An unmanned aerial vehicle group congestion obstacle avoidance control method

Abstract

The application discloses a kind of unmanned aerial vehicle group congestion obstacle avoidance control methods, including the following steps: real-time perception unmanned aerial vehicle state and its neighbor's environmental information;Congestion detection and strategy solution between unmanned aerial vehicles are realized based on improved consensus algorithm;The path of unmanned aerial vehicle is optimized using multi-agent method, fuel efficiency, task completion degree and safety are considered;Collision is avoided by dynamic formation in congestion environment, ensure overall formation stability;The energy state of each unmanned aerial vehicle is dynamically monitored, and energy supplement or task handover is carried out when necessary.The application is a kind of unmanned aerial vehicle group obstacle avoidance control method based on multi-agent cooperation, reinforcement learning and distributed consensus, aims to solve the problem that how unmanned aerial vehicle group optimizes flight path, avoids collision, reduces energy consumption and ensures task to be successfully completed in congestion environment.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of unmanned aerial vehicles, and particularly relates to a congestion obstacle avoidance control method for a group of unmanned aerial vehicles. BACKGROUND

[0002] With the continuous development of unmanned aerial vehicle technology, unmanned aerial vehicle groups play an important role in many fields, such as environmental monitoring, disaster relief, traffic monitoring, agricultural spraying, etc. However, when unmanned aerial vehicle groups perform cooperative tasks, they face many challenges, especially in complex and dynamic environments. How to effectively avoid congestion and collision to ensure the smooth progress of flight tasks while ensuring efficient use of energy is a key problem.

[0003] Traditional unmanned aerial vehicle obstacle avoidance control methods usually rely on centralized algorithms or single-agent decision-making, which can easily lead to a sharp increase in computational complexity in multi-unmanned aerial vehicle cooperative operations, making it difficult to achieve real-time and efficient decision-making. In addition, in complex environments, the dynamic changes of obstacles and other aircraft require the obstacle avoidance strategy to have strong adaptability and flexibility, and traditional methods often struggle to cope with these changes.

[0004] In order to solve these problems, in recent years, distributed control methods based on multi-agent cooperation have been widely applied. This kind of method avoids the bottleneck of centralized computing through information sharing and cooperative decision-making among unmanned aerial vehicles, improving the scalability and real-time performance of the system. At the same time, with the increasing diversification of unmanned aerial vehicle application scenarios, energy constraints have become another important limiting factor. The limited battery life of unmanned aerial vehicles and task requirements force researchers to consider energy consumption in flight path planning and task allocation. How to optimize energy use while ensuring task completion is an important research direction in current unmanned aerial vehicle group control. SUMMARY

[0005] Therefore, the purpose of the present application is to propose a congestion obstacle avoidance control method for a group of unmanned aerial vehicles, comprising the following steps:

[0006] Step 1, real-time perception of the state of unmanned aerial vehicles and the environmental information of their neighbors;

[0007] Step 2, congestion detection and strategy solving among unmanned aerial vehicles based on an improved consensus algorithm;

[0008] Step 3, optimization of the path of unmanned aerial vehicles using multi-agent methods, taking into account fuel efficiency, task completion and safety;

[0009] Step 4, collision avoidance through dynamic formation in congested environments to ensure overall formation stability;

[0010] Step 5, dynamic monitoring of the energy state of each unmanned aerial vehicle, and energy replenishment or task handover if necessary.

[0011] Specifically, the real-time perception of the drone status and its neighboring environmental information includes the following steps:

[0012] Status collection: UAV U i The sensor obtains its own position, speed, and energy state information in real time, which is expressed as a state vector s i (t).

[0013] Neighbor identification: within the communication range R c In the network, the neighbor set is identified through broadcast communication

[0014] State sharing: Broadcast the drone’s state information to neighboring drones.

