstacle approaches the unmanned vehicle at a higher speed, the velocity repulsive potential field prompts the unmanned vehicle to choose an avoidance path to avoid collision.

[0013] In a second aspect, the present invention discloses a cooperative capture device for an unmanned vehicle formation based on piloting and following, comprising: A configuration module is used to determine the roles of the lead vehicle and the following vehicle; the lead vehicle is equipped with a depth camera, and sends the path and control strategy to the following vehicle in stages by planning the path, and the following vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; The communication module is used to realize information sharing between unmanned vehicles through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the follower vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; The execution module is used for the lead vehicle and the follower vehicle to perform the encirclement and capture mission according to the mission instructions, adjust the movement trajectory and speed in real time, the follower vehicle maintains the formation according to the path instructions, and the lead vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

[0014] In a third aspect, the present invention discloses an electronic device, comprising: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the aforementioned unmanned vehicle formation collaborative encirclement method based on pilot following.

[0015] In a fourth aspect, the present invention discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the aforementioned disclosed unmanned vehicle formation collaborative encirclement method based on pilot following are implemented.

[0016] As can be seen from the above, the present invention discloses a method, device, equipment and medium for cooperative capture of unmanned vehicle formation based on pilot and follow, determines the role division of the pilot vehicle and the follower vehicle, the pilot vehicle plans the path through the improved fast random exploration tree algorithm, sends the path and control strategy to the follower vehicle in stages, the follower vehicle dynamically adjusts the position and speed according to the instruction, ensures the consistency of the formation and the execution of the task, realizes the information sharing of the unmanned workshop through the communication network, the pilot vehicle broadcasts the path and task instructions in real time, and the follower vehicle receives and analyzes and dynamically adjusts the motion trajectory to ensure the coordinated consistency of the formation and the efficient stability of information transmission; each vehicle performs the capture task according to the task instruction, adjusts the motion trajectory and speed in real time, the follower vehicle maintains the formation according to the path instruction, the pilot vehicle dynamically adjusts the global path according to the environmental changes and the target position, and updates the instruction in real time through the communication network, and finally realizes the effective encirclement and capture of the target. The present invention is suitable for target capture tasks in complex environments, and provides reliable technical support for multi-target complex scenes. The present invention optimizes the fast random exploration tree algorithm, optimizes the random sampling process by introducing the target bias strategy, makes the path tree more inclined to expand in the direction of the target point, and effectively improves the efficiency and accuracy of path planning. When facing complex environments or dynamically changing scenes, the improved algorithm can adjust the path planning in real time to improve the capture effect of the target. In addition, the present invention also introduces a path planning method based on artificial potential field theory to cope with the obstacle avoidance requirements of obstacles and other vehicles in the formation movement. By establishing the gravitational potential field of the target point and the repulsive potential field model of the obstacle, the unmanned vehicle can effectively avoid obstacles in complex environments, avoid collisions with other vehicles, and ensure the integrity of the formation and the smooth completion of the task. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0018] Figure 1 A schematic diagram of an unmanned vehicle system provided by an embodiment of the present invention; Figure 2 A schematic diagram of the relative positions of pilot and follower provided in an embodiment of the present invention; Figure 3 A schematic diagram of a formation allocation method provided by an embodiment of the present invention; Figure 4 A relative position diagram of each desired capture point and the escaped target of the capture formation members provided in the embodiment of the present invention; Figure 5 A schematic diagram of a pilot vehicle path planning algorithm provided by an embodiment of the present invention; Figure 6 A schematic diagram of the overall method flow provided by an embodiment of the present invention; Figure 7 A schematic diagram of a device provided in an embodiment of the present invention; Figure 8 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The present invention solves the problems of low efficiency of path planning, low success rate of roundup and inconsistent progress of roundup in the existing multi-agent roundup, and realizes more efficient formation roundup by improving the path planning algorithm of the leader and the formation method based on pilot-follower, thereby improving the autonomy and safety of the formation system. The design idea of ​​this embodiment is roughly as follows: in view of the problems of low efficiency of path planning, low success rate of roundup and inconsistent progress of roundup in the multi-agent roundup, a pilot-follower formation method is adopted, and the formation of vehicles in the formation is allocated. The pilot vehicle adopts an improved RRT algorithm for path planning, and the results are broadcast to each follower agent, thereby realizing formation roundup.

