Multi-task end-to-end unmanned aerial vehicle cruising and formation maintaining method

Abstract

The invention discloses a multi-task end-to-end unmanned aerial vehicle cruising and formation maintaining method, which comprises the following steps of: acquiring unmanned aerial vehicle and environment information, and inputting the information into a dynamic formation control module to control an unmanned aerial vehicle group to keep predetermined formation advancing in a flight process so as to avoid obstacles; according to the change of the dynamic environment, the self-adaptive strategy module calculates and outputs the flight strategy and path planning of the unmanned aerial vehicle in real time; each unmanned aerial vehicle independently processes local environment information to ensure global coordination of the unmanned aerial vehicle cluster; and the unmanned aerial vehicle performs cruising and formation maintenance according to the finally generated decision signal. According to the method, the formation form of the unmanned aerial vehicle is adjusted in real time and the optimal strategy is autonomously learned by sensing the environment change, so that the unmanned aerial vehicle can efficiently and reliably complete the multi-task requirement in a complex scene.

Description

Technical Field

[0001] The present invention belongs to the technical field of unmanned aerial vehicles, and in particular relates to a multi-task end-to-end unmanned aerial vehicle cruising and formation maintenance method. Background Art

[0002] With the rapid development of drone technology, multi-UAV systems have been widely used in many fields, such as disaster relief, environmental monitoring, military reconnaissance and air patrol. However, with the complexity of application scenarios, the challenges faced by drone groups in performing multiple tasks are becoming increasingly significant, especially in terms of cruising methods and formation maintenance in complex environments. The response to these challenges directly affects the efficiency and safety of drone groups in performing tasks.

[0003] At present, traditional drone online decision-making strategies are mainly focused on a single decision environment. However, with the rise of multi-environment decision-making, that is, making continuous decisions for multiple environments in a single decision process, new challenges and opportunities have emerged. Considering the possible cost-effectiveness differences in different environments, drones need to accurately evaluate each decision to ensure the most cost-effective decision result.

[0004] In a complex and ever-changing environment, drone formations need to adjust their formations in real time according to the external environment and mission requirements. By dynamically adjusting the relative positions between drones, the formation can adapt to external interference and obstacle changes while maintaining the stability of the communication network. Dynamic formation control requires not only that drones have flexible maneuverability, but also that the system can quickly perceive and process information from the environment to make optimal adjustments.

[0005] Traditional predetermined strategies often cannot adapt to dynamically changing mission requirements and environmental complexity. Through reinforcement learning, drones can continuously learn and optimize their own decisions through interaction with the environment. In multi-task scenarios, RL can help drones autonomously learn how to make efficient flight path planning and formation adjustments in uncertain environments when there are mission conflicts and limited resources. This strategy gives drone groups a higher level of intelligence, enabling them to cope with uncertain factors in the environment and realize automatic allocation and dynamic adjustment of tasks.

[0006] Therefore, it is necessary to provide a new multi-task end-to-end UAV cruising and formation maintenance method that can cope with multiple challenges in complex environments. This method ensures that UAVs can efficiently and reliably complete multi-task requirements in complex scenarios by sensing environmental changes, adjusting the UAV formation form in real time, and autonomously learning the optimal strategy. The innovation of this technology lies not only in its ability to maintain communication connectivity and obstacle avoidance capabilities, but also in the introduction of adaptive strategies to achieve dynamic adjustment of task priorities and optimal configuration of system resources, thereby improving the collaborative working ability of UAV groups in dynamic environments. Summary of the invention

[0007] In view of this, the object of the present invention is a multi-task end-to-end UAV cruising and formation maintenance method, which integrates dynamic formation control, reinforcement learning adaptive strategy and other mechanisms, provides a highly adaptive and robust solution, is suitable for complex, multi-task multi-UAV application scenarios, and significantly improves the operational efficiency of the UAV group and the ability to cope with complex environments, including the following steps:

[0008] Step 1, obtain drone and environment information and input it into the dynamic formation control module to control the drone group to maintain a predetermined formation during flight to avoid obstacles;

[0009] Step 2: According to the changes in the dynamic environment, the adaptive strategy module calculates and outputs the flight strategy and path planning of the drone in real time;

[0010] Step 3: Each drone processes local environment information independently to ensure global coordination of the drone cluster;

[0011] Step 4: The UAV performs cruise and formation maintenance according to the final decision signal generated.

