43 results about "Leader follower" patented technology

The invention discloses a multi-aircraft cooperative formation flight path planning method based on a leader and follower model, and relates to the technical field of environment perception and unmanned aerial vehicle cluster cooperation. The method comprises the following steps of: firstly, designing a multi-agent double delay depth deterministic strategy gradient (LFMATD3) based on a leader-follower model, and converting an optimization problem model into a Markov decision process model by introducing an artificial potential field model and a reward function; and secondly, constructing an independent agent for each unmanned aerial vehicle, optimizing a behavior strategy of the unmanned aerial vehicle by combining a reward function based on an algorithm framework of deep reinforcement learning, and performing flight path planning and realizing dynamic formation control. The method provided by the invention can effectively improve the formation stability and collaboration of the unmanned aerial vehicles in a complex environment.

The invention provides an unmanned aerial vehicle formation conflict avoidance control method and system and a medium, and the method comprises the steps: introducing a virtual leader-follower-based Stackelberg game architecture, enabling a virtual leader unmanned aerial vehicle to adaptively adjust the trajectory according to the formation state, and enabling the follower unmanned aerial vehicle to maintain the stability of the formation while completing a set tracking task; constructing an obstacle avoidance penalty term based on a speed obstacle method, and embedding the obstacle avoidance penalty term into an optimization objective function of the follower unmanned aerial vehicle to ensure that the follower unmanned aerial vehicle realizes collision avoidance in an obstacle environment; and respectively solving Hamiltonian-Jacobian-Bellman equations corresponding to the leader unmanned aerial vehicle and the follower unmanned aerial vehicle by adopting a single-network ADP algorithm, and generating a controller in real time. According to the invention, the problems of safe obstacle avoidance and tracking control of a multi-unmanned aerial vehicle system with formation stability requirements are effectively solved.

The invention relates to the technical field of security management, and discloses a security leadership intelligent evaluation method and system based on a knowledge graph, and the method comprises the steps: constructing a security decision cognitive load knowledge graph, and building a structured cognitive load mapping network; multi-modal cognitive load monitoring is achieved, physiological and behavior data of a tested person are collected, and multi-modal data fusion analysis is carried out; performing an adaptive cognitive load test, generating an adversarial limit scene, dynamically adjusting task complexity, and determining a cognitive resource critical point; analyzing attention resource allocation efficiency, and identifying a resource allocation strategy mode; quantifying a cognitive efficiency index, and evaluating decision-making efficiency and multi-target balance capability in a high-pressure environment; safety leader evaluation is extended from surface behavior observation to deep cognitive process analysis, and the cognitive limit of a leader in an extreme safety situation is accurately identified.

The application provides a multi-agent system mean square consensus control method under hybrid attack, relates to the technical field of intelligent control, and comprises the following steps: establishing a multi-agent system model, designing a controller, on the basis, constructing an error system between a follower agent and a leader, and establishing a mean square consensus condition of the multi-agent system under a deception attack and a DOS attack, so that the multi-agent system is controlled to realize leader-following mean square consensus. The application improves the control strategy by comprehensively considering the possible deception attack and DOS attack during the working period of the multi-agent system, so that the leader-follower mean square bounded consensus is realized, and the control efficiency and control precision are improved.

The invention discloses a nonlinear multi-agent system double-clock asynchronous hybrid neural adaptive control method, and relates to the technical field of nonlinear multi-agent system cooperative control. According to the method, a double-clock asynchronous framework is provided, time decoupling is carried out on updating of the leader observer and updating of the local observer, the limitation of synchronous updating of all assemblies is broken through, and the leader observer and the local assembly are made to operate independently; an event trigger pulse mechanism is designed, sampling is carried out only when a specific event occurs, the communication and calculation cost is remarkably reduced, the event trigger mechanism allows each agent to autonomously determine a trigger moment, and self-adaptive resource allocation between heterogeneous dynamic agents is achieved; and the numerical value of the nonlinear function is simulated and estimated by using the neural network, so that approximate state information can still be obtained under different conditions. And the weight of the neural network is only updated at the triggering moment, so that the resource consumption in the learning process is reduced.

