Intent-based Deep Reinforcement Learning for Multi-agent Informative Path Planning

被引:0
|
作者
Yang, Tianze [1 ]
Cao, Yuhong [1 ]
Sartoretti, Guillaume [1 ]
机构
[1] Natl Univ Singapore, Coll Design & Engn, Dept Mech Engn, Singapore, Singapore
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In multi-agent informative path planning (MAIPP), agents must collectively construct a global belief map of an underlying distribution of interest (e.g., gas concentration, light intensity, or pollution levels) over a given domain, based on measurements taken along their trajectory. They must frequently replan their path to balance the exploration of new areas with the exploitation of known high-interest areas, to maximize information gain within a predefined budget. Traditional approaches rely on reactive path planning conditioned on other agents' predicted future actions. However, as the belief is continuously updated, the predicted actions may not match the executed actions, introducing noise and reducing performance. We propose a decentralized, deep reinforcement learning (DRL) approach using an attention-based neural network, where agents optimize long-term individual and cooperative objectives by sharing their intent, represented as a distribution of medium-/long-term future positions obtained from their own policy. Intent sharing enables agents to learn to claim or avoid broader areas, while the use of attention mechanisms allows them to identify useful portions of imperfect predictions, maximizing cooperation even based on imperfect information. Our experiments compare the performance of our approach, its variants, and high-quality baselines across various MAIPP scenarios. We finally demonstrate the effectiveness of our approach under limited communication ranges, towards deployments under realistic communication constraints.
引用
收藏
页码:71 / 77
页数:7
相关论文
共 50 条
  • [1] Intent-based multi-agent reinforcement learning for service assurance in cellular networks
    Perepu, Satheesh K.
    Martins, Jean P.
    Souza, Ricardo S.
    Dey, Kaushik
    [J]. 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 2879 - 2884
  • [2] Deep Reinforcement Learning for Image-Based Multi-Agent Coverage Path Planning
    Xu, Meng
    She, Yechao
    Jin, Yang
    Wang, Jianping
    [J]. 2023 IEEE 98TH VEHICULAR TECHNOLOGY CONFERENCE, VTC2023-FALL, 2023,
  • [3] Multi-agent Coverage Path Planning Based on Security Reinforcement Learning
    Li S.
    Ma Z.
    Zhang Y.
    Shao J.
    [J]. Binggong Xuebao/Acta Armamentarii, 2023, 44 : 101 - 113
  • [4] Multi-UAV Path Planning and Following Based on Multi-Agent Reinforcement Learning
    Zhao, Xiaoru
    Yang, Rennong
    Zhong, Liangsheng
    Hou, Zhiwei
    [J]. DRONES, 2024, 8 (01)
  • [5] Research on Path-planning of Manipulator based on Multi-agent Reinforcement Learning
    Tong, Liang
    [J]. FRONTIERS OF MANUFACTURING AND DESIGN SCIENCE, PTS 1-4, 2011, 44-47 : 2116 - 2120
  • [6] Improved Multi-Agent Reinforcement Learning for Path Planning-Based Crowd Simulation
    Wang, Qingqing
    Liu, Hong
    Gao, Kaizhou
    Zhang, Le
    [J]. IEEE ACCESS, 2019, 7 : 73841 - 73855
  • [7] Attention-Cooperated Reinforcement Learning for Multi-agent Path Planning
    Ma, Jinchao
    Lian, Defu
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS. DASFAA 2022 INTERNATIONAL WORKSHOPS, 2022, 13248 : 272 - 290
  • [8] Energy Constrained Multi-Agent Reinforcement Learning for Coverage Path Planning
    Zhao, Chenyang
    Liu, Juan
    Yoon, Suk-Un
    Li, Xinde
    Li, Heqing
    Zhang, Zhentong
    [J]. 2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2023, : 5590 - 5597
  • [9] Intent-aware Multi-agent Reinforcement Learning
    Qi, Siyuan
    Zhu, Song-Chun
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2018, : 7533 - 7540
  • [10] A Multi-agent Path Planning Algorithm Based on Hierarchical Reinforcement Learning and Artificial Potential Field
    Zheng, Yanbin
    Li, Bo
    An, Deyu
    Li, Na
    [J]. 2015 11TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2015, : 363 - 369