The requirement of devices to access data cross-domain in smart cities is expanding. The blockchain-based cross-domain authentication and key agreement (AKA) ensures the cross-domain data interaction security. However, the AKA scheme based on single-blockchain has the problem of high on-chain storage burden, risk of domain privacy leakage and inadequate privacy protection caused by the transparency of blockchain. Therefore, a multiblockchain-based cross-domain AKA scheme is proposed in this article. First, a multiblockchain model is designed to support cross-domain authentication. The model consists of two layers. The upper-layer blockchain records brief device identity information used for cross-domain authentication. The under-layer blockchain stores complete device identity information. Second, based on elliptic curve discrete logarithm problem (ECDLP) theory, cross-domain authentication is designed to meet the requirements of security of data exchange between blockchains, and meet the privacy-preserving. Finally, security analysis and performance analysis are conducted. The proposed scheme achieves better cross-domain data interaction security and privacy protection. These improvements are achieved with performance that outperforms single-blockchain-based schemes and is either comparable to or slightly better than multiblockchain-based schemes.

Sparse mobile crowdsensing is a cost-effective sensing paradigm that infers global data by sensing data from partial areas in a city. With the rapid development of diverse autonomous mobile agents such as unmanned aerial vehicles (UAVs) and ground vehicles, they have been widely applied in sparse mobile crowdsensing. However, existing works often predefine the role structures and behavioral preferences of these agents in tasks, which significantly limits their flexibility and adaptability, and making it difficult to fully exploit the collaborative potential of crowdsensing agents to efficiently achieve high-quality data sensing. In this paper, we propose an adaptive role learning framework for sparse mobile crowdsensing (ARL-SMCS), which focuses on role recognition for heterogeneous agents and role refinement among homogeneous agents. This framework, based on a multi-agent reinforcement learning model, introduces a variational autoencoder to learn the latent role representations of agents and uses maximum mean discrepancy to distinguish the functionalities of different types of agents. Additionally, ARL-SMCS incorporates an evolutionary algorithm to further refine task preferences among homogeneous agents. This framework overcomes the limitations of static role assignment in adapting to dynamic environments and task conflicts during task execution, significantly improving sensing quality and resource utilization efficiency. Extensive experiments on two real-world datasets demonstrate that ARL-SMCS consistently outperforms other baseline methods under various conditions, including different numbers, endurance, and decision interval lengths.

Differential privacy is an effective method to solve data privacy leakage. The common differential privacy method is achieved by adding privacy noises to the transmitted data, which may affect data accuracy. For the control system, data accuracy greatly affects the system performance. To circumvent this difficulty, we propose a novel privacy-preserved rolling optimization strategy (PP-ROS) for switched systems. The main contributions are reflected in three aspects: 1) The proposed PP-ROS is used to calculate the private control input by adding Laplace noise to the prediction and control horizons, instead of the transmitted data. 2) Privacy definitions of the prediction and control horizons are presented, and a private model predictive control (P-MPC) controller design is provided based on the PP-ROS. The P-MPC controller achieves the privacy of its parameters. 3) Under PP-ROS and P-MPC, the proof and calculation methods for the privacy levels of control input and system output are given. The results indicate that when noise is added to the horizons, both control input and system output are private. Finally, the availability and benefits of PP-ROS and P-MPC are demonstrated using two simulation examples and comparison results.

The concept of shared control has garnered significant attention within the realm of human-machine hybrid intelligence research. This study introduces a novel approach, specifically a dynamic control authority allocation method, for implementing shared control in autonomous vehicles. Unlike conventional mixed-initiative control techniques that blend human and vehicle inputs with weights determined by predefined index, the proposed method utilizes optimization-based techniques to obtain an optimal dynamic allocation for human and vehicle inputs that satisfies safety constraints. Specifically, a convex quadratic programm (QP) is constructed incorporating control barrier functions (CBF) for safety and control Lyapunov functions (CLF) for satisfying automated control objectives. The cost function of the QP is designed such that human weight increases with the magnitude of human input. A smooth control authority transition is obtained by optimizing over the change rate of the weight instead of the weight itself. The proposed method is verified in lane-changing scenarios with human-in-the-loop (HmIL) and hardware-in-the-loop (HdIL) experiments. Results show that the proposed method outperforms index-based control authority allocation method in terms of agility, safety and comfort.