[0015] Specifically, the congestion detection includes the following steps:

[0016] At each time step, conflict detection is first performed to predict each pair of drones that may collide;

[0017] Calculate the time to shortest distance for each pair of drones, measuring the time it takes for two drones to reach their closest point: Among them, p i and p j :UAV U i and U j The position vector, v i and v j :UAV U i and U j The velocity vector of TCPA ij When >0, it means that the two drones may approach a certain minimum distance in the future;

[0018] Calculate the shortest distance for each pair of drones, measuring the minimum distance between the two drones to reach the closest point:

[0019] CPA ij =‖p i +TCPA ij ·v i -(p j +TCPA ij ·v j )‖

[0020] If CPA ij <d safe , then it is considered that there is a potential conflict between the two UAVs, where d safe is the set safety distance threshold;

[0021] Each pair of potentially conflicting UAVs (U i,U j ) will calculate the conflict level based on its time to shortest distance and shortest distance, and set a resolution priority for each pair of conflicts. The conflict level calculation is: Among them, w1 and w2 are weight coefficients, which are used to adjust the impact of time to shortest distance and shortest distance on the conflict level. The higher the conflict level, the greater the need for priority resolution.

[0022] Specifically, the strategic solution includes the following steps:

[0023] Each UAV that detects a potential conflict will generate multiple candidate avoidance strategies, each candidate strategy u i,k Contains the following information: Speed ​​adjustment Δv i,k , change speed to avoid conflict, and adjust heading Δθ i,k , change the heading angle, and adjust the height Δh i,k , change the flight altitude;

[0024] The goal of the candidate strategy is to reduce the risk of collision and minimize the energy consumption C energy (u i,k );

[0025] Each drone will broadcast its candidate strategy set to neighboring drones Have all potentially conflicting drones share strategic information;

[0026] Definition and initialization of consensus variables. Each drone defines a consensus variable y i (t), represents the avoidance strategy selection at the current time step t. In the initial state, the candidate strategy with the minimum energy consumption is selected as the initial value:

[0027] At each time step, each drone will update the consensus variable based on the information of its neighbors. The goal is to gradually reach a consensus among the entire drone group and use the Laplace consensus algorithm to update the consensus variable: Among them, ∈ is the learning rate, which controls the step size of each update, y j (t) is the neighbor drone U j consensus variable at time step t;

[0028] When the consensus variable y i When (t) converges to a stable value, it is considered that the UAV group has reached a consensus, and each UAV executes the final avoidance strategy according to the consensus variable, and the position is updated: p i (t+1)=p i (t)+v i (t)Δt, velocity update: v i (t+1)=vi (t)+Δv i,k , Energy Update: E i (t+1)=E i (t)-C energy (u i,k ), p i (t) is the UAV U i The three-dimensional position of the drone at time t, v i (t) is the UAV U i The velocity vector of the drone at time t, E i (t) is the UAV U i Energy state of the drone at time t.

[0029] The multi-agent approach to optimizing the path of a drone, taking into account fuel efficiency, mission completion, and safety, includes the following steps:

[0030] A multi-objective reward function is designed: R i (t) = w1R fuel (t)+w2R safety (t)+w3R task (t), where w1, w2, and w3 are the weights of each target, which determine the importance of each target in path optimization. fuel (t) represents the fuel efficiency reward, which is based on energy consumption. The less energy consumption, the greater the reward. R safety (t) represents the safety reward, which is based on the minimum distance to obstacles or other drones. The greater the distance, the higher the reward. R task (t) represents the task completion reward, which is based on the degree of achievement of the task goal;

[0031] Each drone U i The state space of is defined as a vector containing its current position, velocity, energy and state information of the surrounding environment. Among them, p i (t) represents the UAV U i The three-dimensional position vector at time t, v i (t) represents the UAV U i The velocity vector, E i (t) represents the UAV U i The remaining energy, Obstacle information, indicating the nearest obstacle and its location, Mission information, indicating the progress of the drone's current mission;

[0032] Designing actor networks Used according to the state s i (t) Generate the optimal action a i(t), the goal is to maximize the cumulative reward: Among them, θ i are the parameters of the actor network;

[0033] Design Reviewer Network V i (s i ), used to estimate the state s i The value function of , which is the expected reward in a given state;

[0034] Design advantage function A i (t) measures the quality of the currently selected action relative to the average level and is calculated as: i (t) = R i (t)+γV i (s i (t+1))-V i (s i (t)), γ is the discount factor, and the actor adjusts the strategy through the advantage function;

[0035] The parameters of the actor network are updated strategically according to the gradient of the advantage function, and the critic network is updated by minimizing the mean squared error (MSE).

[0036] After the training is completed, the optimized strategy is used for path planning. At each time step, the UAV moves according to its current state s. i (t) Generate the optimal action a through the actor network i (t), after executing the action, the drone will update its position, velocity and energy state.

