When2com: Multi-Agent Perception via Communication Graph Grouping

Abstract

While significant advances have been made for single-agent perception, many applications require multiple sensing agents and cross-agent communication due to benefits such as coverage and robustness. It is therefore critical to develop frameworks which support multi-agent collaborative perception in a distributed and bandwidth-efficient manner. In this paper, we address the collaborative perception problem, where one agent is required to perform a perception task and can communicate and share information with other agents on the same task. Specifically, we propose a communication framework by learning both to construct communication groups and decide when to communicate. We demonstrate the generalizability of our framework on two different perception tasks and show that it significantly reduces communication bandwidth while maintaining superior performance.

Accepted to CVPR 2020; for the project page, see https://ycliu93.github.io/projects/multi-agent-perception.html

References in corpus (4)

• Interaction Networks for Learning about Objects, Relations and Physics
• Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
• Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
• Graph Convolutional Reinforcement Learning

Cited by in corpus (1)

• Learning Distilled Collaboration Graph for Multi-Agent Perception