[0012] Specifically, the dynamic formation control module updates the UAV motion according to the synthetic potential field, and the total resultant force calculation formula of the synthetic potential field is:

[0013] F total (q) = F att (q)+∑F rep (q)+∑F drone (q)

[0014] Among them, F total (q) is the total force, which is used to guide the movement direction and speed of the UAV. ∑ represents the sum of all related objects. F att (q) represents the gravitational vector, pointing to the target position, and its calculation formula is: F att (q)=-k att (qq goal ), q represents the current position vector of the drone, qgoal represents the target position vector, k att is the gravitational coefficient, which indicates the strength of gravity, F rep (q) represents the repulsive force vector, pointing away from the obstacle. ρ(q) represents the distance from the drone to the obstacle, ρ0 is the influence range of the repulsive force, and the maximum distance of the repulsive force, k rep is the repulsion coefficient, which indicates the strength of the repulsion. represents the gradient of the distance function, which is directed from the obstacle to the drone, F drone (q) represents the repulsive force vector between drones, and the calculation formula is: d(q): The distance between the current drone and other drones. d0 represents the safe distance between drones. k drone is the repulsion coefficient between drones, Represents the gradient of the distance function, which is directed from other drones to the current drone.

[0015] Specifically, the adaptive strategy module includes the following steps:

[0016] Combine the features of multi-task learning to obtain the current state S t And process the input: S t =MTL(X t ,E t ,P t ) Among them, X t is the state of the drone itself, E t is environmental information, P t Prioritize the tasks;

[0017] Based on the current state S t and priority information to adjust the weight of strategy selection: (Q(S t ,A)+λ·P t W) where λ is the adjustment coefficient, P t is the task priority, W is the weight matrix, A t represents the optimal action at the current moment, A represents the optional action set, and Q represents the action value function;

[0018] Use the Q-learning algorithm to update the action value function Q in combination with future discounted rewards: Among them, α is the learning rate, γ is the discount factor, which is used to measure the importance of future rewards, and A ′ represents the possible action at the next moment, Q(S t ,A t ) is the action value function, which means that in state S t Next, execute action At The expected total reward that can be obtained, R t Indicates immediate reward;

[0019] Using the policy network optimized by multi-task learning, update the policy network parameters by gradient descent to minimize the loss function of policy selection: Among them, θ is the policy network parameter, η is the learning rate, represents the gradient, is the loss function, and the calculation formula of the loss function is:

[0020]

[0021] in, Express expectations.

[0022] Preferably, the UAV independently processing the local environment information in step 3 comprises the following steps:

[0023] UAV i senses itself and its surrounding environment through sensors and exchanges information with neighboring UAVs to form a local environment information set L i and neighboring drone information set N i ;

[0024] UAV i is based on the local environment information set L i and the information set N of neighboring drones i , independently calculate the optimal decision D i , the calculation formula is: Among them, A i is the set of actions that can be performed by drone i, Q(L i ,A i ,N i ) is the action value function, which means that in the local information L i and neighboring drone information N i Next, execute action A i The expected total reward that can be obtained;

[0025] Ensure the decision-making of drone i through communication and information exchange with neighboring drones i The decision-making of its neighboring drones should be consistent with the global goal to avoid decision conflicts, D′ i =Cooperate(D i ,D neighbors ), where D neighbors is the decision set of neighboring drones, Cooperate is the collaborative function used to adjust decisions to avoid conflicts, and D′ i For local decision making after coordination.

[0026] Preferably, the UAV independently processing the local environment information in step 3 comprises the following steps:

[0027] The perceived local environment information set L i and the information set N of neighboring drones i Fusion, generating local state representation, and extracting key features V i , V i =f fusion (L i ,N i ) where f fusion Represents the feature fusion function, the key feature V extracted i As input for subsequent decision making;

[0028] According to the real-time environment and the importance of the task, the priority of the task is dynamically adjusted to generate the task weight W i , to ensure that critical tasks are prioritized;

[0029] Use reinforcement learning algorithm to calculate the value Q(V) of each action in the current local state i ,A i ,W i ), Q(V i ,A i ,W i )=RL(V i ,A i ,W i ), where RL represents the reinforcement learning model, and the Q-value function generated by training is used to evaluate the value of each possible action;