[0021] The embodiment of the present invention provides a method for cooperative capture of unmanned vehicle formations based on pilot-follower, and the method is used in a system, wherein the system includes: a multi-agent end and a ground end. The agent end includes: at least two unmanned vehicles. Figure 1 As shown, multiple unmanned vehicles and the ground end together constitute a system communication network. Among them, the unmanned boat can be a four-wheeled unmanned vehicle or a tracked vehicle, and other models are acceptable. Each intelligent end and the ground end are equipped with Wi-Fi and ZigBee communication modules respectively; each intelligent body establishes communication through Wi-Fi and Zigbee, and the intelligent body and the ground end establish communication through Wi-Fi. For example, each unmanned vehicle is equipped with a ZigBee communication module for transmitting distance and angle data between vehicles. Both the pilot unmanned vehicle and the ground end are equipped with Wi-Fi modules, and information interaction is realized through a router, so that the ground end can display target information in real time.

[0022] like Figure 5 As shown, the method includes: S1. Determine the roles of the pilot vehicle and the following vehicle; the pilot vehicle is equipped with a depth camera, and sends the path and control strategy to the following vehicle in stages by planning the path. The following vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; Before implementing the roundup mission, the roles of the lead vehicle and the follower vehicle must be determined. The lead vehicle plays a core leadership role in the entire formation, responsible for global path planning and mission decision-making. To this end, the lead vehicle is equipped with a sensor depth camera that can perceive the surrounding environment in real time and obtain environmental information and target status.

[0023] Preferably, in the process of path planning, the pilot vehicle adopts an improved RRT (rapid random tree) algorithm, which can effectively handle complex environments and changing target points to achieve fast path planning. Through the improved RRT algorithm, the pilot vehicle can generate an optimal path that takes into account multiple factors in a short time. Path planning is not just a simple route selection, but also includes the division of each control stage. Each stage corresponds to different task requirements and environmental conditions. The pilot vehicle selects appropriate control strategies at different stages and sends these strategies and path information to the follower vehicle in stages. After receiving these instructions, the follower vehicle dynamically adjusts its position and speed according to the instructions to ensure the formation consistency of the entire formation and the efficient execution of the task.

[0024] S2. Information sharing between unmanned vehicles is achieved through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the following vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; Information sharing is crucial in the coordinated capture mission of the unmanned vehicle formation. In order to achieve efficient information sharing, a variety of communication technologies are used in the system, mainly including Wi-Fi and ZigBee communication modules. Each unmanned vehicle can not only communicate with the ground terminal through Wi-Fi, but also establish a point-to-point communication connection with other unmanned vehicles through ZigBee to ensure stable and low-latency transmission of information within the unmanned vehicle formation. The shared information includes the real-time location information, speed, environmental perception data (such as target status information captured by the depth camera) of each unmanned vehicle, as well as the current state and motion trajectory of the target object. The leading vehicle broadcasts path planning and task instructions in real time through the wireless communication network. After the following vehicle receives and parses this information, it dynamically adjusts its motion trajectory and speed according to the preset control algorithm and its own sensor data to ensure the overall coordination of the formation. In addition, the communication network also has a fault detection and redundant transmission mechanism. When the communication of a vehicle is interrupted, other vehicles can automatically adjust the communication link to ensure that the communication network of the formation is always intact and efficient. This information sharing mechanism not only improves the reliability of task execution, but also ensures the coordination consistency in a dynamic and complex environment.