[0037] The multi-agent method adopts a parameter sharing mechanism and a strategic communication mode, and includes the following steps:

[0038] Sharing of state information: Each drone will share its state information s at each time step t i (t) Broadcast to its neighbors, and the status information is passed to the neighboring drones the choice of strategies for adjusting them;

[0039] Sharing of action information, each drone U i According to the state s i (t) Generate an action a i (t), that is, it makes flight decisions based on the current environment state, and the UAV sends its selected action a through wireless communication i (t) is passed to its neighboring drones This allows neighboring drones to adjust their strategies and share experiences;

[0040] Sharing of rewards and experience, each drone chooses an action ai (t) and environmental feedback to get immediate reward R i (t), the drone will give its reward R i (t) is stored as an experience quadruple together with the action taken and the state: i (t)=(s i (t),a i (t),R i (t),s i (t+1)), is broadcasted to other neighboring drones so that they can use this information for strategy updates;

[0041] At each time step t, each drone sends its experience quadruple to the global experience pool, aggregates the experience of all drones in the experience pool, randomly extracts batches of experience from the experience pool for training, and updates the policy network parameters of all drones: Among them, γ is the discount factor, which controls the impact of future rewards, and α is the learning rate, which adjusts the step size of each parameter update;

[0042] Each drone generates new control inputs based on the shared policy network and adjusts them according to the policies of other drones. Each agent adjusts its policy after each update. Broadcast to all neighboring drones via wireless communication After receiving the policy, the neighboring drone updates its local policy network, enabling it to make decisions based on the shared knowledge.

[0043] Specifically, the dynamic monitoring of the energy status of each drone and the energy replenishment or task handover when necessary include the following steps:

[0044] When the energy of a certain drone is lower than the set threshold E threshold When , the task transfer mechanism is started;

[0045] Select the appropriate drone to take over the task and use the path planning algorithm to calculate the task takeover path;

[0046] Replacing drones to join the formation, keeping the formation stable, and adjusting paths to avoid conflicts;

[0047] When the drone is running low on energy, a replenishment mechanism and task handover are used to ensure the smooth completion of the mission.

[0048] The beneficial effects of this invention are as follows: To effectively respond to dynamic environmental changes, this technical solution, a drone swarm obstacle avoidance control method based on multi-agent collaboration, reinforcement learning, and distributed consensus, aims to solve the problem of how drone swarms can optimize flight paths, avoid collisions, reduce energy consumption, and ensure successful mission completion in congested environments. Through a task transfer and path adjustment mechanism, if a local drone is unable to continue a mission due to insufficient energy, the task can be promptly assigned to other drones, thus avoiding mission interruptions and improving the efficiency and robustness of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 The overall flow chart of a real-time obstacle avoidance UAV trajectory planning method is shown. DETAILED DESCRIPTION

[0050] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It should be understood that the embodiments described herein are merely some, rather than all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0051] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0052] like Figure 1 As shown, this embodiment proposes a congestion avoidance control method for a drone swarm, comprising the following steps:

[0053] Step 1: Real-time perception of the drone status and its neighbors’ environmental information;

[0054] Step 2: Implement congestion detection and strategy resolution between drones based on the improved consensus algorithm;

[0055] Step 3: Use a multi-agent approach to optimize the UAV’s path, taking into account fuel efficiency, mission completion, and safety.

[0056] Step 4: Avoid collisions through dynamic formation in congested environments to ensure overall formation stability;

[0057] Step 5: Dynamically monitor the energy status of each drone and perform energy replenishment or task handover when necessary.

[0058] Specifically, the real-time perception of the drone status and its neighboring environmental information includes the following steps:

[0059] Status collection: UAV U iThe sensor obtains its own position, speed, and energy state information in real time, which is expressed as a state vector s i (t).

[0060] Neighbor identification: within the communication range R c In the network, the neighbor set is identified through broadcast communication

[0061] State sharing: Broadcast the drone’s state information to neighboring drones.