[0030] According to the calculated Q value, select the action with the highest value as the current optimal decision D i , This step ensures that the drone can make the most profitable decision in the current state. i is the set of actions that can be performed by drone i, Q(V i ,A i ,W i ) is the action value function, expressed in the feature vector V i and task weight W i Next, execute action A i The expected total reward that can be obtained;

[0031] By exchanging information with neighboring drones, coordinating and adjusting decisions, conflicting decisions can be avoided and the consistency of drone group behavior can be ensured: D' i =Cooperate(D i ,D neighbors ), where D neighborsis the decision set of neighboring drones, Cooperate is the cooperative function, and D′ i In order to coordinate the local decisions after the coordination, the decisions are fine-tuned through the coordination mechanism so that the individual behaviors in the drone group are compatible with each other.

[0032] Specifically, the collaborative function is used to achieve decision consistency adjustment, including the following steps:

[0033] Drone i collects updated decision information from neighboring drones to form a complete decision information matrix;

[0034] Analyze the decision information matrix and calculate the decision consistency error E between each pair of drones i , that is, the deviation between the path points of each drone at the same time step: E i (j,k)=‖P j ′ (t)-P ′ k (t)‖, where P j ′ (t) and P ′ k (t) represents the adjusted path points of drones j and k at time step t. If the error is greater than a preset tolerance threshold e tol , then it is considered that there is a consistency problem;

[0035] For each pair of drones j and k with consistency error, calculate the consistency adjustment vector ΔP ij , to minimize the deviation of the path, the consistency adjustment vector Among them, α is the adjustment coefficient, which controls the amplitude of adjustment;

[0036] Apply the consistency adjustment vector to the corresponding drones and update their paths to reduce the global consistency error: in, represents the set of drones adjacent to drone i, and the final decision output is the adjusted path P i ″ .

[0037] The beneficial effects of the present invention are as follows: The method of the present invention combines multi-task learning and reinforcement learning, so that the drone can adaptively adjust the flight strategy according to the changes in the environment and give priority to completing key tasks. This dynamic task priority management ensures that different task objectives can collaborate efficiently, reduces task conflicts and maximizes the efficiency of task completion. At the same time, through distributed decision-making and collaborative adjustment mechanisms, the drone group can ensure the coordination and consistency of global behavior. Conflict detection and resolution, consistency adjustment and other steps ensure that the actions between drones will not have path conflicts or interference, thereby maintaining the integrity of the formation. In addition, each drone can make autonomous decisions based on local information and collaborate with other drones through real-time information sharing. This method has high robustness and flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is the overall flow chart of the UAV cruising and formation maintenance method. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all 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.

[0040] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0041] This embodiment proposes a multi-task end-to-end UAV cruising and formation maintenance method, such as Figure 1 As shown, the following steps are included:

[0042] Step 1, obtain drone and environment information and input it into the dynamic formation control module to control the drone group to maintain a predetermined formation during flight to avoid obstacles;

[0043] Step 2: According to the changes in the dynamic environment, the adaptive strategy module calculates and outputs the flight strategy and path planning of the drone in real time;

[0044] Step 3: Each drone processes local environment information independently to ensure global coordination of the drone cluster;

[0045] Step 4: The UAV performs cruise and formation maintenance according to the final decision signal generated.

[0046] In the embodiment, the main function of the dynamic formation control module is to dynamically adjust the relative positions between drones according to the changes in the real-time environment, to ensure that the entire drone group can maintain the predetermined formation form during the flight, while avoiding collisions and loss of communication connections. Generally, the following functions are included: Formation structure maintenance: maintaining the stability of the drone formation in the face of environmental interference (such as wind, obstacles, hostile interference); communication connectivity assurance: ensuring that the communication link between drones is not destroyed and maintaining the collaborative operation capability of the group; obstacle avoidance: when an obstacle appears in the flight path, dynamically adjust the formation form to safely pass or bypass the obstacle.