[0025] S3, the pilot vehicle and the follower vehicle perform the encirclement and capture mission according to the mission instructions, and adjust the motion trajectory and speed in real time. The follower vehicle maintains the formation according to the path instructions. The pilot vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

[0026] During the mission execution phase, each unmanned vehicle launches a capture operation based on the instructions sent by the pilot vehicle. Based on the preliminary planning, the pilot vehicle continuously optimizes and adjusts the global path in combination with real-time environmental perception data. As the mission progresses, obstacles in the environment may change, and the trajectory of the target object may also shift. At this time, the follower vehicle adjusts its own trajectory and speed in real time according to the latest path instructions sent by the pilot vehicle to ensure that it always remains in the predetermined formation and can perform the mission in coordination with the pilot vehicle. In addition, the follower vehicle is also equipped with an anti-collision function during the execution process. By receiving the position and speed information sent by other vehicles and using an artificial potential field, it avoids collisions with other vehicles. In special circumstances, such as when the target object suddenly changes direction or new obstacles appear, the pilot vehicle adjusts the global path in real time and sends the updated instructions to all follower vehicles. This dynamic adjustment mechanism ensures that the unmanned vehicle formation can flexibly respond to various emergencies, and ultimately achieves effective encirclement and capture of the target object.

[0027] In this embodiment, if Figure 3 As shown, the trap point allocation method used in the trap method system is as follows: The formation of the unmanned vehicle fleet needs to be determined based on the location of the unmanned vehicle and the designed capture point. The capture point is set according to the target location, the number of unmanned vehicles and the expected encirclement formation.

[0028] The capture is considered successful when the unmanned vehicle formation surrounds the target in the expected encirclement formation, so the capture standard is modeled. The capture standard of the present invention can be expressed in polar coordinates centered on the target. Assuming that the coordinates of the target are , then The polar coordinates of the unmanned vehicle are as follows: (1) (2) In this example, the capture points are allocated as follows: Figure 4 As shown, the intersection of the opposite direction of the target speed and the capture circle is taken as the first capture point , then the remaining capture points According to formula (1) and (2), it can be determined that The coordinates of the capture point are .

[0029] After the initial capture point is determined, it is assigned to each unmanned vehicle according to its initial position to determine the formation. Since the leading unmanned vehicle is the core of the entire formation, it is assigned to the first capture point to determine the position of the leading unmanned vehicle in the formation. The remaining capture points are assigned based on the "shortest distance" principle. The Euclidean distance between the initial position of each following unmanned vehicle and the initial capture point is calculated separately: (3) Each following unmanned vehicle is assigned the initial capture point closest to it, thereby determining the formation and the position of each unmanned vehicle in the formation.

[0030] In this example, the leader-follower method in the system is as shown in formula (4)(5)(6): When performing formation movement, it is necessary to solve the assumption that the default coordinate system is the world coordinate system and the body coordinate system of the leading unmanned vehicle is coordinate system C. Angle, Follow the ground unmanned vehicle at a distance. Is the following distance In the leading member body coordinate system , The weight on the axis, They are the positions of the pilot and follower unmanned vehicles in the world coordinate system. It is the body coordinate system of the pilot unmanned vehicle Axes and the World Coordinate System The angle formed by the axes.

[0031] Expected following distance in the body coordinate system of the pilot unmanned vehicle , It can be expressed as: (4) The actual following distance between the follower and the leader in the vehicle body coordinate system , It can be expressed as: (5) From the above formula, we can get the expected position coordinates in the world coordinate system , as follows: (6) like Figure 2 As shown, according to the desired position coordinates, the following unmanned vehicle adopts the sliding mode control method to calculate the desired speed and the desired yaw angle rate, thereby ensuring the formation and maintenance of the formation.

[0032] In one embodiment of the invention, the path planning algorithm of the pilot vehicle of the present invention includes that after the pilot vehicle determines the roundup point, it needs to perform path planning to reach the designated roundup point. Since the rounded target is mobile, the real-time requirements of path planning are high, so the present invention introduces a new fast random tree (RRT) algorithm to optimize the path planning process. The RRT algorithm of the prior art is a representative sampling-based algorithm in the field of path planning. Its main idea is to randomly sample in the entire search space and generate path points by gradually expanding, so as to plan a collision-free path from the starting point to the end point. Specifically, the execution steps of the RRT algorithm of the prior art include the following aspects: First, create a spatial structure representing the map environment within the search space and define the starting point , Target point And the location of obstacles in the map. Based on this, the algorithm will gradually expand the path from the starting point until a feasible path to the target point is found.