[0062] Specifically, the congestion detection includes the following steps:

[0063] At each time step, conflict detection is first performed to predict each pair of drones that may collide;

[0064] Calculate the time to shortest distance for each pair of drones, measuring the time it takes for two drones to reach their closest point: Among them, p i and p j :UAV U i and U j The position vector, v i and v j :UAV U i and U j The velocity vector of TCPA ij When >0, it means that the two drones may approach a certain minimum distance in the future;

[0065] Calculate the shortest distance for each pair of drones, measuring the minimum distance between the two drones to reach the closest point:

[0066] CPA ij =‖p i +TCPA ij ·v i -(p j +TCPA ij ·v j )‖

[0067] If CPA ij <d safe , then it is considered that there is a potential conflict between the two UAVs, where d safe is the set safety distance threshold;

[0068] Each pair of potentially conflicting UAVs (U i ,U j ) will calculate the conflict level based on its time to shortest distance and shortest distance, and set a resolution priority for each pair of conflicts. The conflict level calculation is: Among them, w1 and w2 are weight coefficients, which are used to adjust the impact of time to shortest distance and shortest distance on the conflict level. The higher the conflict level, the greater the need for priority resolution.

[0069] Specifically, the strategic solution includes the following steps:

[0070] Each UAV that detects a potential conflict will generate multiple candidate avoidance strategies, each candidate strategy u i,k Contains the following information: Speed ​​adjustment Δv i,k , change speed to avoid conflict, and adjust heading Δθ i,k , change the heading angle, and adjust the height Δh i,k , change the flight altitude;

[0071] The goal of the candidate strategy is to reduce the risk of collision and minimize the energy consumption C energy (u i,k );

[0072] Each drone will broadcast its candidate strategy set to neighboring drones Have all potentially conflicting drones share strategic information;

[0073] Definition and initialization of consensus variables. Each drone defines a consensus variable y i (t), represents the avoidance strategy selection at the current time step t. In the initial state, the candidate strategy with the minimum energy consumption is selected as the initial value:

[0074] At each time step, each drone will update the consensus variable based on the information of its neighbors. The goal is to gradually reach a consensus among the entire drone group and use the Laplace consensus algorithm to update the consensus variable: Among them, ∈ is the learning rate, which controls the step size of each update, y j (t) is the neighbor drone U j consensus variable at time step t;

[0075] When the consensus variable y i When (t) converges to a stable value, it is considered that the UAV group has reached a consensus, and each UAV executes the final avoidance strategy according to the consensus variable, and the position is updated: p i (t+1)=p i (t)+v i (t)Δt, velocity update: v i (t+1)=v i (t)+Δv i,k , Energy Update: E i (t+1)=E i (t)-C energy(u i,k ), p i (t) is the UAV U i The three-dimensional position of the drone at time t, v i (t) is the UAV U i The velocity vector of the drone at time t, E i (t) is the UAV U i Energy state of the drone at time t.

[0076] The multi-agent approach to optimizing the path of a drone, taking into account fuel efficiency, mission completion, and safety, includes the following steps:

[0077] A multi-objective reward function is designed: R i (t) = w1R fuel (t)+w2R safety (t)+w3R task (t), where w1, w2, and w3 are the weights of each target, which determine the importance of each target in path optimization. fuel (t) represents the fuel efficiency reward, which is based on energy consumption. The less energy consumption, the greater the reward. R safety (t) represents the safety reward, which is based on the minimum distance to obstacles or other drones. The greater the distance, the higher the reward. R task (t) represents the task completion reward, which is based on the degree of achievement of the task goal;

[0078] Each drone U i The state space of is defined as a vector containing its current position, velocity, energy and state information of the surrounding environment. Among them, p i (t) represents the UAV U i The three-dimensional position vector at time t, v i (t) represents the UAV U i The velocity vector, E i (t) represents the UAV U i The remaining energy, Obstacle information, indicating the nearest obstacle and its location, Mission information, indicating the progress of the drone's current mission;

[0079] Designing actor networks Used according to the state s i (t) Generate the optimal action a i (t), the goal is to maximize the cumulative reward: Among them, θ i are the parameters of the actor network;

[0080] Design Reviewer Network Vi (s i ), for estimating the value function of state s i , i.e., the expected reward in a given state;

[0081] Designing advantage function A i (t), which measures how good the current chosen action is relative to the average level, the formula is: A i (t) = R i (t) + γV i (s i (t+1)) - V i (s i (t)), γ is the discount factor, and the actor adjusts the policy through the advantage function;

[0082] The parameters of the actor network are updated according to the gradient of the advantage function, and the critic network is updated by minimizing the mean square error (MSE) to update the value function;

[0083] After training is completed, the optimized policy is used for path planning, and at each time step, the UAV generates the optimal action a i (t) through the actor network according to its current state s i (t), and after executing the action, the UAV updates its position, speed and energy state.

