The core message of this article is to propose a novel multi-robot active target tracking framework that considers the existence of sensing and communication danger zones in the environment. The authors formulate the tracking problem as a nonlinear optimization that balances tracking performance and robot safety, and provide practical approximations to efficiently solve the chance-constrained optimization.
Large language models can be effectively used as high-level planners to resolve deadlocks in multi-robot systems by assigning a leader and a direction for the leader to move.
The core message of this paper is to efficiently restore a biconnected communication network in a multi-robot system after the failure of one or more robots, by minimizing the maximum movement of the robots.
The core message of this paper is to develop a scalable algorithm, called EA-SCR, that can efficiently restore k-connectivity in a multi-robot system while minimizing the maximum movement of the robots.
A vision-based learning from demonstration framework that leverages interaction keypoints and soft actor-critic methods to enable multi-robot systems to learn and execute complex behavior-based and contact-based tasks from visual demonstrations.
A bi-level learning framework that combines graph learning for group coordination and reinforcement learning with a spring-damper model for individual robot navigation, enabling multi-robot teams to dynamically adapt their formation to navigate complex environments effectively.