The embodiment of the invention provides an edge computing system, an online action method of the edge computing system, an online action network parameter training method, electronic equipment, a storage medium and a program product, and relates to the technical field of machine learning. The method comprises the following steps: generating an action space of each leader agent based on an online action network parameter and an observation state space of each leader agent, executing the action space of each leader agent, and updating a system state space according to an execution result; and obtaining an observation state space of each follower agent according to the updated system state space, generating and executing an action space of each follower agent according to the online action network parameter and the observation state space of each follower agent, and performing reinforcement learning training on the online action network parameter. According to the embodiment of the invention, based on the two-stage action that the leader firstly acts and the follower then acts, the accuracy of performing reinforcement learning training is improved.

The application provides a kind of multi-agent system control method under the condition of having saturation constraint and time delay, it is related to intelligent control technical field, comprising: establishing multi-agent system model, wherein, virtual leader is established between leader and follower agent, follower communicates with virtual leader, virtual leader communicates with leader, on this basis, controller is designed based on saturation constraint and communication time delay, error system between follower agent and leader is constructed, consistency condition is established, and the leader-following consistency of multi-agent system is controlled.The application is aimed at the problem that the dimensions of leader and follower in the model are different, a virtual leader is established between leader and follower agent, and the communication between actual leader and follower is completed.In addition, in view of the actual situation that the inherent properties of agent are limited, the control protocol is adjusted based on saturation constraint information and communication time delay, so that the leader-following consistency of the system is realized.

According to the group decision-making method based on the leader-follower dynamic game, a leader-follower hierarchical adjustment rule is designed to carry out iterative adjustment on an expert evaluation matrix, control and stability of a leader on a decision-making direction are guaranteed, bidirectional optimization is formed through feedback of the follower, and the decision-making efficiency is improved. The authority and the democratic are effectively coordinated, the group consensus degree is remarkably improved, the number of iterations is reduced, and the consensus achievement efficiency is improved. The method comprises the following steps: S1, collecting an evaluation matrix expressed by experts to hesitate a fuzzy language term set; s2, clustering experts through distance measurement and determining intra-class and clustering weights; s3, calculating multi-layer consensus degree to measure and evaluate consistency; s4, if the group consensus degree does not reach the preset threshold value, iteratively adjusting the expert evaluation matrix according to a hierarchical adjustment rule until the expert evaluation matrix reaches the standard; and S5, sorting the schemes by using an approximate positive and negative ideal solution.

The application discloses a kind of group consensus control methods of leader-following nonlinear multi-agent system, comprising: step one: in group multi-agent system, sub-system is divided;Select an agent as leader agent in each sub-system;Step two: each agent is regarded as a mass point obeying single integrator motion model, and the nonlinear dynamics model of each agent in group multi-agent system is established;Step three: the communication connection network between agent is established;Step four: design control protocol and adaptive state observer, initialize each agent state value and state observation value;Step five: the corresponding control protocol is calculated by the current state value of each agent and convergence target, and each agent executes next action;Step six: the adaptive law is calculated using the current state and observation value of agent;Step seven: the state value of each agent after executing action is obtained using state observer.

The application belongs to the field of multi-agent system control, and relates to a finite time consensus control method for a leader-follower multi-agent system, comprising the following steps: constructing a communication topology graph G of the leader-follower multi-agent system; the leader-follower multi-agent system comprises a plurality of followers and a leader; constructing a multi-agent dynamics system; the multi-agent dynamics system comprises a leader dynamics system and a follower dynamics system; performing finite time consensus control on the leader-follower multi-agent system by using a traction control method based on the communication topology graph G and the multi-agent dynamics system; in the traction control, the topological condition is relaxed, the traction control gain is corrected according to the neighbor communication gain, the follower obtains its control input through the information of the neighbor follower, the probability convergence is ensured even if part of the followers cannot indirectly obtain the leader information, the anti-interference ability is enhanced, the convergence speed is improved, and the communication resource consumption is reduced.

