DRL-searcher: A unified approach to multi-robot efficient search for a moving target

This article studies the multirobot efficient search (MuRES) for a nonadversarial moving target problem, whose objective is usually defined as either minimizing the target’s expected capture time or maximizing the target’s capture probability within a given time budget. Different from canonical MuRE...

Full description

Saved in:
Bibliographic Details
Main Authors: GUO, Hongliang, PENG, Qihang, CAO, Zhiguang, JIN, Yaochu
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8217
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9220
record_format dspace
spelling sg-smu-ink.sis_research-92202023-10-13T09:18:03Z DRL-searcher: A unified approach to multi-robot efficient search for a moving target GUO, Hongliang PENG, Qihang CAO, Zhiguang JIN, Yaochu This article studies the multirobot efficient search (MuRES) for a nonadversarial moving target problem, whose objective is usually defined as either minimizing the target’s expected capture time or maximizing the target’s capture probability within a given time budget. Different from canonical MuRES algorithms, which target only one specific objective, our proposed algorithm, named distributional reinforcement learning-based searcher (DRL-Searcher), serves as a unified solution to both MuRES objectives. DRL-Searcher employs distributional reinforcement learning (DRL) to evaluate the full distribution of a given search policy’s return, that is, the target’s capture time, and thereafter makes improvements with respect to the particularly specified objective. We further adapt DRL-Searcher to the use case without the target’s real-time location information, where only the probabilistic target belief (PTB) information is provided. Lastly, the recency reward is designed for implicit coordination among multiple robots. Comparative simulation results in a range of MuRES test environments show the superior performance of DRL-Searcher to state of the arts. Additionally, we deploy DRL-Searcher to a real multirobot system for moving target search in a self-constructed indoor environment with satisfying results. 2023-05-22T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/8217 info:doi/10.1109/TNNLS.2023.3274667 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Budget control Heuristic algorithms Industrial robots Learning algorithms Modular robots Multipurpose robots Robot learning Artificial Intelligence and Robotics Theory and Algorithms
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Budget control
Heuristic algorithms
Industrial robots
Learning algorithms
Modular robots
Multipurpose robots
Robot learning
Artificial Intelligence and Robotics
Theory and Algorithms
spellingShingle Budget control
Heuristic algorithms
Industrial robots
Learning algorithms
Modular robots
Multipurpose robots
Robot learning
Artificial Intelligence and Robotics
Theory and Algorithms
GUO, Hongliang
PENG, Qihang
CAO, Zhiguang
JIN, Yaochu
DRL-searcher: A unified approach to multi-robot efficient search for a moving target
description This article studies the multirobot efficient search (MuRES) for a nonadversarial moving target problem, whose objective is usually defined as either minimizing the target’s expected capture time or maximizing the target’s capture probability within a given time budget. Different from canonical MuRES algorithms, which target only one specific objective, our proposed algorithm, named distributional reinforcement learning-based searcher (DRL-Searcher), serves as a unified solution to both MuRES objectives. DRL-Searcher employs distributional reinforcement learning (DRL) to evaluate the full distribution of a given search policy’s return, that is, the target’s capture time, and thereafter makes improvements with respect to the particularly specified objective. We further adapt DRL-Searcher to the use case without the target’s real-time location information, where only the probabilistic target belief (PTB) information is provided. Lastly, the recency reward is designed for implicit coordination among multiple robots. Comparative simulation results in a range of MuRES test environments show the superior performance of DRL-Searcher to state of the arts. Additionally, we deploy DRL-Searcher to a real multirobot system for moving target search in a self-constructed indoor environment with satisfying results.
format text
author GUO, Hongliang
PENG, Qihang
CAO, Zhiguang
JIN, Yaochu
author_facet GUO, Hongliang
PENG, Qihang
CAO, Zhiguang
JIN, Yaochu
author_sort GUO, Hongliang
title DRL-searcher: A unified approach to multi-robot efficient search for a moving target
title_short DRL-searcher: A unified approach to multi-robot efficient search for a moving target
title_full DRL-searcher: A unified approach to multi-robot efficient search for a moving target
title_fullStr DRL-searcher: A unified approach to multi-robot efficient search for a moving target
title_full_unstemmed DRL-searcher: A unified approach to multi-robot efficient search for a moving target
title_sort drl-searcher: a unified approach to multi-robot efficient search for a moving target
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8217
_version_ 1781793935630270464