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

arXiv cs.RO / 4/14/2026

💬 OpinionSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper argues that fleet-level multi-robot coordination can be achieved without breaking each robot into internal multi-agent fragments, keeping each unit as a single coherent embodied agent.
It introduces Federated Single-Agent Robotics (FSAR), a runtime architecture where robots expose a governed capability surface and coordinate via fleet-level federation rather than intra-robot multi-agent decomposition.
FSAR’s coordination relies on shared capability registries, policy-aware authority delegation, trust-scoped interactions, and layered recovery boundaries to reduce authority conflicts.
The work formalizes coordination relations (e.g., delegation, capability requests, and local-vs-fleet recovery) and describes a fleet runtime with shared Embodied Capability Module (ECM) discovery and contract-aware task delegation.
In evaluations against decomposition-heavy baselines, FSAR reports statistically significant improvements in governance locality and recovery containment, alongside fewer policy violations.

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.