Explore the vast range of titles available.

The unmanned warehouse dispatching system of the ‘goods to people’ model uses a structure mainly based on a handling robot, which saves considerable manpower and improves the efficiency of the warehouse picking operation. However, the optimal performance of the scheduling system algorithm has high requirements. This study uses a deep Q-network (DQN) algorithm in a deep reinforcement learning algorithm, which combines the Q-learning algorithm, an empirical playback mechanism, and the volume-based technology of productive neural networks to generate target Q-values to solve the problem of multi-robot path planning. The aim of the Q-learning algorithm in deep reinforcement learning is to address two shortcomings of the robot path-planning problem: slow convergence and excessive randomness. Preceding the start of the algorithmic process, prior knowledge and prior rules are used to improve the DQN algorithm. Simulation results show that the improved DQN algorithm converges faster than the classic deep reinforcement learning algorithm and can more quickly learn the solutions to path-planning problems. This improves the efficiency of multi-robot path planning.

This paper addresses the problem of Multi-robot Coverage Path Planning for unknown environments in the presence of robot failures. Unexpected robot failures can seriously degrade the performance of a robot team and in extreme cases jeopardize the overall operation. Therefore, this paper presents a distributed algorithm, called Cooperative Autonomy for Resilience and Efficiency, which not only provides resilience to the robot team against failures of individual robots, but also improves the overall efficiency of operation via event-driven replanning. The algorithm uses distributed Discrete Event Supervisors, which trigger games between a set of feasible players in the event of a robot failure or idling, to make collaborative decisions for task reallocations. The game-theoretic structure is built using Potential Games, where the utility of each player is aligned with a shared objective function for all players. The algorithm has been validated in various complex scenarios on a high-fidelity robotic simulator, and the results demonstrate that the team achieves complete coverage under failures, reduced coverage time, and faster target discovery as compared to three alternative methods.

This letter proposes a self‐organising distributed task assignment algorithm based on a ring network for multi‐robot systems. Unlike conventional multi‐robot task assignment methods, the proposed approach enables task assignment through simple data exchange, without the need for a supervisor, global synchronisation and leader election. To evaluate the proposed method, simulations were conducted with seven robots and variable task durations. Results show that all tasks were successfully assigned with balanced distribution. The optimal algorithm consistently chose the robot with the lowest execution cost, demonstrating efficient allocation without centralised control. This letter proposes a self‐organising distributed task assignment algorithm based on a ring network for multi‐robot systems. Unlike conventional multi‐robot task assignment methods, the proposed approach enables task assignment through simple data exchange, without the need for a supervisor, global synchronisation and leader election.

To address the issues of short flight duration and the inability to carry high‐computation resources in small observation unmanned aerial vehicles (UAVs) due to limited energy and payload capacities, this paper proposes a deployment framework for an air–water surface collaborative observation system based on energy‐replenishment and computation offloading. In this framework, UAVs serve as platforms for observation tools, while unmanned surface vehicles (USVs) function as platforms for energy replenishment and edge computing nodes. The edge computing nodes are capable of processing, analyzing, and distributing observation data received from the UAVs. UAVs can perform coordinated landing and recharging on the USVs using high‐precision BeiDou positioning. Experimental results indicate that the application of this framework allows small observation UAVs to avoid the burden of carrying heavy computational loads during flight and enables cyclic recharging and operation using the USV platform. The findings of this study have broad applicability in various scenarios, including environmental monitoring, disaster patrol, marine mapping, and marine aquaculture. To address the issues of short flight duration and the inability to carry high‐computation resources in small observation unmanned aerial vehicles (UAVs) due to limited energy and payload capacities, a deployment framework is proposed for an air–water surface collaborative observation system based on energy replenishment and computation offloading. In this framework, the UAV serve as a platform for observation tools, while unmanned surface vehicles (USVs) act as platforms for energy replenishment and edge computing nodes. The edge computing nodes process, analyze, and distribute the observation data received from the UAV. Upon receiving a charging signal, the UAV performs coordinated positioning with the USV using high‐precision BeiDou positioning and land on the USV. After recharging, the UAV resumes their observation tasks. Experimental results demonstrate that this framework prevents the small observation UAV from having to carry heavy computational loads during flight and also, the small observation UAV can utilize the USV platform for cyclic recharging and takeoff. The findings of this study can be extended to the collaborative application of multiple UAVs and USVs, enabling broader and more sustained observations. This approach has significant potential for applications in environmental monitoring, disaster rescue, marine mapping, border patrol, and marine aquaculture capacity monitoring.

This article solves dominance regions for boundary‐guarding games based on optimal control, where autonomous vehicles with rotation constraints serve as defenders to guard the target zone. Based on the definition of transition point, the minimum reach time is explicitly expressed in unbounded and convex domains, respectively. Using the proposed explicit expression of minimum reach time, this article develops a numerical algorithm to generate dominance regions for boundary‐guarding games. Finally, simulation results are provided to verify the algorithmic validity to generate dominance regions for rotationally‐constrained autonomous vehicles. This article solves dominance regions for boundary‐guarding games based on optimal control, where autonomous vehicles with rotation constraints serve as defenders to guard the target zone. The explicit expression of minimum reach time, is proposed to generate dominance regions for boundary‐guarding games.

