Collision Avoidance Verification of Multiagent Systems with Learned Policies

arXiv:2403.03314v1 Announce Type: cross
Abstract: For many multiagent control problems, neural networks (NNs) have enabled promising new capabilities. However, many of these systems lack formal guarantees (e.g., collision avoidance, robustness), which prevents leveraging these advances in safety-critical settings. While there is recent work on formal verification of NN-controlled systems, most existing techniques cannot handle scenarios with more than one agent. To address this research gap, this paper presents a backward reachability-based approach for verifying the collision avoidance properties of Multi-Agent …

abstract advances arxiv capabilities collision control cs.lg cs.ma cs.ro cs.sy eess.sy however networks neural networks nns robustness safety safety-critical systems type verification work