[0084] Specifically, the multi-agent algorithm optimizes the path according to the multi-objective reward function, which can effectively balance energy efficiency, safety and task completion. During the training process, the agents cooperate through shared policies, ensuring efficient operation of the UAV swarm in complex environments and enabling real-time adjustments based on environmental and task requirements.

[0085] In the method of congestion obstacle avoidance control of UAV considering energy constraints, through the parameter sharing mechanism and policy communication, the UAV can learn from the strategies of other UAVs during the training process, making the strategy of each agent (i.e., UAV) more general and effective. This method can improve the overall collaboration of the multi-UAV system, reduce conflicts between individuals, and speed up task completion.

[0086] The multi-agent method adopts a parameter sharing mechanism and a policy communication mode, including the following steps:

[0087] Sharing of state information, each UAV broadcasts its state information s i (t) to its neighbors at each time step t, and the state information is passed to neighbor UAVs to adjust their policy selection;

[0088] Sharing of action information, each UAV Ui According to the state s i (t) generates an action a i (t), that is, it makes flight decisions based on the current environment state, and the UAV transmits its selected action a i (t) to its neighbor UAVs through wireless communication Thus allowing neighbor UAVs to adjust their strategies and share experiences;

[0089] Reward and experience sharing, each UAV gets an immediate reward R i (t) according to its selected action a i (t), the UAV will store its reward R i (t) with the action taken and the state as experience quadruple: ε i (t) = (s i (t), a i (t), R i (t), s i (t+1)) is broadcast to other neighbor UAVs so that they can use this information to update their strategies;

[0090] At each time step t, each UAV sends its experience quadruple to the global experience pool, where the experiences of all UAVs are aggregated, and a batch of experiences is randomly drawn from the experience pool for training, updating the policy network parameters of all UAVs: Where γ is the discount factor, controlling the influence of future rewards, and α is the learning rate, adjusting the step size of each parameter update;

[0091] Each UAV generates new control inputs based on the shared policy network and adjusts according to the strategies of other UAVs, and each agent updates its policy through wireless communication to all neighbor UAVs After the neighbor UAVs receive the policy, they update their local policy network so that they can make decisions based on shared knowledge.

[0092] In the method of congestion avoidance control of UAVs considering energy constraints, task transfer and path adjustment is a key link, especially when the energy of a UAV is insufficient to complete the current task, through the task transfer mechanism, the continuity of the task can be ensured, and through the re-planning of the path, the task is allocated to other UAVs. This process involves energy awareness, task allocation, path planning and formation adjustment, etc., to ensure that the UAV swarm can still complete the task efficiently and cooperatively under energy constraints.

[0093] Specifically, the dynamic monitoring of the energy state of each UAV, and the energy supplement or task transfer when necessary, includes the following steps:

[0094] When the energy of a certain UAV is lower than the set threshold E threshold , the task transfer mechanism is started;

[0095] The appropriate UAV is selected to take over the task, and the path planning algorithm is used to calculate the task takeover path;

[0096] The replacement UAV joins the formation, keeps the formation stable, and adjusts the path to avoid conflicts;

[0097] When the energy of the UAV is insufficient, the task is ensured to be completed successfully through the replenishment mechanism and the task handover.

[0098] The word "preferred" is used herein as a term of art to denote features that can be used in embodiments, examples, or implementations. Any aspect or design described herein as "preferred" is not necessarily to be construed as being more advantageous than other aspects or designs. The use of the word preferred is intended to present a concept in a particular manner. The term "or" as used in this application is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise, or as is clear from the context, the phrase "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, the phrase "X employs A or B" is satisfied by any of the following instances: X employs A; X employs B; or X employs both A and B. In addition, the articles "a" and "an" as used in this application are intended to mean one or more unless otherwise specified or clear from the context to be directed to a singular form.

