Problem
Research questions and friction points this paper is trying to address.
Embodied Collective Intelligence
Multi-Robot Systems
Agentic AI
Shared State
Embodied AI
When Multi-Robot Systems Meet Agentic AI:Towards Embodied Collective Intelligence
🤖 AI Summary
Current multi-robot systems lack effective mechanisms for sharing embodied agents’ closed-loop states—such as situational understanding, task progress, and skill experience—hindering deep collaboration. This work proposes the Embodied Collective Intelligence (ECI) framework, which for the first time tightly integrates the closed-loop cognitive capabilities of embodied agents with multi-robot coordination through co-perception, co-action, and co-evolution, centered around a shared world memory. The framework introduces a novel paradigm of collective intelligence driven by shared internal states, enabling teams to accumulate and reuse contextual knowledge, task progress, and experiential skills. Experiments demonstrate that newly joined robots significantly improve navigation performance by inheriting and merging this shared memory, providing quantitative empirical support for the ECI approach.
📝 Abstract
Embodied AI is increasingly becoming agentic, shifting robots from perception--control pipelines towards closed-loop systems that can retrieve context, deliberate during execution, monitor feedback, and refine future behavior. In parallel, robotics research has also moved from single-robot autonomy towards multi-robot systems, driven by the need for wider sensing, distributed action, heterogeneous capabilities, and fault tolerance. As AI agents move from single-agent use towards multi-agent collaboration, robotics faces a parallel challenge: robot teams must move beyond sharing maps, task assignments, and datasets towards sharing the state produced by embodied agent loops. This article explores Embodied Collective Intelligence (ECI), a future multi-robot paradigm in which a robot team accumulates and uses world context, task progress, and skill experience as shared resources. Specifically, we first review how embodied AI is becoming agentic and how multi-robot cooperation has evolved. We then present Embodied Collective Intelligence through Co-Perception, Co-Action, and Co-Evolution. Finally, we use an illustrative navigation study to examine one concrete component of the concept: shared world-memory inheritance. The study shows that a newly added robot can benefit from merged team memory, but it is not intended as a full evaluation of the ECI framework. Taken together, the review and conceptual framework motivate Embodied Collective Intelligence as a direction for embodied multi-agent intelligence, while the case study grounds one measurable part of the concept.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Embodied Collective Intelligence
Agentic AI
Multi-Robot Systems
Shared World Memory
Co-Evolution
🔎 Similar Papers
No similar papers found.