Reinforcement learning behavioral control (RLBC) is limited to an individual agent without any swarm mission, because it models the behavior priority learning as a Markov decision process. In this paper, a novel multi-agent reinforcement learning behavioral control (MARLBC) method is proposed to overcome such limitations by implementing joint learning. Specifically, a multi-agent reinforcement learning mission supervisor (MARLMS) is designed for a group of nonlinear second-order systems to assign the behavior priorities at the decision layer. Through modeling behavior priority switching as a cooperative Markov game, the MARLMS learns an optimal joint behavior priority to reduce dependence on human intelligence and high-performance computing hardware. At the control layer, a group of second-order reinforcement learning controllers are designed to learn the optimal control policies to track position and velocity signals simultaneously. In particular, input saturation constraints are strictly implemented via designing a group of adaptive compensators. Numerical simulation results show that the proposed MARLBC has a lower switching frequency and control cost than finite-time and fixed-time behavioral control and RLBC methods.

This work presents a butterfly spiral propulsion mode of snake robots to realize the tracking control on the objective trajectory in multiple scenarios. This method investigates the force mechanism of each body element in the yaw and pitch directions. The butterfly spiral gait mechanic and friction models are constructed to offset the lateral torque force caused by joint rotation. In addition, this work combines an integral part of improving the line of sight guidance scheme, which eliminates the robot's sideslip when tracking the curve track and enhances the body's adaptability to different scenarios. Lyapunov's theory proves the stability of the designed guidance strategy. Simulation and experimental results illustrate that the designed butterfly spiral gait and guidance scheme can provide the snake robot faster tracking results and more stable error performance than the cylindrical and conical spiral gait.

This paper studies control strategies of intelligent vehicles at unsignalized intersections. By considering the interaction among multiple vehicles and communication disturbances, the problem is formulated as a robust differential game in which the controlled vehicle computes actions using disturbed information of locally neighboring vehicles. Both cooperative and non-cooperative differential game models are considered. The controlled vehicle optimizes its own cost in the non-cooperative game while coordinates its strategy with other vehicles to optimize a joint cost in the cooperative game. We show that the local optimal strategy of each intelligent vehicle defined by a single optimization problem converges to global robust Nash equilibrium in the non-cooperative game, and converges to the global robust Pareto-Nash equilibrium in the cooperative game. The effectiveness of the robust differential game method is verified by simulations under two scenarios. Results show that under the proposed differential game approach, vehicles pass through unsignalized intersections more quickly than methods using traditional discrete game approaches. In addition, vehicles can avoid colliding with each other and obstacles at the presence of communication disturbances.

To eliminate the influence of nonlinear state terms in the highly-coupled unmanned aerial vehicle (UAV) model and improve the aircraft’s ability to suppress wind field interferences, this work presents a path-following scheme for UAVs. This method uses the radial basis neural network (RBNN) to develop an adaptive approximation law for the gyroscopic effect function to balance for the influence of system uncertainty and nonlinear state terms on UAV modeling and reduce the dependence of the UAV’s roll and pitch control orders on attitude velocity information. In addition, the adaptive update laws of the disturbance predictions are designed to compensate for the control input and repress the chattering and deviation of the drone. The stability of the proposed controller was proven by using the Lyapunov theorem. Simulations and experiments have shown that the controller can perform faster convergence speed and higher following accuracy of the flight position and attitude errors.