[0047] Specifically, the dynamic formation control module updates the UAV motion according to the synthetic potential field, and the total resultant force calculation formula of the synthetic potential field is:

[0048] F total (q) = F att (q)+∑F rep (q)+∑F drone (q)

[0049] Among them, F total (q) is the total force, which is used to guide the movement direction and speed of the UAV. ∑ represents the sum of all related objects. F att (q) represents the gravitational vector, pointing to the target position, and its calculation formula is: F att (q)=-k att (qq goal ), q represents the current position vector of the drone, q goal represents the target position vector, k att is the gravitational coefficient, which indicates the strength of gravity, F rep (q) represents the repulsive force vector, pointing away from the obstacle. ρ(q) represents the distance from the drone to the obstacle, ρ0 is the influence range of the repulsive force, and the maximum distance of the repulsive force, k rep is the repulsion coefficient, which indicates the strength of the repulsion. represents the gradient of the distance function, which is directed from the obstacle to the drone, F drone (q) represents the repulsive force vector between drones, and the calculation formula is: The distance between the current drone and other drones, d0 represents the safe distance between drones, k drone is the repulsion coefficient between drones, Represents the gradient of the distance function, which is directed from other drones to the current drone.

[0050] Specifically, the adaptive strategy module includes the following steps:

[0051] Combine the features of multi-task learning to obtain the current state S t And process the input: S t =MTL(X t ,E t ,P t ) Among them, X t is the state of the drone itself, E t is environmental information, P t Prioritize the tasks;

[0052] Based on the current state S t and priority information to adjust the weight of strategy selection: Among them, λ is the adjustment coefficient, P t is the task priority, W is the weight matrix, A t represents the optimal action at the current moment, A represents the optional action set, and Q represents the action value function;

[0053] Use the Q-learning algorithm to update the action value function Q in combination with future discounted rewards: Among them, α is the learning rate, γ is the discount factor, which is used to measure the importance of future rewards, and A ′ represents the possible action at the next moment, Q(S t ,A t ) is the action value function, which means that in state S t Next, execute action A t The expected total reward that can be obtained, R t Indicates immediate reward;

[0054] Using the policy network optimized by multi-task learning, update the policy network parameters by gradient descent to minimize the loss function of policy selection: Among them, θ is the policy network parameter, η is the learning rate, represents the gradient, is the loss function, and the calculation formula of the loss function is:

[0055]

[0056] in, Express expectations.

[0057] In this embodiment, the adaptive strategy module is mainly responsible for adjusting the flight strategy and path planning of the drone in real time according to the changes in the dynamic environment in the multi-task end-to-end drone cruising and formation maintenance method. Its core purpose is to use reinforcement learning technology to enable the drone to adaptively optimize its cruising path and formation decision in a complex and changing environment to achieve the best mission execution effect.

[0058] The adaptive strategy module enables drones to autonomously learn and adjust flight strategies in complex and changing environments through the collaborative work of real-time environmental perception, strategy selection, and strategy optimization. The module uses a deep reinforcement learning algorithm to continuously optimize the drone's cruising path and formation decision-making, thereby improving the efficiency and success rate of drone mission execution. In a multi-task end-to-end drone system, the adaptive strategy module is the key to achieving the intelligence and adaptive capabilities of drone groups.

[0059] Preferably, the UAV independently processing the local environment information in step 3 comprises the following steps:

[0060] UAV i senses itself and its surrounding environment through sensors and exchanges information with neighboring UAVs to form a local environment information set L i and neighboring drone information set N i ;

[0061] UAV i is based on the local environment information set L i and the information set N of neighboring drones i , independently calculate the optimal decision D i , the calculation formula is: Among them, A i is the set of actions that can be performed by drone i, Q(L i ,A i ,N i ) is the action value function, which means that in the local information L i and neighboring drone information N i Next, execute action A i The expected total reward that can be obtained;

[0062] Ensure the decision-making of drone i through communication and information exchange with neighboring drones i The decision-making of its neighboring drones should be consistent with the global goal to avoid decision conflicts, D′ i =Cooperate(D i ,D neighbors ), where D neighbors is the decision set of neighboring drones, Cooperate is the collaborative function used to adjust decisions to avoid conflicts, and D′ i For local decision making after coordination.

[0063] The main function of the distributed decision-making module in this embodiment is to ensure that each drone in the drone group can make decisions independently based on its own and its neighboring drones' local information without relying on the central control system. This distributed decision-making mechanism can enhance the autonomy and robustness of the drone group, enabling the drone formation to maintain efficient mission execution in a dynamic and complex environment.

