Safety Embedded Stochastic Optimal Control of Networked Multi-Agent Systems via Barrier States
share
This paper presents a safe stochastic optimal control method for networked multi-agent systems (MASs) by using barrier states (BaSs) to embed the safety constraints into the system dynamics. The networked multi-agent system (MAS) is factorized into multiple subsystems, each of which is augmented with BaSs for the central agent. The optimal control law is obtained by solving the joint Hamilton-Jacobi-Bellman (HJB) equation on the augmented subsystem, which ensures safety via the boundedness of the BaSs. The BaS-based optimal control method generates safe control actions and also preserves optimality. The safe optimal control solution is ultimately approximated with path integrals. We validate the efficacy of the proposed approach in numerical simulations on a cooperative UAV team in two different scenarios.
READ FULL TEXT