[0033] Secondly, the algorithm randomly selects a sampling point in the map space , and calculate the nearest node between the sampling point and the currently generated path tree Next, we move from the nearest node to the sampling point in a predetermined step length. The path is extended to generate a new path node. The newly generated path node needs to undergo obstacle collision detection. If the node does not collide with any obstacle, it is included in the path tree and the path is further extended.

[0034] Repeat the above steps of random sampling and path extension until the extended path covers the target point At this point, the algorithm has completed the planning of a collision-free path from the starting point to the target point. In addition, if the sampling point With the target point If the line between them does not intersect with any obstacle, the path node can also be included in the path tree, and the path is returned as the final result.

[0035] In order to further improve the path search efficiency of the RRT algorithm, the present invention improves the prior art RRT algorithm and proposes a path planning method based on a target bias strategy. In the RRT algorithm of the present invention, the target bias strategy effectively reduces the randomness of the algorithm search by adjusting the generation method of random sampling points, thereby reducing the time consumption of blank areas during the path search process. Specifically, the target bias strategy introduces a probability value in the random sampling process so that the sampling points are more likely to be generated toward the target point. Figure 5 As shown, the method of the present invention is specifically: In the process of generating sampling points, a probability value is first randomly obtained according to the uniform probability distribution, and then the probability value is compared with the pre-set threshold. If the probability value is less than the threshold, the target point is directly selected as the sampling point, thereby increasing the probability of the path tree growing to the target point; if the probability value is greater than the threshold, random sampling is still performed in the entire search space in the manner of the prior art RRT algorithm. The mathematical representation of the target bias strategy is as follows: (7) in, is the probability value obtained randomly according to the uniform probability distribution, is a pre-set threshold. represents the target point, represents random sampling points.

[0036] By introducing the target bias strategy, the improved RRT algorithm of the present invention can significantly improve the efficiency of path planning. Specifically, this strategy makes the path tree more inclined to grow in the direction of the target point during the expansion process, thereby effectively reducing the invalid search for blank areas during the path planning process and shortening the time for path generation. At the same time, since the target bias strategy can reduce the randomness of the path to a certain extent, the smoothness and feasibility of the path are improved. When facing complex environments or dynamically changing scenes, the improved RRT algorithm of the present invention can better adapt to environmental changes and achieve efficient capture of targets by adjusting path planning in real time.

[0037] In one embodiment of the present invention, in order to improve the safety and efficiency of unmanned vehicles in formation movement, especially the ability to avoid obstacles and collisions in complex environments, the present invention introduces a path planning method based on artificial potential field theory. When unmanned vehicles follow the formation movement, they often encounter obstacles on the path, and there is also a potential risk of collision when the distance between unmanned vehicles is close. In order to solve these problems, Figure 6 As shown, the present invention models obstacles, other vehicles and capture points through an artificial potential field model to quantify collision risks and provide a reasonable obstacle avoidance strategy for the unmanned vehicle.

[0038] In this model, the overall artificial potential field can be expressed as the sum of the target point gravitational potential field and the obstacle repulsive potential field, and the specific form is as follows: (8) in, is the potential field function of the unmanned vehicle under the gravitational force of the target point, and is the repulsive potential field function due to obstacles and other vehicles.

[0039] To simplify the calculation, the present invention uniformly treats obstacles and other vehicles, treating them as impassable obstacles, so that the total artificial potential field function can be simplified as: (9) in, It is the repulsive potential field function caused by obstacles and other vehicles.

[0040] In the artificial potential field model, the gravitational potential field at the target point It is mainly used to guide the unmanned vehicle to move to the capture point. The potential field function can be defined as: (10) in, is the scale factor of the gravitational potential field, It is the Euclidean distance between the current position of the unmanned vehicle and the target point.

[0041] For impassable obstacles and other vehicles, the present invention considers two different repulsive potential fields: obstacle repulsive potential field and velocity repulsive potential field. The obstacle repulsive potential field is used to represent the repulsive force of the obstacle itself on the unmanned vehicle, and its mathematical form is as follows: (11) in, is the repulsive potential field of the obstacle, is the scale factor of the obstacle repulsive potential field, is the location of the obstacle, is the Euclidean distance between the autonomous vehicle and the obstacle, It represents the maximum distance at which an obstacle affects the unmanned vehicle. If the distance between the unmanned vehicle and the obstacle is less than the distance of action of the obstacle, the repulsive potential field will act on the unmanned vehicle, making it move away from the obstacle; otherwise, the repulsive potential field will not work.

