Learning Efficient Multi-Agent Cooperative Visual Exploration

10/12/2021
by   Chao Yu, et al.
0

We consider the task of visual indoor exploration with multiple agents, where the agents need to cooperatively explore the entire indoor region using as few steps as possible. Classical planning-based methods often suffer from particularly expensive computation at each inference step and a limited expressiveness of cooperation strategy. By contrast, reinforcement learning (RL) has become a trending paradigm for tackling this challenge due to its modeling capability of arbitrarily complex strategies and minimal inference overhead. We extend the state-of-the-art single-agent RL solution, Active Neural SLAM (ANS), to the multi-agent setting by introducing a novel RL-based global-goal planner, Spatial Coordination Planner (SCP), which leverages spatial information from each individual agent in an end-to-end manner and effectively guides the agents to navigate towards different spatial goals with high exploration efficiency. SCP consists of a transformer-based relation encoder to capture intra-agent interactions and a spatial action decoder to produce accurate goals. In addition, we also implement a few multi-agent enhancements to process local information from each agent for an aligned spatial representation and more precise planning. Our final solution, Multi-Agent Active Neural SLAM (MAANS), combines all these techniques and substantially outperforms 4 different planning-based methods and various RL baselines in the photo-realistic physical testbed, Habitat.

READ FULL TEXT

page 5

page 17

research
07/23/2021

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

Exploration is critical for good results in deep reinforcement learning ...
research
01/09/2023

Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration

We consider the problem of cooperative exploration where multiple robots...
research
09/23/2019

Active collaboration in relative observation for Multi-agent visual SLAM based on Deep Q Network

This paper proposes a unique active relative localization mechanism for ...
research
12/28/2021

Embodied Learning for Lifelong Visual Perception

We study lifelong visual perception in an embodied setup, where we devel...
research
11/15/2022

Learning-Augmented Model-Based Planning for Visual Exploration

We consider the problem of time-limited robotic exploration in previousl...
research
11/23/2019

Corpus-Level End-to-End Exploration for Interactive Systems

A core interest in building Artificial Intelligence (AI) agents is to le...
research
11/29/2022

Multi-robot Social-aware Cooperative Planning in Pedestrian Environments Using Multi-agent Reinforcement Learning

Safe and efficient co-planning of multiple robots in pedestrian particip...

Please sign up or login with your details

Forgot password? Click here to reset