Pseudo-perturbation-based Broadcast Control of Multi-agent Systems
Yuji Ito, Md Abdus Samad Kamal, Takayoshi Yoshimura, Shun-ichi Azuma

TL;DR
This paper introduces a pseudo-perturbation-based broadcast control law for multi-agent systems, improving coordination speed and reducing unhelpful actions by using virtual multiple actions instead of single stochastic actions, with theoretical and simulation validation.
Contribution
It proposes a novel PBC law that enhances broadcast control by incorporating multiple virtual actions, leading to faster convergence and better performance over traditional BC methods.
Findings
PBC achieves asymptotic coordination with probability 1.
PBC reduces unavailing actions compared to BC.
Increasing virtual actions further improves control performance.
Abstract
The present paper proposes a novel broadcast control (BC) law for multi-agent coordination. A BC framework has been developed to achieve global coordination tasks with low communication volume. The BC law uses broadcast communication, which transmits an identical signal to all agents indiscriminately without any agent-to-agent communication. Unfortunately, all of the agents are required to take numerous random actions because the BC law is based on stochastic optimization. Such random actions degrade the control performance for coordination tasks and may invoke dangerous situations. In order to overcome these drawbacks, the present paper proposes the pseudo-perturbation-based broadcast control (PBC) law, which introduces multiple virtual random actions instead of the single physical action of the BC law. The following advantages of the PBC law are theoretically proven. The PBC law…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDistributed Control Multi-Agent Systems · Advanced Control Systems Optimization · Modular Robots and Swarm Intelligence