[0099] Moreover, although the present disclosure has been illustrated and described with respect to one or more implementations, equivalent alterations and modifications will occur to others skilled in the art based on the foregoing description and illustrations. The present disclosure includes all such modifications and alterations and is limited only by the scope of the following claims. In particular, with respect to the various functions performed by the above described components (e.g., elements, etc.), the terms (including a reference to a "means") used to describe such components are intended to correspond, unless otherwise indicated or unless it is clear from the context, to any component which performs the described functionality (e.g., that is functionally equivalent), whether or not the structure is structurally equivalent to the structure shown. In addition, while a particular feature of the disclosure can have been disclosed with respect to only one of several implementations, such feature can be combined with one or other features of the other implementations as can be desired and advantageous for any given or particular application. Furthermore, structures and functionality presented as discrete components in the example configurations can be implemented as a combined structure or component. Such modifications to particular implementations are not to be construed as modifications to the present disclosure. Furthermore, terms like "include", "has", "with", or variants thereof do not exclude a possibility of additional elements or steps.

[0100] The functional units in the embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or multiple or more units may be integrated into a single module. The aforementioned 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 aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk, etc. The aforementioned devices or systems may execute the storage method in the corresponding method embodiment.

[0101] In summary, the above embodiment is one implementation method of the present invention, but the implementation method of the present invention is not limited to the described 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 scope of protection of the present invention.

Claims

1. A congestion avoidance control method for a drone swarm, characterized in that: The steps include: Step 1: Real-time perception of the drone’s status and its neighbors’ environmental information; Step 2: Implement congestion detection and strategy resolution between drones based on the improved consensus algorithm; Step 3: Utilize a multi-agent approach to optimize the UAV’s path, taking into account fuel efficiency, mission completion, and safety. Step 4: Avoid collisions through dynamic formation in congested environments to ensure overall formation stability; Step 5: Dynamically monitor the energy status of each drone and perform energy replenishment or task handover when necessary; The real-time perception of the drone status and its neighboring environmental information includes the following steps: Status collection: UAV U i The sensor obtains its own position, speed, and energy state information in real time, which is expressed as a state vector s i (t); Neighbor identification: within the communication range R c In the network, the neighbor set is identified through broadcast communication State sharing: broadcasting the drone’s state information to neighboring drones; The congestion detection comprises the following steps: At each time step, conflict detection is first performed to predict each pair of drones that may collide; Calculate the time to shortest distance TCPA for each pair of drones ij , measures the time it takes for two drones to reach their closest point, Among them, p i and p j UAV U i and U j The position vector, v i and v j UAV U i and U j The velocity vector of TCPA ij When >0, it means that the two drones may approach a certain minimum distance in the future; Calculate the shortest distance CPA for each pair of drones ij , measures the minimum distance between two drones to reach the closest point: CPA ij =‖p i +TCPA ij ·v i -(p j +TCPA ij ·v j )‖ If CPA ij <d safe , then it is considered that there is a potential conflict between the two UAVs, where d safe is the set safety distance threshold; Each pair of potentially conflicting UAVs (U i ,U j ) will calculate the conflict level based on its time to shortest distance and shortest distance, and set a resolution priority for each pair of conflicts. The conflict level calculation is: Among them, w1 and w2 are weight coefficients, which are used to adjust the impact of time to shortest distance and shortest distance on the conflict level. The higher the conflict level, the greater the need for priority resolution; The strategic solution includes the following steps: Each UAV that detects a potential conflict will generate multiple candidate avoidance strategies, each candidate strategy u i,k Contains the following information: Speed ​​adjustment Δv i,k , change speed to avoid conflict, and adjust heading Δθ i,k , change the heading angle, and adjust the height Δh i,k , change the flight altitude; The goal of the candidate strategy is to reduce the risk of collision and minimize the energy consumption C energy (u i,k ); Each drone will broadcast its candidate strategy set to neighboring drones Have all potentially conflicting drones share strategic information; Definition and initialization of consensus variables. Each drone defines a consensus variable y i (t), represents the avoidance strategy selection at the current time step t, y i (t) is the neighbor drone U i The consensus variable at time step t, in the initial state, selects the candidate strategy with the minimum energy consumption as the initial value: At each time step, each drone will update the consensus variable based on the information of its neighbors. The goal is to gradually reach a consensus among the entire drone swarm and use the Laplace consensus algorithm to update the consensus variable. When the consensus variable y i When (t) converges to a stable value, it is considered that the UAV group has reached a consensus, and each UAV executes the final avoidance strategy according to the consensus variable, and the position is updated: p i (t+1)=p i (t)+v i (t)Δt, velocity update: v i (t+1)=v i (t)+Δv i,k , Energy Update: E i (t+1)=E i (t)-C energy (u i,k ), p i (t) is the UAV U i The three-dimensional position of the drone at time t, v i (t) is the UAV U i The velocity vector of the drone at time t, E i (t) is the UAV U i The energy state of the UAV at time t, Δt is the time change value.