Aiming at the reconnaissance task of unmanned vehicle formation under the malicious attack, a security state estimation method based on attack signal reconstruction is proposed. First the reconstruction of attack signal is transformed into a sparse error correction problem by stacking the measurement information of adjacent vehicles, and is solved by orthogonal matching pursuit (OMP) algorithm. Then the attack compensation based particle filter is designed to estimate the target state for each vehicle. An information fusion strategy is designed to obtain the final reconnaissance result based on agent centrality and the number of attacks on unmanned vehicles. Finally, simulations are provided to illustrate the effectiveness of the proposed method. Aiming at the reconnaissance task of unmanned vehicle formation under the malicious attack, a security state estimation method based on attack signal reconstruction is proposed. First, the reconstruction of attack signal is transformed into a sparse error correction problem by stacking the measurement information of adjacent vehicles, and is solved by orthogonal matching pursuit (OMP) algorithm. Then, the attack compensation based particle filter is designed to estimate the target state for each vehicle. An information fusion strategy is designed to obtain the final reconnaissance result based on node centrality and the number of attacks on unmanned vehicles. Finally, simulations are provided to illustrate the effectiveness of the proposed method.

Formation control is a fundamental task in the realm of autonomous multiagent systems. To drive a group of agents to maneuver continuously with the desired formation, this paper studies the finite‐time affine formation control problem with disturbances, input constraints and safety guarantee. A non‐singular terminal sliding mode control (NTSMC) is implemented to achieve finite‐time convergence of all followers to their desired positions. Additionally, an auxiliary system is deployed to address input constraints resulting from the physical properties of the affine formation system. To mitigate the impact of lumped disturbances, a finite‐time disturbance observer (FTDO) is employed to estimate the disturbances and compensate for their effects. Based on FTDO, the auxiliary system and the above NTSMC, a finite‐time robust controller is developed as the nominal controller. By modifying the nominal controllers to comply with safety constraints, control barrier functions are employed to ensure the safety of the formation system in obstacle‐filled environment. Finally, the effectiveness and feasibility of this method are validated through simulations and real‐world experiments. Formation control is a fundamental task in the realm of autonomous multiagent systems. To drive a group of agents to maneuver continuously with the desired formation, this paper studies the finite‐time affine formation control problem with disturbances, input constraints and safety guarantee. We implement a non‐singular terminal sliding mode control (NTSMC) to achieve finite‐time convergence of all followers to their desired positions. Additionally, we deploy an auxiliary system to address input constraints resulting from the physical properties of the affine formation system. To counteract the impact of lumped disturbances, a finite‐time disturbance observer (FTDO) is utilized for estimation and compensation. Based on FTDO, the auxiliary system and the above NTSMC, a finite‐time robust controller is developed as the nominal controller. By modifying the nominal controllers to comply with safety constraints, we employ control barrier functions to ensure the safety of the affine formation system.

This article addresses the issue of collaborative wildfire monitoring using a group mobile mecanum‐wheeled omnidirectional vehicles (MWOVs) affected by nonlinear uncertainties and external disturbances. By integrating finite‐time extended state observers (FTESO) and backstepping nonsingular fast terminal sliding mode (BNFTSM) control method, an observer‐based finite‐time time‐varying elliptical formation control scheme is proposed for a group of MWOVs tasked with monitoring the propagation of wildfires in an elliptical pattern. First, the FTESO is employed to estimate the unavailable velocity system states and the lumped disturbances. Then, a novel nonsingular fast terminal sliding surface, enhanced with an exponential term, is introduced to improve the convergence rate. Through the Lyapunov theorem, the convergence of position and velocity cooperative tracking errors to zero in fast finite‐time is demonstrated. To showcase the effectiveness of the proposed control scheme, comparative simulation results are presented. In an effort to reduce damage and accidents during wildfire combat, this article proposes a control scheme for a group of mobile mecanum‐wheeled omnidirectional vehicles (MWOVs) assigned to monitor wildfire spread. The control scheme guarantees fast finite‐time convergence of cooperative tracking errors, even in the presence of unknown external disturbances and parameter uncertainties. This ensures that the MWOVs can accurately track the progression of a wildfire.

This paper tackles the problem of constructing a communication map of a known environment using multiple robots. A communication map encodes information on whether two robots can communicate when they are at two arbitrary locations and plays a fundamental role for a multi-robot system deployment to reliably and effectively achieve a variety of tasks, such as environmental monitoring and exploration. Previous work on communication map building typically considered only scenarios with a fixed base station and designed offline methods, which did not exploit data collected online by the robots. This paper proposes Gaussian Process-based online methods to efficiently build a communication map with multiple robots. Such robots form a mesh network, where there is no fixed base station. Specifically, we provide two leader-follower online sensing strategies to coordinate and guide the robots while collecting data. Furthermore, we improve the performance and computational efficiency by exploiting prior communication models that can be built from the physical map of the environment. Extensive experimental results in simulation and with a team of TurtleBot 2 platforms validate the approach.

This paper proposes a novel human–multi-robot-system interaction approach that enjoys two main features: natural interaction and affect-based adaptation of robots behavior. Specifically, the proposed system enables interaction by means of a wrist-worn device, such as a commercial smartwatch, which allows to track user’s movements and heart activity. Thus, on the one side, the proposed system allows the user to intuitively drive the robots by establishing a natural mapping between wrist movements and robots velocity. On the other side, the system estimates user’s mental fatigue during interaction by means of the analysis of heart rate variability. The proposed interaction system adapts then the behavior of the multi-robot system when the interacting user gets overwhelmed with the interaction and control task, which is then simplified. Experimental validation is provided, to show the effectiveness of the proposed system. First, the natural and affect-based interaction are considered separately. Then, the approach is tested considering a complex realistic scenario, which is simulated in virtual reality in order to get an immersive and realistic interaction experience. The results of the experimental validation clearly show that the proposed affect-based adaptive system leads to relieving the user’s fatigue and mental workload.