[0064] Preferably, the UAV independently processing the local environment information in step 3 comprises the following steps:

[0065] The perceived local environment information set L i and the information set N of neighboring drones i Fusion, generating local state representation, and extracting key features V i , V i =f fusion (L i ,N i ) where f fusion Represents the feature fusion function, the key feature V extracted i As input for subsequent decision making;

[0066] According to the real-time environment and the importance of the task, the priority of the task is dynamically adjusted to generate the task weight W i :W i =AdjustPriority(T i ,V i ) to ensure that key tasks are given priority; task priorities are adjusted by analyzing factors such as task time requirements and environmental threat levels;

[0067] Use reinforcement learning algorithm to calculate the value Q(V) of each action in the current local state i ,A i ,W i ): Q(V i ,A i ,W i )=RL(V i ,A i ,W i ), where RL represents the reinforcement learning model, and the Q-value function generated by training is used to evaluate the value of each possible action;

[0068] According to the calculated Q value, select the action with the highest value as the current optimal decision: This step ensures that the drone can make the most profitable decision in the current state. i is the set of actions that can be performed by drone i, Q(V i ,A i ,W i ) is the action value function, expressed in the feature vector V i and task weight W i Next, execute action A i The expected total reward that can be obtained;

[0069] By exchanging information with neighboring drones, coordinating and adjusting decisions, conflicting decisions can be avoided and the consistency of drone group behavior can be ensured: D' i =Cooperate(D i ,D neighbors ), where D neighbors is the decision set of neighboring drones, Cooperate is the cooperative function, and D′ i In order to coordinate the local decisions after the coordination, the decisions are fine-tuned through the coordination mechanism so that the individual behaviors in the drone group are compatible with each other.

[0070] The improved local decision-making module significantly improves the decision-making efficiency and task execution capability of the drone group by enhancing its adaptability to dynamic environments and its ability to coordinate with neighboring drones. The design of this module not only ensures the independence of drones, but also ensures that the entire drone group can coordinate and efficiently execute tasks in complex environments through task priority management and decision-making coordination mechanisms. This improvement enables drones to adjust decisions more flexibly and intelligently when facing multiple tasks and dynamic environments, ensuring the achievement of mission objectives.

[0071] Specifically, the collaborative function is used to achieve decision consistency adjustment, including the following steps:

[0072] Drone i collects updated decision information from neighboring drones to form a complete decision information matrix;

[0073] Analyze the decision information matrix and calculate the decision consistency error E between each pair of drones i , that is, the deviation between the path points of each drone at the same time step: E i (j,k)=‖P j ′ (t)-P ′ k (t)‖, where P j ′ (t) and P ′ k (t) represents the adjusted path points of drones j and k at time step t. If the error is greater than a preset tolerance threshold e tol , then it is considered that there is a consistency problem;

[0074] For each pair of drones j and k with consistency error, calculate the consistency adjustment vector ΔP ij , to minimize the deviation of the path, the consistency adjustment vector Among them, α is the adjustment coefficient, which controls the amplitude of adjustment;

[0075] Apply the consistency adjustment vector to the corresponding drones and update their paths to reduce the global consistency error: in, represents the set of drones adjacent to drone i, and the final decision output is the adjusted path P i ″ .

[0076] The decision-making collaborative computing module ensures that the drone group achieves global coordination based on independent decision-making through sharing of local decisions, conflict detection and resolution, consistency adjustment and feedback loop. The improvement of this module significantly improves the collaborative efficiency and success rate of mission execution of multi-drone systems in complex environments.

[0077] A new multi-task end-to-end UAV cruising and formation maintenance method in this embodiment can cope with multiple challenges in complex environments. This method ensures that UAVs can efficiently and reliably complete multi-task requirements in complex scenarios by sensing environmental changes, adjusting the UAV formation form in real time, and autonomously learning the optimal strategy. The innovation of this technology lies not only in its ability to maintain communication connectivity and obstacle avoidance capabilities, but also in the introduction of adaptive strategies to achieve dynamic adjustment of task priorities and optimal configuration of system resources, thereby improving the collaborative working capabilities of UAV groups in dynamic environments.