In this study, a novel reinforcement learning task supervisor (RLTS) with memory in a behavioral control framework is proposed for human—multi-robot coordination systems (HMRCSs). Existing HMRCSs suffer from high decision-making time cost and large task tracking errors caused by repeated human intervention, which restricts the autonomy of multi-robot systems (MRSs). Moreover, existing task supervisors in the null-space-based behavioral control (NSBC) framework need to formulate many priority-switching rules manually, which makes it difficult to realize an optimal behavioral priority adjustment strategy in the case of multiple robots and multiple tasks. The proposed RLTS with memory provides a detailed integration of the deep Q-network (DQN) and long short-term memory (LSTM) knowledge base within the NSBC framework, to achieve an optimal behavioral priority adjustment strategy in the presence of task conflict and to reduce the frequency of human intervention. Specifically, the proposed RLTS with memory begins by memorizing human intervention history when the robot systems are not confident in emergencies, and then reloads the history information when encountering the same situation that has been tackled by humans previously. Simulation results demonstrate the effectiveness of the proposed RLTS. Finally, an experiment using a group of mobile robots subject to external noise and disturbances validates the effectiveness of the proposed RLTS with memory in uncertain real-world environments.

In this article, the problem of human intervention and autonomous controller design for human–agent interaction systems is addressed. In particular, a human drift diffusion model is developed for second-order linear multiagent systems subject to unknown external disturbances. The proposed human drift diffusion model can model human decision-making behavior using multiple sources of human decision-making information. Accurate human intervention timing is obtained by setting varying thresholds for different decision-making information. In addition, a fixed-time sliding mode adaptive behavioural controller is developed to execute human decisions in the framework of the null-space based behavioral control method. The controller guarantees that agents can follow human commands given an arbitrary initial task error and can finish tasks in fixed time. A simulation under various scenarios shows that the proposed human drift diffusion model is able to provide appropriate human intervention and the proposed controller can guarantee human command fulfillment within fixed time.

This paper focuses on the simulation and comparison of different types of first-order decentralized sliding mode estimators (FDSMEs). From the previous works, three types of FDSMEs were presented and applied to solve the cooperative control problems. Utilizing the FDSME, a finite-time leader-follower tracking control algorithm is proposed for a networked single-integrator vehicle system. Then based on the existing structure of FDSME, a new compound FDSME is developed to improve the estimation performance. Simulation and comparison of all the presented FDSMEs are given in detail to evaluate the theoretical results. Finally, regulation rules of the parameters in the compound FDSME are summarized according to the simulation results.

Summary The problem of distributed cooperative control for networked multiagent systems is investigated in this paper. Each agent is modeled as an uncertain nonlinear high‐order system incorporating with model uncertainty, unknown external disturbance, and actuator fault. The communication network between followers can be an undirected or a directed graph, and only some of the follower agents can obtain the commands from the leader. To develop the distributed cooperative control algorithm, a prefilter is designed, which can derive the state‐space representation to a newly constructed plant. Then, a set of distributed adaptive neural network controllers are designed by making certain modifications on traditional backstepping techniques with the aid of adaptive control, neural network control, and a second‐order sliding mode estimator. Rigorous proving procedures are provided, which show that uniform ultimate boundedness of all the tracking errors can be achieved in a networked multiagent system. Finally, a numerical simulation is carried out to evaluate the theoretical results.

In the paper, a city educational resources assignment problem (CERAP) is raised. The combination of big data, multi-agent model and cellular automata (CA) methodologies are argued and developed. Then, the agent-based computational framework is discussed to the educational social science control (assignment) system. The proposed methodologies provides a powerful way to address nonlinearities, humanities, and especially interdisciplinary control problem. Agent-based modeling offers powerful new forms of hybrid theoretical-computational work. The agent-based approach invites the interpretation of society as a distributed computational network, and in turn the interpretation of social dynamics as a type of computation. Then, the simulation tools are mentioned. Finally, a short discussion and conclusion end this paper.

In this paper, we aim to develop a set of distributed adaptive fuzzy controllers for a group of uncertain nonlinear high-order multi-agent systems in the presence of actuator faults. Firstly, a pre-filter is designed which can derive the state space representation to a newly constructed plant. Design of the control variable will be provided by making certain modifications on traditional backstepping technique with the aid of adaptive control, fuzzy control and a second-order sliding mode estimator. It shows that the effects due to actuator faults, external disturbances and the uncertainties of the model can be compensated with the proposed scheme, and the global boundedness of the tracking errors can also be ensured.