Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation

2026-04-13

AI Summary

This work addresses the limitations of traditional multi-robot coordination approaches, which often rely excessively on decomposing tasks into multiple internal agents within each robot, leading to governance complexity, poor recoverability, and policy conflicts. To overcome these issues, the paper proposes a Federated Single-Agent Robot (FSAR) architecture that eliminates internal fragmentation by treating each robot as a unified intelligent agent while enabling coordination through an inter-robot federated mechanism. The FSAR framework incorporates a shared capability registry, policy-aware permission allocation, trust-scoped interactions, a hierarchical recovery protocol, and an embodied capability module (ECM) discovery mechanism. Experimental results demonstrate that, compared to centralized and fragmented baselines, FSAR significantly improves governance locality (d = 2.91, p < .001) and recovery isolation (d = 4.88, p < .001), effectively reducing permission conflicts and policy violations.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

As embodied robots move toward fleet-scale operation, multi-robot coordination is becoming a central systems challenge. Existing approaches often treat this as motivation for increasing internal multi-agent decomposition within each robot. We argue for a different principle: multi-robot coordination does not require intra-robot multi-agent fragmentation. Each robot should remain a single embodied agent with its own persistent runtime, local policy scope, capability state, and recovery authority, while coordination emerges through federation across robots at the fleet level. We present Federated Single-Agent Robotics (FSAR), a runtime architecture for multi-robot coordination built on single-agent robot runtimes. Each robot exposes a governed capability surface rather than an internally fragmented agent society. Fleet coordination is achieved through shared capability registries, cross-robot task delegation, policy-aware authority assignment, trust-scoped interaction, and layered recovery protocols. We formalize key coordination relations including authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries, and hierarchical human supervision, and describe a fleet runtime architecture supporting shared Embodied Capability Module (ECM) discovery, contract-aware cross-robot coordination, and fleet-level governance. We evaluate FSAR on representative multi-robot coordination scenarios against decomposition-heavy baselines. Results show statistically significant gains in governance locality (d=2.91, p<.001 vs. centralized control) and recovery containment (d=4.88, p<.001 vs. decomposition-heavy), while reducing authority conflicts and policy violations across all scenarios. Our results support the view that the path from embodied agents to embodied fleets is better served by federation across coherent robot runtimes than by fragmentation within them.

Problem

• multi-robot coordination
• single-agent robotics
• federated systems
• embodied agents
• fleet-scale operation

Innovation

• Federated Single-Agent Robotics
• multi-robot coordination
• embodied agents
• capability federation
• runtime architecture