[0078] As used herein, the word "preferred" is intended to be used as an example, instance, or illustration. Any aspect or design described herein as "preferred" is not necessarily to be construed as being more advantageous than other aspects or designs. On the contrary, the use of the word "preferred" is intended to present concepts in a specific way. The term "or" as used in this application is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless otherwise specified or clear from the context, "X uses A or B" means any one of the naturally included permutations. That is, if X uses A; X uses B; or X uses both A and B, then "X uses A or B" is satisfied in any of the foregoing examples.

[0079] Moreover, although the present disclosure has been shown and described with respect to one or implementations, those skilled in the art will think of equivalent variations and modifications based on the reading and understanding of this specification and the accompanying drawings. The present disclosure includes all such modifications and variations, and is limited only by the scope of the appended claims. In particular, with respect to the various functions performed by the above-mentioned components (such as elements, etc.), the terms used to describe such components are intended to correspond to any component (unless otherwise indicated) that performs the specified function of the component (such as it is functionally equivalent), even if the structure is not equivalent to the disclosed structure of the function in the exemplary implementation of the present disclosure shown herein. In addition, although the specific features of the present disclosure have been disclosed with respect to only one of several implementations, such features can be combined with one or other features of other implementations that may be desired and advantageous for a given or specific application. Moreover, insofar as the terms "including", "having", "containing" or their variations are used in specific embodiments or claims, such terms are intended to be included in a manner similar to the term "comprising".

[0080] The functional units in the embodiments of the present invention may be integrated into a processing module, or each unit may exist physically separately, or multiple or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. The above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc. The above-mentioned devices or systems may execute the storage method in the corresponding method embodiment.

[0081] To sum up, the above embodiment is an implementation mode of the present invention, but the implementation mode of the present invention is not limited by the embodiment. Any other changes, modifications, substitutions, combinations, and simplifications that deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A multi-task end-to-end UAV cruising and formation maintenance method, characterized in that: The following steps are involved: Step 1, obtain drone and environment information and input it into the dynamic formation control module to control the drone group to maintain a predetermined formation during flight to avoid obstacles; Step 2: According to the changes in the dynamic environment, the adaptive strategy module calculates and outputs the flight strategy and path planning of the drone in real time; Step 3: Each drone processes local environment information independently to ensure global coordination of the drone cluster; Step 4: The UAV performs cruise and formation maintenance according to the finally generated decision signal; The dynamic formation control module updates the UAV motion according to the synthetic potential field. The total resultant force calculation formula of the synthetic potential field is: F total (q)=F att (q)+∑F rep (q)+∑F drone (q), Among them, F total (q) is the total force, which is used to guide the movement direction and speed of the UAV. ∑ represents the sum of all related objects. F att (q) represents the gravitational vector, pointing to the target position, and its calculation formula is: F att (q)=-k att (qq goal ), q represents the current position vector of the drone, q goal represents the target position vector, k att is the gravitational coefficient, which indicates the strength of gravity, F rep (q) represents the repulsive force vector, pointing in the direction away from the obstacle, and its calculation formula is: Among them, ρ(q) represents the distance from the drone to the obstacle, ρ0 is the influence range of the repulsive force, and the maximum distance of the repulsive force, k rep is the repulsion coefficient, which indicates the strength of the repulsion. represents the gradient of the distance function, which is directed from the obstacle to the drone, F drone (q) represents the repulsive force vector between drones, and the calculation formula is: Among them, d(q) represents the distance between the current UAV and other UAVs, d0 represents the safe distance between UAVs, and k drone is the repulsion coefficient between drones, Represents the gradient of the distance function, which is directed from other drones to the current drone.

2. A multi-task end-to-end UAV cruising and formation maintenance method according to claim 1, characterized in that: The adaptive strategy module comprises the following steps: Combine the features of multi-task learning to obtain the current state S t And process the input: S t =MTL(X t ,E t ,P t ) Among them, X t is the state of the drone itself, E t is environmental information, P t Prioritize the tasks; Based on the current state S t and priority information to adjust the weight of strategy selection: Among them, λ is the adjustment coefficient, P t is the task priority, W is the weight matrix, A t represents the optimal action at the current moment, A represents the optional action set, and Q represents the action value function; Using the Q learning algorithm, combined with future discounted rewards, update the action value function Q: Q(S t , Among them, α is the learning rate, γ is the discount factor, which is used to measure the importance of future rewards, and A ′ represents the possible action at the next moment, Q(S t ,A t ) is the action value function, which means that in state S t Next, execute action A t The expected total reward that can be obtained, R t Indicates immediate reward; Using the policy network optimized by multi-task learning, update the policy network parameters by gradient descent to minimize the loss function of policy selection: Among them, θ is the policy network parameter, η is the learning rate, represents the gradient, is the loss function, and the calculation formula of the loss function is: in, Express expectations.

