Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates

TL;DR

This paper introduces a decentralized neural barrier certificate framework for multi-agent control, enabling scalable, safe, and generalizable coordination among many agents in complex environments.

Contribution

It presents a novel joint-learning approach for control policies and barrier functions, scalable to large numbers of agents, with neural architectures invariant to agent permutations.

Findings

Outperforms existing methods in safety and task completion

Demonstrates strong generalization from small to large agent populations

Enables decentralized control with scalability to 1024 agents

Abstract

We study the multi-agent safe control problem where agents should avoid collisions to static obstacles and collisions with each other while reaching their goals. Our core idea is to learn the multi-agent control policy jointly with learning the control barrier functions as safety certificates. We propose a novel joint-learning framework that can be implemented in a decentralized fashion, with generalization guarantees for certain function classes. Such a decentralized framework can adapt to an arbitrarily large number of agents. Building upon this framework, we further improve the scalability by incorporating neural network architectures that are invariant to the quantity and permutation of neighboring agents. In addition, we propose a new spontaneous policy refinement method to further enforce the certificate condition during testing. We provide extensive experiments to demonstrate that our method significantly outperforms other leading multi-agent control approaches in terms of maintaining safety and completing original tasks. Our approach also shows exceptional generalization capability in that the control policy can be trained with 8 agents in one scenario, while being used on other scenarios with up to 1024 agents in complex multi-agent environments and dynamics.