Safe Policy Synthesis in Multi-Agent POMDPs via Discrete-Time Barrier Functions
This addresses safety-critical planning for heterogeneous autonomous agents in uncertain, partially observable environments, representing an incremental advance by applying barrier functions to MPOMDPs.
The paper tackles the problem of ensuring safety in multi-agent partially observable Markov decision processes (MPOMDPs) by using discrete-time barrier functions to design policies, without relying on belief space discretization or finite memory, and demonstrates efficiency in high-fidelity robot simulations.
A multi-agent partially observable Markov decision process (MPOMDP) is a modeling paradigm used for high-level planning of heterogeneous autonomous agents subject to uncertainty and partial observation. Despite their modeling efficiency, MPOMDPs have not received significant attention in safety-critical settings. In this paper, we use barrier functions to design policies for MPOMDPs that ensure safety. Notably, our method does not rely on discretization of the belief space, or finite memory. To this end, we formulate sufficient and necessary conditions for the safety of a given set based on discrete-time barrier functions (DTBFs) and we demonstrate that our formulation also allows for Boolean compositions of DTBFs for representing more complicated safe sets. We show that the proposed method can be implemented online by a sequence of one-step greedy algorithms as a standalone safe controller or as a safety-filter given a nominal planning policy. We illustrate the efficiency of the proposed methodology based on DTBFs using a high-fidelity simulation of heterogeneous robots.