Mean-field control barrier functions for stochastic multi-agent systems
This work solves a specific theoretical gap for researchers in stochastic multi-agent control, though it appears incremental.
The paper addresses the lack of mean-field control barrier functions for Fokker-Planck equations, enabling safe control of stochastic multi-agent systems with bounded stability guarantees, as demonstrated in coverage and shepherding simulations.
Many applications involving multi-agent systems require fulfilling safety constraints. Control barrier functions offer a systematic framework to enforce forward invariance of safety sets. Recent work extended this paradigm to mean-field scenarios, where the number of agents is large enough to make density-space descriptions a reasonable workaround for the curse of dimensionality. However, an open gap in the recent literature concerns the development of mean-field control barrier functions for Fokker-Planck (advection-diffusion) equations. In this work, we address this gap, enabling safe mean-field control of agents with stochastic microscopic dynamics. We provide bounded stability guarantees under safety corrections and corroborate our results through numerical simulations in two representative scenarios, coverage and shepherding control of multi-agent systems.