3. A multi-task end-to-end UAV cruising and formation maintenance method according to claim 2, characterized in that: The UAV independently processes local environment information in step 3, including the following steps: UAV i senses itself and its surrounding environment through sensors and exchanges information with neighboring UAVs to form a local environment information set L i and the neighboring drone information set N i ; UAV i is based on the local environment information set L i and the information set N of neighboring drones i , independently calculate the optimal decision D i , the calculation formula is: Among them, A i is the set of actions that can be performed by UAV i, Q(L i ,A i ,N i ) is the action value function, which means that in the local information L i and neighboring drone information N i Next, execute action A i The expected total reward that can be obtained; Ensure the decision-making of drone i through communication and information exchange with neighboring drones i The decision-making of its neighboring drones should be consistent with the global goal to avoid decision conflicts, D′ i =Cooperate(D i ,D neighbors ), where D neighbors is the decision set of neighboring drones, Cooperate is the collaborative function used to adjust decisions to avoid conflicts, and D′ i For local decision making after coordination.

4. A multi-task end-to-end UAV cruising and formation maintenance method according to claim 2, characterized in that: The UAV independently processes local environment information in step 3, including the following steps: The perceived local environment information set L i and the information set N of neighboring drones i Fusion, generating local state representation, and extracting key features V i , V i =f fusion (L i ,N i ) where f fusion Represents the feature fusion function, the key feature V extracted i As input for subsequent decision making; According to the real-time environment and the importance of the task, the priority of the task is dynamically adjusted to generate the task weight W i , to ensure that critical tasks are prioritized; Use reinforcement learning algorithm to calculate the value Q(V) of each action in the current local state i ,A i ,W i ), Q(V i ,A i ,W i )=RL(V i ,A i ,W i ), where RL represents the reinforcement learning model, and the Q-value function generated by training is used to evaluate the value of each possible action; According to the calculated Q value, select the action with the highest value as the current optimal decision D i , This step ensures that the drone can make the most profitable decision in the current state. i is the set of actions that can be performed by drone i, Q(V i ,A i ,W i ) is the action value function, expressed in the feature vector V i and task weight W i Next, execute action A i The expected total reward that can be obtained; By exchanging information with neighboring drones, coordinating and adjusting decisions, conflicting decisions can be avoided and the consistency of drone group behavior can be ensured: D' i =Cooperate(D i ,D neighbors ), where D neighbors is the decision set of neighboring drones, Cooperate is the cooperative function, and D′ i In order to coordinate the local decisions after the coordination, the decisions are fine-tuned through the coordination mechanism so that the individual behaviors in the drone group are compatible with each other.

5. A multi-task end-to-end UAV cruising and formation maintenance method according to claim 3 or 4, characterized in that: The collaborative function is used to achieve decision consistency adjustment, including the following steps: Drone i collects updated decision information from neighboring drones to form a complete decision information matrix; Analyze the decision information matrix and calculate the decision consistency error E between each pair of drones i , that is, the deviation between the path points of each drone at the same time step, and its calculation formula is: E i (j,k)=‖P j ′ (t)-P ′ k (t)‖, Among them, P j ′ (t) and P ′ k (t) represents the adjusted path points of drones j and k at time step t. If the error is greater than a preset tolerance threshold e tol , then it is considered that there is a consistency problem; For each pair of drones j and k with consistency error, calculate the consistency adjustment vector ΔP ij , in order to minimize the deviation of the path, the calculation formula of the consistency adjustment vector is: Among them, α is the adjustment coefficient, which controls the amplitude of adjustment; The consistency adjustment vector is applied to the corresponding UAVs to update their paths to reduce the global consistency error. The update formula is: in, represents the set of drones adjacent to drone i, and the final decision output is the adjusted path P i ″ .

Images