Multi Robot Collision Avoidance by Learning Whom to Communicate

09/14/2022
by   Senthil Hariharan Arul, et al.
0

Agents in decentralized multi-agent navigation lack the world knowledge to make safe and (near-)optimal plans reliably. They base their decisions on their neighbors' observable states, which hide the neighbors' navigation intent. We propose augmenting decentralized navigation with inter-agent communication to improve their performance and aid agent in making sound navigation decisions. In this regard, we present a novel reinforcement learning method for multi-agent collision avoidance using selective inter-agent communication. Our network learns to decide 'when' and with 'whom' to communicate to request additional information in an end-to-end fashion. We pose communication selection as a link prediction problem, where the network predicts if communication is necessary given the observable information. The communicated information augments the observed neighbor information to select a suitable navigation plan. As the number of neighbors for a robot varies, we use a multi-head self-attention mechanism to encode neighbor information and create a fixed-length observation vector. We validate that our proposed approach achieves safe and efficient navigation among multiple robots in challenging simulation benchmarks. Aided by learned communication, our network performs significantly better than existing decentralized methods across various metrics such as time-to-goal and collision frequency. Besides, we showcase that the network effectively learns to communicate when necessary in a situation of high complexity.

READ FULL TEXT
research
09/22/2016

Deep-Learned Collision Avoidance Policy for Distributed Multi-Agent Navigation

High-speed, low-latency obstacle avoidance that is insensitive to sensor...
research
10/11/2017

ALAN: Adaptive Learning for Multi-Agent Navigation

In multi-agent navigation, agents need to move towards their goal locati...
research
09/25/2020

With Whom to Communicate: Learning Efficient Communication for Multi-Robot Collision Avoidance

Decentralized multi-robot systems typically perform coordinated motion p...
research
09/12/2021

Learning Selective Communication for Multi-Agent Path Finding

Learning communication via deep reinforcement learning (RL) or imitation...
research
10/04/2019

DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local Global Collision Avoidance

We present a novel algorithm (DeepMNavigate) for global multi-agent navi...
research
07/01/2021

Distributed Multi-agent Navigation Based on Reciprocal Collision Avoidance and Locally Confined Multi-agent Path Finding

Avoiding collisions is the core problem in multi-agent navigation. In de...
research
06/15/2023

Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization

This paper presents a fully decentralized approach for realtime non-coop...

Please sign up or login with your details

Forgot password? Click here to reset