The invention discloses a semantic perception coordination method for automatic driving vehicles, and the method comprises the steps: collecting the state information of vehicles in real time, and dividing the vehicles into different temporary groups according to the spatial position relation between the vehicles; data synchronization and leader election are carried out in each group by adopting a Raft protocol, followers in each temporary group periodically upload own state information to the leader, and the leader generates a consistency state matrix of the group according to the collected state information of the followers in the group; the leader in each group broadcasts the consistency state matrix to all followers and inputs the consistency state matrix into a large language model, the consistency state matrix is converted into natural language description through the large language model, and action parameters of each group member are generated; and each vehicle inputs the action parameters into the rule-based driving model, and the rule-based driving model generates a control instruction according to the state information of the vehicle, so that the motion consistency of the vehicles in the group is realized. According to the invention, semantic perception and consistency coordination between vehicles are realized, and the safety and reliability of an intelligent traffic system are improved.

A hybrid-order multi-agent control method, apparatus, device, and readable storage medium are disclosed. The hybrid-order multi-agent control method includes: for each iteration of each follower agent, calculating the following consistency error between the follower agent and the leader agent, and the neighbor consistency error between the follower agent and other follower agents; calculating the sliding mode error based on the following consistency error and the neighbor consistency error; calculating the control input using the controller's control law based on the sliding mode error, the Nussbaum gain function, and a composite control term; controlling the follower agent based on the control input to enable it to follow the leader agent in performing the same task; and updating the parameters of the controller's control law based on the sliding mode error. Through this application, after multiple iterative learning and optimizations, even in the face of component failures and unknown interference, the follower agent can effectively follow the leader agent.

Automatically setting homepoints in a machine synchronization system is disclosed. A leader kinematic model of a leader machine is obtained. A follower kinematic model of a follower machine is obtained. A homepoint that enables an alignment of the follower machine to the leader machine is calculated based on the leader kinematic model and the follower kinematic model. The homepoint is then set for the follower machine.

The invention discloses an aggregator-electric vehicle master-slave game charging pricing method considering the regret psychology. The method comprises the following steps: establishing an EV cost model based on a real-time road network speed-flow model; secondly, introducing a regret theory to describe the perception loss of the user caused by not selecting an optimal scheme in different scenes, and further constructing a user charging decision model; and then, establishing a master-slave game framework taking a load aggregator LA as a leader and an electric vehicle EV user as a follower, optimizing the charging service price of the aggregator, guiding the spatial-temporal distribution of the electric vehicle needing to be charged, and distributing the remaining income obtained by the aggregator by using a Shapley value method. According to the invention, the Shapley value method is adopted to carry out income distribution on the charging stations in the cooperative alliance, and the alliance stability and individual rationality are guaranteed, so that the user satisfaction and participation degree are enhanced while the system economy is improved.

The present invention provides an optimization control method for a human-in-the-loop multi-agent system under FDI attack, belonging to the technical field of multi-agent system control. The control method constructs a non-fully autonomous leader system and takes into account the FDI attack from the follower controller to the actuator end. In view of the antagonistic relationship between the attacker and the defender, a performance function is constructed and the Nash equilibrium point, that is, the optimal strategy of the attacker and the defender, is obtained under the unified design framework of zero-sum game and adaptive dynamic programming theory; at the same time, in order to reduce the consumption of network resources, a dynamic event triggering mechanism is designed; combined with a single evaluation network structure based on a neural network, the Nash optimal solution is obtained. The control method of the present invention realizes dynamic event-triggered game optimization control under the influence of FDI attack, constructs a method for simultaneously designing the optimal strategies of the attacker and the defender under a unified framework, and saves communication resources while achieving game performance optimization.

