A Distributed Simplex Architecture for Multi-Agent Systems

TL;DR

The paper introduces Distributed Simplex Architecture (DSA), a novel runtime assurance method that guarantees safety in multi-agent systems with distributed control, extending traditional Simplex control to more complex, multi-agent scenarios.

Contribution

It extends the Simplex control architecture to distributed multi-agent systems, providing a safety guarantee through local instances that ensure overall system safety.

Findings

Proven safety guarantees for DSA in multi-agent systems.

Successful case studies including flocking, navigation, and microgrid operation.

Experimental validation demonstrating effectiveness of DSA.

Abstract

We present Distributed Simplex Architecture (DSA), a new runtime assurance technique that provides safety guarantees for multi-agent systems (MASs). DSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. The traditional Simplex approach is limited to single-agent systems or a MAS with a centralized control scheme. DSA addresses this limitation by extending the scope of Simplex to include MASs under distributed control. In DSA, each agent has a local instance of traditional Simplex such that the preservation of safety in the local instances implies safety for the entire MAS. We provide a proof of safety for DSA, and present experimental results for several case studies, including flocking with collision avoidance, safe navigation of ground rovers through way-points, and the safe operation of a microgrid.