[0042] In addition, considering the impact of obstacles and other vehicles on the unmanned vehicle during movement, the present invention also introduces a velocity repulsion potential field. This potential field takes into account the potential impact of the speed of the obstacle and its direction of movement on the unmanned vehicle, and is specifically defined as follows: (12) in, is the velocity repulsive potential field, is the scale factor of the velocity repulsive potential field, is the velocity vector of the obstacle, It is the angle between the obstacle's moving direction and the positive direction of the coordinate axis. When an obstacle approaches the unmanned vehicle at a high speed, the velocity repulsion potential field will play a significant role, prompting the unmanned vehicle to choose an avoidance path to avoid collision.

[0043] By combining the gravitational potential field and the repulsive potential field, the artificial potential field model proposed in the present invention can effectively guide the unmanned vehicle to safely perform the formation task in a complex environment. In practical applications, the unmanned vehicle senses obstacles and other vehicles in the environment and updates the artificial potential field function in real time, thereby dynamically adjusting the path planning to ensure the collision-free path and efficient execution of the task. At the same time, because the artificial potential field model has a high computational efficiency, it can provide a fast path correction capability when the unmanned vehicle faces a dynamically changing environment, thereby improving the overall response speed and adaptability of the system.

[0044] In summary, the path planning method based on artificial potential field theory proposed in this invention can significantly improve the safety and stability of unmanned vehicles in platoon movement, effectively avoid the risk of collision with obstacles and other vehicles, and achieve smooth arrival at the target point. This method is not only suitable for path planning of a single unmanned vehicle, but can also provide support for the coordinated movement of multiple unmanned vehicles, thereby improving the overall task execution capability of unmanned vehicle formations in complex environments. This embodiment discloses a method for encircling a formation of unmanned vehicles based on piloting and following, which relates to the technical field of cooperative control and encirclement tasks of unmanned vehicle groups, and aims to achieve effective encirclement and control of mobile targets through precise formation design and dynamic path planning.

[0045] In the technical solution of the present invention, the formation design of the unmanned vehicle formation is based on the determination of the capture point, and combines the target position, the number of unmanned vehicles and the expected encirclement formation. The system first takes the intersection of the opposite direction of the target speed and the capture circle as the first capture point, and determines the position of other capture points based on this point. Subsequently, based on the initial position of the unmanned vehicle, each unmanned vehicle is assigned to the corresponding capture point to determine the overall formation formation. As the core of the formation, the leading unmanned vehicle will be assigned to the first capture point first to ensure its dominant position in the formation. Other following unmanned vehicles are assigned to the corresponding capture points in turn based on the principle of "shortest distance", thereby forming the best formation structure to ensure the effectiveness and accuracy of the capture mission.

[0046] On this basis, the present invention adopts an improved leader-follower method, combined with a sliding mode control algorithm, to achieve formation maintenance and dynamic adjustment of unmanned vehicles in formation movement. In the formation process, it is assumed that the default coordinate system is the world coordinate system, and the body coordinate system of the leading unmanned vehicle is the local coordinate system C. The following unmanned vehicle follows the leading unmanned vehicle at a certain angle and distance, and by calculating the expected position coordinates in the world coordinate system, the sliding mode control method is used to adjust the motion state of the unmanned vehicle in real time to ensure the stability of the formation and the strictness of the formation.

[0047] In order to cope with the real-time requirements of target mobility and path planning, the present invention introduces an improved fast random tree (RRT) algorithm. The prior art RRT algorithm randomly samples and generates path points in the search space, thereby planning a collision-free path. The present invention optimizes the random sampling process by introducing a target bias strategy, so that the path tree is more inclined to expand in the direction of the target point, effectively improving the efficiency and accuracy of path planning. When facing complex environments or dynamically changing scenes, the improved algorithm can adjust the path planning in real time to improve the capture effect of the target. In addition, the present invention also introduces a path planning method based on artificial potential field theory to cope with the obstacle avoidance requirements of obstacles and other vehicles in formation movement. By establishing a gravitational potential field model of the target point and a repulsive potential field model of the obstacle, the unmanned vehicle can effectively avoid obstacles in a complex environment, avoid collisions with other vehicles, and ensure the integrity of the formation and the smooth completion of the task.

