Integrated Sensing and Communication for Effective Multi-Agent Cooperation Systems

Multi-agent systems (MASs) have emerged as effective means to accomplish important tasks without human involvement in various real-world environments. In MASs, task completion efficiency is determined by the level of cooperation among agents. Meanwhile, achieving high levels of cooperation relies on accurate and comprehensive environmental perception. To this end, agents exchange their local perceptions to expand the scope of their sensing information. However, it limits the improvement of sensing performance by relying solely on information exchange, particularly for mobile target sensing. To address this, we introduce the integrated sensing and communication (ISAC) technique to MASs. This enables the agents to perform distributed radio sensing, while concurrently exchanging their local perceptions. In this article, we propose an ISAC-based MAS framework, where agents can dynamically determine ISAC strategies and cooperatively perceive the environment through ISAC operations. The features of the proposed framework are elucidated and compared with existing networked ISAC systems and communication-centric MASs. For the proposed framework, we suggest a deep reinforcement learning (DRL)-based system design. Simulation results demonstrate the effectiveness of the proposed framework. Finally, we discuss potential challenges and opportunities for future research.