Multiagent Hierarchical Reinforcement Learning with Asynchronous Termination applied to Robotic Pick and Place

Xi Lan; Yuansong Qiao; Brian Lee

doi:10.1109/ACCESS.2024.3409076

Multiagent Hierarchical Reinforcement Learning with Asynchronous Termination applied to Robotic Pick and Place

Xi Lan, Yuansong Qiao, Brian Lee

Limerick Institute of Technology,

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Recent breakthroughs in hierarchical multi-agent deep reinforcement learning (HMADRL) are propelling the development of sophisticated multi-robot systems, particularly in the realm of complex coordination tasks. These advancements hold significant potential for addressing the intricate challenges inherent in fast-evolving sectors such as intelligent manufacturing. In this study, we introduce an innovative simulator tailored for a multi-robot pick-and-place (PnP) operation, built upon the OpenAI Gym framework. Our aim is to demonstrate the efficacy of HMADRL algorithms for multi robot coordination in a manufacturing setting, concentrating on their influence on the gripping rate, a crucial indicator for gauging system performance and operational efficiency.

Original language	English
Pages (from-to)	78988-79002
Number of pages	15
Journal	IEEE Access
Volume	12
DOIs	https://doi.org/10.1109/ACCESS.2024.3409076
Publication status	Published - 2024

Keywords

Multi-agent system
asynchronous termination
multi-agent-hierarchical reinforcement learning
multi-robot system
pick and place

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ACCESS.2024.3409076

Cite this

@article{5903e7f58f2d4dc3b9980b7aaafd670e,

title = "Multiagent Hierarchical Reinforcement Learning with Asynchronous Termination applied to Robotic Pick and Place",

abstract = "Recent breakthroughs in hierarchical multi-agent deep reinforcement learning (HMADRL) are propelling the development of sophisticated multi-robot systems, particularly in the realm of complex coordination tasks. These advancements hold significant potential for addressing the intricate challenges inherent in fast-evolving sectors such as intelligent manufacturing. In this study, we introduce an innovative simulator tailored for a multi-robot pick-and-place (PnP) operation, built upon the OpenAI Gym framework. Our aim is to demonstrate the efficacy of HMADRL algorithms for multi robot coordination in a manufacturing setting, concentrating on their influence on the gripping rate, a crucial indicator for gauging system performance and operational efficiency.",

keywords = "Multi-agent system, asynchronous termination, multi-agent-hierarchical reinforcement learning, multi-robot system, pick and place",

author = "Xi Lan and Yuansong Qiao and Brian Lee",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2024",

doi = "10.1109/ACCESS.2024.3409076",

language = "English",

volume = "12",

pages = "78988--79002",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Multiagent Hierarchical Reinforcement Learning with Asynchronous Termination applied to Robotic Pick and Place

AU - Lan, Xi

AU - Qiao, Yuansong

AU - Lee, Brian

PY - 2024

Y1 - 2024

N2 - Recent breakthroughs in hierarchical multi-agent deep reinforcement learning (HMADRL) are propelling the development of sophisticated multi-robot systems, particularly in the realm of complex coordination tasks. These advancements hold significant potential for addressing the intricate challenges inherent in fast-evolving sectors such as intelligent manufacturing. In this study, we introduce an innovative simulator tailored for a multi-robot pick-and-place (PnP) operation, built upon the OpenAI Gym framework. Our aim is to demonstrate the efficacy of HMADRL algorithms for multi robot coordination in a manufacturing setting, concentrating on their influence on the gripping rate, a crucial indicator for gauging system performance and operational efficiency.

AB - Recent breakthroughs in hierarchical multi-agent deep reinforcement learning (HMADRL) are propelling the development of sophisticated multi-robot systems, particularly in the realm of complex coordination tasks. These advancements hold significant potential for addressing the intricate challenges inherent in fast-evolving sectors such as intelligent manufacturing. In this study, we introduce an innovative simulator tailored for a multi-robot pick-and-place (PnP) operation, built upon the OpenAI Gym framework. Our aim is to demonstrate the efficacy of HMADRL algorithms for multi robot coordination in a manufacturing setting, concentrating on their influence on the gripping rate, a crucial indicator for gauging system performance and operational efficiency.

KW - Multi-agent system

KW - asynchronous termination

KW - multi-agent-hierarchical reinforcement learning

KW - multi-robot system

KW - pick and place

UR - http://www.scopus.com/inward/record.url?scp=85195396773&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2024.3409076

DO - 10.1109/ACCESS.2024.3409076

M3 - Article

AN - SCOPUS:85195396773

SN - 2169-3536

VL - 12

SP - 78988

EP - 79002

JO - IEEE Access

JF - IEEE Access

ER -

Multiagent Hierarchical Reinforcement Learning with Asynchronous Termination applied to Robotic Pick and Place

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this