The present disclosure provides a comprehensive energy intelligent agent collaborative fault-tolerant group control method for improving the resilience of an energy system. According to the differentiated goals of each intelligent agent in the comprehensive energy intelligent agent, the comprehensive energy intelligent agent is divided into multiple intelligent agent subsystems; for each intelligent agent subsystem, a leader-follower model including a leader, a follower, and a collaborative fault-tolerant control module is constructed to achieve group autonomy; wherein the leader in any intelligent agent subsystem is a control unit, the follower is a controlled device, the followers are neighbor intelligent agents, and the neighbor intelligent agents output consistency under any follower failure through the collaborative fault-tolerant control module; for the group autonomous intelligent agent group, a group control architecture is adjusted, the interest balance of each intelligent agent subsystem is taken as a target, a Q learning algorithm is used to solve the Nash equilibrium point of the game between multiple intelligent agent subsystems by using evolutionary game theory, and the comprehensive energy intelligent agent is scheduled and planned according to the solution result to achieve inter-group coordination.

The invention discloses a discrete agent-based load group modeling and consistency regulation and control method and system, and the method comprises the steps: building a discrete time load group model based on a load group, and enabling the discrete time load group model to comprise a leader and a plurality of followers; determining a system matrix including an adjacent matrix and a leader connection matrix; dividing the followers by using competition relationship representation; obtaining a low-gain state feedback matrix; setting the maximum response time of regulation and control; in the regulation and control process, a complete intermittent control protocol and a partial intermittent control protocol are generated; respectively calculating control tracks of followers under different control protocols and corresponding saturation constraint values; calculating a consistency error between the system states of the leader and the follower at the regulation and control time k; and judging whether the regulation process is ended or not according to the consistency error. According to the method, control paradigm innovation, heterogeneous system compatibility, time-varying demand adaptation, communication overhead optimization, stable performance guarantee and system self-evolution can be realized, and the flexibility, high efficiency and engineering practicability of power load regulation and control are remarkably improved.

The invention discloses a leader following method and system of an omnidirectional mobile robot based on anti-interference pulses, and relates to the technical field of leader following of omnidirectional mobile robots, and the method comprises the steps: constructing a system model containing hybrid disturbance, designing an observer to estimate the system model, and designing a compensator according to the observer; a pulse control packet loss model is established based on Bernoulli distribution, a pulse controller containing packet loss information is designed, compensation and the pulse controller are combined, a pulse controller based on disturbance observation is formed, an augmented system is obtained, sufficient conditions for ensuring the stability of a mean square index of the system are deduced, and the stability of the system is improved. And a gain matrix of the observer and the pulse controller is solved according to the state information of the leader and the follower, a control instruction is generated by combining the obtained gain matrix, and leader-follower control over the follower robot is achieved. According to the invention, the leader-following control cost of the omni-directional mobile robot is effectively reduced, and the robustness of the leader-following control of the omni-directional mobile robot is enhanced.

This invention discloses an iterative control method for unknown nonlinear multi-agent systems based on model decoupling encoding and decoding, belonging to the field of multi-agent cooperative control technology. The method acquires the state and trajectory information of each follower and leader in a multi-agent system. The follower state information is quantized and transmitted through a model-decoupled dynamic encoding and decoding mechanism. This mechanism does not embed system dynamic parameters, but only dynamically adjusts the state error scaling factor to prevent quantizer saturation. After receiving the quantized data, each follower reconstructs its decoded state information using a decoder. Based on this information and the leader's trajectory, a local performance index function without neighbor control input is constructed. An online value iteration algorithm is used to update the weight parameters of the evaluation network and execution network of each follower. After convergence, the optimal control strategy is obtained, generating control inputs to drive the system to achieve leader-follower consistency tracking. This invention effectively reduces communication resource consumption and improves system robustness and cooperative efficiency.

The application relates to the technical field of automatic control, and discloses a kind of multi-agent data-driven adaptive two-part tracking control method and device.The application designs a kind of completely distributed direct data-driven adaptive consensus protocol for the cooperative control problem of multi-agent system under unknown dynamics model and the complex scene that dynamic leader control input is non-zero and unknown, the protocol only uses input data matrix, state data matrix and state derivative data matrix in the sampling measurement value of leader agent and follower agent, and on-line adaptive adjustment control parameter and coupling weight matrix.Thereby, without the condition of system accurate model and global network information, two-part tracking consensus of leader-follower multi-agent system is realized under the condition that dynamic leader exists.The method significantly improves the flexibility, scalability and engineering applicability of the control system.

