Distributed Adaptive Fault-Tolerant Time-Varying Formation Control of Unmanned Airships With Limited Communication Ranges Against Input Saturation for Smart City Observation

Graph Soft Actor-Critic Reinforcement Learning for Large-Scale Distributed Multirobot Coordination

Learning distributed cooperative policies for large-scale multirobot systems remains a challenging task in the multiagent reinforcement learning (MARL) context. In this work, we model the interactions among the robots as a graph and propose a novel off-policy actor-critic MARL algorithm to train distributed coordination policies on the graph by leveraging the ability of information extraction of graph neural networks (GNNs). First, a new type of Gaussian policy parameterized by the GNNs is designed for distributed decision-making in continuous action spaces. Second, a scalable centralized value function network is designed based on a novel GNN-based value function decomposition technique. Then, based on the designed actor and the critic networks, a GNN-based MARL algorithm named graph soft actor-critic (G-SAC) is proposed and utilized to train the distributed policies in an effective and centralized fashion. Finally, two custom multirobot coordination environments are built, under which the simulation results are performed to empirically demonstrate both the sample efficiency and the scalability of G-SAC as well as the strong zero-shot generalization ability of the trained policy in large-scale multirobot coordination problems.

Event-Triggered Dynamic Coverage Control for Multiple Stratospheric Airships

This article first investigates the dynamic coverage control problem for the multiple stratospheric airships (MSAs) system considering its practical application scenarios. A dynamic coverage control framework is put forward, in which the MSA system can be guided and controlled to fully cover the observation target region. Once a specific target is detected, the coverage target can be switched. First, the location information of the monitored target is predicted by an autoregressive model against processing delay. Second, the coverage control scheme consists of two layers: a novel potential field-based virtual control law to generate the desired velocity and angular velocity and an adaptive tracking controller to track them. In the virtual control law, a dynamic artificial potential field is introduced to adapt to the dynamic scenarios. In the tracking controller, which is combined with the adaptive control technique and the saturation compensator theory, the external disturbances and input saturation are addressed. Third, the event-triggered mechanism is designed to reduce the control frequency to prolong the actuator life. The simulation results are given to substantiate the capability of the proposed dynamic coverage control framework.