Multi-Agent Safe Planning with Gaussian Processes

TL;DR

This paper presents a decentralized safe learning algorithm for multi-agent systems that ensures safety during navigation with minimal prior knowledge about other agents, demonstrated through robotic experiments.

Contribution

It introduces a novel multi-agent safe learning method using Gaussian processes that operates in a decentralized manner with mild assumptions.

Findings

Algorithm performs well with robots running other algorithms

Ensures safety in multi-agent navigation

Operates with minimal prior knowledge

Abstract

Multi-agent safe systems have become an increasingly important area of study as we can now easily have multiple AI-powered systems operating together. In such settings, we need to ensure the safety of not only each individual agent, but also the overall system. In this paper, we introduce a novel multi-agent safe learning algorithm that enables decentralized safe navigation when there are multiple different agents in the environment. This algorithm makes mild assumptions about other agents and is trained in a decentralized fashion, i.e. with very little prior knowledge about other agents' policies. Experiments show our algorithm performs well with the robots running other algorithms when optimizing various objectives.