The application relates to a multi-agent system preset performance consistency control method and device. The method comprises the following steps: constructing a nonlinear multi-agent system model comprising a follower agent and a leader agent; combining a preset performance constraint function to construct an equivalent conversion system model; constructing an event-triggered control protocol comprising a distributed sampling event-triggered controller and a dynamic event-triggered function; based on the equivalent conversion system model and the event-triggered control protocol, constructing a multi-agent system simultaneous closed loop model and performing stability analysis to obtain sufficient conditions for the multi-agent system to realize preset performance consistency control under external disturbance and nonlinear influence; and according to the sufficient conditions, solving the control gain parameters of the distributed sampling event-triggered controller. The method can ensure the anti-interference performance of the system, significantly reduce the update frequency of the controller, improve the transient and steady-state performance of the system, and is suitable for distributed scenes with limited communication resources.

The application relates to the technical field of automatic control, and discloses a kind of multi-agent data-driven adaptive two-part tracking control method and device.The application designs a kind of completely distributed direct data-driven adaptive consensus protocol for the cooperative control problem of multi-agent system under unknown dynamics model and the complex scene that dynamic leader control input is non-zero and unknown, the protocol only uses input data matrix, state data matrix and state derivative data matrix in the sampling measurement value of leader agent and follower agent, and on-line adaptive adjustment control parameter and coupling weight matrix.Thereby, without the condition of system accurate model and global network information, two-part tracking consensus of leader-follower multi-agent system is realized under the condition that dynamic leader exists.The method significantly improves the flexibility, scalability and engineering applicability of the control system.

The invention discloses a switching topology-containing partial differential multi-agent system consistency control method, and relates to the field of networked systems, partial differential equations and cooperative control, and the method comprises the steps: respectively constructing a follower system dynamic model and a leader dynamic model; constructing an error system; establishing a balance interaction topology for a plurality of followers in the follower system; constructing a plurality of guidance diagrams including follower systems and leaders according to the balanced interaction topology; the plurality of induction diagrams are always or intermittently kept in weak communication; constructing a boundary control law and a control target; according to a boundary control law, the dynamic model of the follower system is adjusted in real time until a control target is met; according to the method, the leader following consistency can be realized under the condition that the induction graph always or intermittently keeps weak communication, and the leader following consistency is exponentially guaranteed.

The invention relates to the technical field of multi-agent cooperative control, discloses a multi-leader follower cluster control method enhanced by adopting a multilayer graph attention mechanism, and solves the problems of poor topology adaptability and low cross-level cooperative efficiency in a dynamic environment. According to the main scheme, the method comprises the following steps: designing a state coding module adapted to role differences and a strategy network and evaluation network model based on graph attention differentiation; designing a role separation playback pool for leader-follower cooperative control; and designing a strategy gradient optimization method of deep reinforcement learning. Aiming at a cluster control task in a continuous action space, a graph attention enhanced multi-agent collaborative framework is provided, different role state input is unified through dynamic topology modeling, cross-level information fusion is realized by using a graph attention mechanism, the adaptive capacity of agents to a dynamic environment and the distinguishing capacity of the agents to a level relationship are improved, and the clustering control efficiency is improved. A role isolation experience storage mechanism is designed, and mutual interference between strategies of a leader and a follower is reduced.

The application discloses a leader-unknown time-varying heterogeneous formation tracking method and a related device, relates to the field of cluster formation tracking control, and comprises the following steps: determining all adjacent followers corresponding to a target follower according to a communication topology relationship diagram of a time-varying heterogeneous formation, and acquiring a leader state information estimation value and a leader output information estimation value of each adjacent follower; then estimating the leader state information of the target follower at the next moment by using a leader state information and a system matrix distributed observer, and then estimating the leader output information of the target follower at the current moment by using a leader output information and an output matrix distributed observer; finally, a distributed formation tracking controller is used for calculation to obtain a control input vector of the target follower at the current moment. The application can track and control the leader-unknown time-varying heterogeneous formation without a persistent excitation condition.

