Multi-AUV Path Planning Based on Hierarchical Opponent Multiactor-Attention-Critic Reinforcement Learning Framework
- 16 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (13) , 25948-25962
Abstract
The increasing exploitation of marine resources and intensifying human activities have led to significant marine pollution, highlighting the critical challenge of pollutant dispersal in aquatic environments. To address this challenge, we propose a path-planning framework based on multi-agent reinforcement learning to enable rapid deployment of detection equipment to polluted sites. Specifically, we propose a hierarchical opponent multi-actor-attention-critic framework (HOMAAC) to optimize equipment delivery path planning. In HOMAAC, the hierarchical graphical attention mechanism is employed to enhance cooperative perception and interaction among entities. Opponent modeling is innovatively employed to enhance collaboration efficiency and reduce conflicts among autonomous underwater vehicles (AUVs). This modeling approach enables each AUV to dynamically adjust its motion trajectory, thereby improving the efficiency and safety of equipment delivery and path planning. The results of experiments conducted in a multi-agent underwater logistics delivery environment validate the superior performance of the proposed framework in terms of task completion rate and time spent in addressing the path planning issue, providing valuable insights for the field of intelligent underwater delivery and marine environment monitoring.Keywords
Funding Information
- Joint Funds of the National Natural Science Foundation of China (U22A2011)
- Frontier Technologies Research and Development Program of Jiangsu (BF2024072)
- Open Fund of State Key Laboratory of Acoustics and Marine Information (SKLA202501)
- Fundamental Research Funds for the Central Universities (N25LPY014)
This publication has 30 references indexed in Scilit:
- Attentional Opponent Modelling for Multi-agent Cooperation2023
- Cooperative Formation Control for Multiple AUVs With Intermittent Underwater Acoustic Communication in IoUTIEEE Internet of Things Journal, 2023
- Multi-agent actor-critic with time dynamical opponent modelNeurocomputing, 2022
- Evaluation of Multi-Vehicular Underwater Transportation Systems under Disturbances, Sensor Noise and Limited Sensor Readings2022
- Comprehensive Ocean Information-Enabled AUV Path Planning Via Reinforcement LearningIEEE Internet of Things Journal, 2022
- Opponent portrait for multiagent reinforcement learning in competitive environmentInternational Journal of Intelligent Systems, 2021
- TWINBOT: Autonomous Underwater Cooperative TransportationIEEE Access, 2021
- XCS with opponent modelling for concurrent reinforcement learnersNeurocomputing, 2020
- Decentralized Impedance Control for Cooperative Manipulation of Multiple Underwater Vehicle Manipulator Systems under Lean Communication2018
- Design of chemical sensor arrays for monitoring disposal sites on the ocean floorIEEE Journal of Oceanic Engineering, 1998