2. The method for controlling a swarm of drones from congestion and avoiding obstacles according to claim 1, characterized in that: The multi-agent approach to optimizing the path of a drone, taking into account fuel efficiency, mission completion, and safety, includes the following steps: A multi-objective reward function is designed: R i (t) = w1R fuel (t)+w2R safety (t)+w3R task (t), where w1, w2, and w3 are the weights of each target, which determine the importance of each target in path optimization. fuel (t) represents the fuel efficiency reward, which is based on energy consumption. The less energy consumption, the greater the reward. R safety (t) represents the safety reward, which is based on the minimum distance to obstacles or other drones. The greater the distance, the higher the reward. R task (t) represents the task completion reward, which is based on the degree of achievement of the task goal; Each drone U i The state space of is defined as a vector containing the position, velocity, energy and state information of the surrounding environment at time t. Among them, p i (t) represents the UAV U i The three-dimensional position at time t, v i (t) represents the UAV U i The velocity vector at time t, E i (t) represents the UAV U i The remaining energy at time t, Obstacle information, indicating the nearest obstacle and its location, Mission information, indicating the progress of the drone's current mission; Designing actor networks Used according to the state s i (t) Generate the optimal action a i (t), the goal is to maximize the cumulative reward: Among them, θ i are the parameters of the actor network; Design Reviewer Network To estimate the state s i The value function of , which is the expected reward in a given state; Design advantage function A i (t) measures the quality of the currently selected action relative to the average level and is calculated as: γ is the discount factor, and the actor adjusts the strategy through the advantage function; The parameters of the actor network are updated strategically according to the gradient of the advantage function, and the critic network is updated by minimizing the mean squared error to update the value function. After the training is completed, the optimized strategy is used for path planning. At each time step, the UAV moves according to its current state s. i (t) Generate the optimal action a through the actor network i (t), after executing the action, the drone will update its position, velocity and energy status.

3. The method for controlling a swarm of drones from congestion and avoiding obstacles according to claim 2, characterized in that: The multi-agent method adopts a parameter sharing mechanism and a strategic communication mode, and includes the following steps: Sharing of state information: Each UAV will share its own state information s at each time step t i (t) Broadcast to its neighbors, and the status information is passed to the neighboring drones the choice of strategies for adjusting them; Sharing of action information, each drone U i According to the state s i (t) Generate an action a i (t), that is, it makes flight decisions based on the current environment state, and the UAV sends its selected action a via wireless communication. i (t) is passed to its neighboring drones This allows neighboring drones to adjust their strategies and share experiences; Sharing of rewards and experience, each drone chooses an action a i (t) and environmental feedback to get immediate reward R i (t), the drone will give its reward R i (t) is stored as an experience quadruple together with the action taken and the state: i (t)=(s i (t),a i (t),R i (t),s i (t+1)), is broadcasted to other neighboring drones so that they can use this information for strategy updates; At each time step t, each drone sends its experience quadruple to the global experience pool, aggregates the experience of all drones in the experience pool, randomly extracts batches of experience from the experience pool for training, and updates the policy network parameters of all drones; Each drone generates new control inputs based on the shared policy network and adjusts them according to the policies of other drones. After each update, each agent will Broadcast to all neighboring drones via wireless communication After receiving the strategy, the neighboring drone updates the local strategy network and can make decisions based on the shared knowledge.

4. The method for controlling a swarm of drones from congestion and avoiding obstacles according to claim 3, wherein: The dynamic monitoring of the energy status of each drone and the energy replenishment or task handover when necessary include the following steps: When the energy of a drone is lower than the set threshold E threshold When , the task transfer mechanism is started; Select the appropriate drone to take over the task and use the path planning algorithm to calculate the task takeover path; Replacing drones to join the formation, keeping the formation stable, and adjusting paths to avoid conflicts; When the drone is running low on energy, a replenishment mechanism and task handover are used to ensure the smooth completion of the mission.

Images