The present invention discloses a consensus method based on credibility, including: in the current round, updating the credibility of each node and starting a timer; determining a leader pL from each node; triggering a Byzantine broadcast protocol on the block B proposed by the leader pL so that non-leader nodes follow the Byzantine broadcast protocol to broadcast the block B and vote on the block B; when the timer reaches a preset time, the node pj determines the first block proposed by the leader and updates the local set according to the signatures involved in the first block. At the beginning of each round, the present invention updates the credibility of each node by taking evidence of the historical behavior of each node, punishes by reducing the credibility of the node, and rewards good behavior by increasing the credibility of the node. Since the credibility of the node is also its own voting weight, it is beneficial to resist flash attacks.

This invention discloses a safety optimization control method for a leader-follower UAV formation, comprising: step S01: constructing a UAV formation under a leader-follower formation control structure; step S02: modeling the formation tracking dynamics of the follower UAVs as an integrator model, introducing a speed command saturation function into the integrator model, and representing the underlying unknown command tracking error as an uncertainty term in the model; step S03: establishing an optimal control problem, considering the actual speed limit of the UAVs, and solving the optimal control strategy that considers the speed constraint by introducing the Hamiltonian and the Hamilton-Jacobi-Bellman equation; and step S04: applying an adaptive dynamic programming algorithm to adaptively compensate for the speed limit and command tracking error. This invention has the advantages of simple principle, wide applicability, and high safety performance.

The invention belongs to the field of multi-agent system control, and relates to a finite time consistency control method of a leader-follower multi-agent system, which comprises the following steps: constructing a communication topological graph G of the leader-follower multi-agent system; the leader-following multi-agent system comprises a plurality of followers and a leader; constructing a multi-agent dynamic system; the multi-agent dynamics system comprises a leader dynamics system and a follower dynamics system. Based on the communication topological graph G and the multi-agent dynamic system, finite time consistency control is conducted on the leader-follower multi-agent system through a traction control method; according to the method, topological conditions are relaxed in traction control, traction control gains are corrected according to neighbor communication gains, followers obtain control input of the followers through information of neighbor followers, and it is ensured that even if part of followers cannot indirectly obtain leader information, convergence can still be achieved according to probabilities, the anti-interference capacity is enhanced, the convergence speed is increased, and communication resource consumption is reduced.

Moving body control system 30 is a moving body control system including a leader moving body 40 and a follower moving body 50. The leader moving body 40 includes a leader preliminary agreement unit 41 that shares an agreement item, which is an item agreed upon regarding a method by which the leader moving body 40 and the follower moving body 50 merge, with the follower moving body 50 prior to merging, and a leader movement control unit 42 that controls movement of the leader moving body 40 based on the shared agreement item. The follower moving body 50 includes a follower preliminary agreement unit 51 that shares the agreement item with the leader moving body 40 prior to merging, and a follower movement control unit 52 that controls movement of the follower moving body 50 based on the shared agreement item.

The invention provides a comprehensive energy agent cooperative fault-tolerant group control method for improving the toughness of an energy system. Dividing the comprehensive energy agent into a plurality of agent subsystems according to the differentiation target of each agent in the comprehensive energy agent; constructing a leader-follower model comprising a leader, a follower and a cooperative fault-tolerant control module for each agent subsystem to realize intra-group autonomy; in any agent subsystem, a leader is a control unit, followers are controlled devices, the followers are neighbor agents, and output consistency between the neighbor agents is achieved through the cooperative fault-tolerant control module when any follower breaks down. Aiming at an intra-group autonomous agent group scheduling and group control architecture, by taking benefit balance of each agent subsystem as a target, a Nash equilibrium point of a game among a plurality of agent subsystems is solved by applying a Q learning algorithm and an evolutionary game theory, and scheduling planning is performed on the comprehensive energy agent according to a solving result so as to realize inter-group coordination.