[0048] In summary, this embodiment provides a systematic unmanned vehicle formation capture method, which realizes efficient capture and control of the target by combining the precise allocation of capture points, the optimized RRT path planning algorithm and the artificial potential field obstacle avoidance strategy. This method not only improves the cooperative combat capability of the unmanned vehicle formation, but also provides reliable technical support for complex scenarios with multiple targets.

[0049] The present invention also proposes a cooperative capture device for an unmanned vehicle formation based on piloting and following, as shown in the attached Figure 7The device 10 includes a configuration module, a communication module, and an execution module.

[0050] A configuration module is used to determine the roles of the lead vehicle and the following vehicle; the lead vehicle is equipped with a depth camera, and sends the path and control strategy to the following vehicle in stages by planning the path, and the following vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; The communication module is used to realize information sharing between unmanned vehicles through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the follower vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; The execution module is used for the lead vehicle and the follower vehicle to perform the encirclement and capture mission according to the mission instructions, adjust the movement trajectory and speed in real time, the follower vehicle maintains the formation according to the path instructions, and the lead vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

[0051] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the unmanned vehicle formation collaborative encirclement method based on pilot following performed by the electronic device disclosed in any of the aforementioned embodiments.

[0052] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present invention, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0053] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0054] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0055] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the unmanned vehicle formation collaborative capture method based on pilot following performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the electronic device, the data 223 can also include data collected by its own input and output interface 25, etc.

[0056] Furthermore, an embodiment of the present invention also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the steps of the unmanned vehicle formation collaborative encirclement method based on pilot following disclosed in any of the aforementioned embodiments are implemented.

[0057] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0058] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0059] The steps of the method or algorithm described in conjunction with the embodiments disclosed in the present invention can be implemented directly by hardware, software modules executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0060] Finally, it should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0061] The above is a detailed introduction to the unmanned vehicle formation collaborative encirclement method, device, equipment and storage medium based on pilot following provided by the present invention. The present invention uses specific examples to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A collaborative capture method of unmanned vehicle formation based on piloting and following, characterized in that: The method comprises: Determine the roles of the lead vehicle and the follower vehicle; the lead vehicle is equipped with a depth camera, and sends the path and control strategy to the follower vehicle in stages by planning the path. The follower vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; Information sharing between unmanned vehicles is achieved through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the following vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; The lead vehicle and the follower vehicle perform the encirclement and capture mission according to the mission instructions, and adjust the motion trajectory and speed in real time. The follower vehicle maintains the formation according to the path instructions. The lead vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

2. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 1 is characterized in that: During the mission execution phase, the unmanned vehicle carries out a roundup operation based on the instructions sent by the lead vehicle. The lead vehicle adjusts the global path based on real-time environmental perception data. The follower vehicle adjusts its own motion trajectory and speed in real time based on the latest path instructions sent by the lead vehicle to ensure that it always remains in the predetermined formation and performs the mission in coordination with the lead vehicle.

3. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 2 is characterized in that: The method for allocating the capture points of the capture operation is specifically as follows: The formation of the unmanned vehicle fleet is determined according to the location of the unmanned vehicle and the designed capture point. The capture point is set according to the target location, the number of unmanned vehicles and the expected encirclement formation. The intersection of the reverse direction of the target speed and the capture circle is used as the first capture point, and the second capture point is used as the second capture point. The capture point is determined based on the Euclidean distance between the initial position of each following unmanned vehicle and the initial capture point and the expected following distance in the body coordinate system of the leading unmanned vehicle; After the initial capture point is determined, it is assigned to each unmanned vehicle according to its initial position. The pilot unmanned vehicle is assigned to the first capture point, and the remaining capture points are assigned based on the principle of closest distance. Calculate the Euclidean distance between the initial position of each following unmanned vehicle and the initial capture point respectively; Allocate the initial capture point closest to each following unmanned vehicle to facilitate determining the formation and position of each unmanned vehicle in the formation; When performing formation movement, the solution assumes that the default coordinate system is the world coordinate system. According to the expected position coordinates, the following unmanned vehicle calculates the expected speed and expected yaw rate to ensure the formation and maintenance of the formation.

4. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 1 is characterized in that: The leading vehicle plans a path based on a fast random exploration tree algorithm and sends the path and control strategy to the following vehicles in stages.

5. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 4 is characterized in that: The path planning based on the fast random exploration tree algorithm specifically includes: In the process of generating the sampling points, a probability value is randomly obtained according to the uniform probability distribution; The probability value is compared with a pre-set threshold. If the probability value is less than the threshold, the target point is directly selected as the sampling point; if the probability value is greater than the threshold, the original sampling method is continued to perform random sampling in the entire search space.

6. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 5 is characterized in that: The original sampling method specifically includes: Creating a spatial structure representing the map environment in the search space, defining the starting point, the target point, and the location of obstacles in the map; Starting from the starting point, gradually expand the path until a feasible path to the target point is found; A sampling point is randomly selected in the map space, and the distance between the sampling point and the nearest node in the currently generated path tree is calculated. The path is extended in a predetermined step length along the direction from the nearest node to the sampling point to generate a new path node. The new path node needs to undergo obstacle collision detection. If the new path node does not collide with any obstacle, it is included in the path tree and the path is further extended. Repeat the above steps of random sampling and path extension until the extended path covers the target point.

7. The unmanned vehicle formation collaborative capture method based on pilot-following according to claim 1 is characterized in that: The following vehicle is equipped with an anti-collision function during the execution process, and uses an artificial potential field method to avoid collision with other vehicles by receiving position and speed information sent by other vehicles; the artificial potential field method includes: The overall artificial potential field is expressed as the sum of the target point gravitational potential field and the obstacle repulsive potential field; The total artificial potential field function is expressed as the sum of the repulsive potential field function generated by obstacles and other vehicles and the gravitational potential field of the target point; the gravitational potential field of the target point is used to guide the unmanned vehicle to move to the capture point; For obstacles and other vehicles that cannot be passed, they are processed based on the obstacle repulsion potential field and the speed repulsion potential field. The obstacle repulsion potential field is used to represent the repulsive force of the obstacle itself on the unmanned vehicle. If the distance between the unmanned vehicle and the obstacle is less than the action distance of the obstacle, the obstacle repulsion potential field will act on the unmanned vehicle to keep it away from the obstacle; otherwise, the obstacle repulsion potential field will not work; When an obstacle approaches the unmanned vehicle at a higher speed, the velocity repulsive potential field prompts the unmanned vehicle to choose an avoidance path to avoid collision.

8. A cooperative capture device for unmanned vehicle formation based on piloting and following, characterized in that: include: A configuration module is used to determine the roles of the lead vehicle and the following vehicle; the lead vehicle is equipped with a depth camera, and sends the path and control strategy to the following vehicle in stages by planning the path, and the following vehicle dynamically adjusts the position and speed according to the instructions to ensure the consistency of the formation and the efficient execution of the task; The communication module is used to realize information sharing between unmanned vehicles through the communication network. The pilot vehicle broadcasts the path and task instructions in real time, and the follower vehicle receives and analyzes them and dynamically adjusts the movement trajectory to ensure efficient and stable formation coordination and information transmission; The execution module is used for the lead vehicle and the follower vehicle to perform the encirclement and capture mission according to the mission instructions, adjust the movement trajectory and speed in real time, the follower vehicle maintains the formation according to the path instructions, and the lead vehicle dynamically adjusts the global path according to environmental changes and target position and updates the instructions through the communication network to achieve effective encirclement and capture of the target.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the unmanned vehicle formation collaborative encirclement method based on pilot following as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, the steps of the unmanned vehicle formation collaborative encirclement method based on pilot following as described in any one of claims 1 to 7 are implemented.

Images