Learning Communication-Conditioned Generative Policies for Decentralized Multi-Agent Collision Avoidance

2026-09-13

AI Summary

本文提出了一种基于通信条件生成策略的去中心化多智能体避碰框架，通过从全局状态下的特权离线演示中训练流匹配策略，使智能体在部分可观测条件下学习交换和聚合潜在消息，从而实现协调交互。

Abstract

In this work, we propose a decentralized communication-conditioned generative framework for multi-agent collision avoidance. Agents generate short-horizon action sequences using a flow-matching policy trained from privileged offline demonstrations with access to global state. The demonstrations do not include explicit communication signals; instead, agents learn to exchange and aggregate latent messages that encode interaction-relevant intent under partial observability. This formulation supports flexible inference at test time, where unconditioned generation corresponds to independent behavior and communication-conditioned generation enables coordinated interaction without centralized planning. The resulting policies operate in a fully decentralized manner at execution time, relying only on local observations and learned messages. Combined with a receding-horizon inference scheme, the proposed approach enables efficient single-step inference of short-horizon action sequences and degrades gracefully under communication dropouts. Extensive simulation results demonstrate near-expert collision avoidance performance and strong generalization to denser, unseen multi-agent scenarios, along with zero-shot transfer to real-robot experiments.

Problem

• Multi-Agent Collision Avoidance
• Decentralized Control
• Communication-Conditioned Generation

Innovation

• decentralized
• communication-conditioned
• flow-matching policy
• latent messages
• receding-horizon inference