Multi-AUV Cooperative Path Planning Based on Plasticity Injection TD3 Framework for IoUT Data Collection
- 25 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1-17
Abstract
Multi-agent reinforcement learning for multi autonomous underwater vehicle path planning faces significant technical challenges in data collection tasks within the Internet of Underwater Things. These challenges are particularly pronounced under dynamic underwater conditions, where the policy network tends to prematurely converge on suboptimal policies, thereby undermining its adaptability to environmental variations. As adaptability continues to decline during extended exploration, training stagnates, and learning efficiency decreases. To address these challenges, we propose an adaptive plasticity injection based twin delayed deep deterministic policy gradient (PITD3) framework that integrates an adaptive trigger and a dual-mode plasticity injection method. The adaptive trigger continuously monitors fluctuations in reward and temporal difference loss, activating plasticity restoration when learning stagnates or exploration becomes inefficient. The dual-mode plasticity injection method reinitializes the actor head and critic heads through selective parameter injection, restoring learning capacity and preventing long-term performance degradation. Experimental results demonstrate that the proposed PITD3 framework out performs baseline frameworks, achieving substantial improvements in collision avoidance, data collection rate, and energy efficiency.Keywords
Funding Information
- National Natural Science Foundation of China (U22A2011)
- Open Fund of State Key Laboratory of Acoustics and Marine Information (SKLA202501)
- National Natural Science Foundation of China (62572107)
This publication has 36 references indexed in Scilit:
- Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions2025
- Autonomous PID Tuning: Two-Phase Reinforcement Learning Through Adversarial Imitation Learning Under Imperfect DemonstrationsIEEE Transactions on Automation Science and Engineering, 2025
- Cooperative Trajectory Tracking Control for USV-AUV Based Integral Terminal Sliding Mode Control2025
- Active Robust Adversarial Reinforcement Learning Under Temporally Coupled PerturbationsIEEE Transactions on Artificial Intelligence, 2024
- Environment- and Energy-Aware AUV-Assisted Data Collection for the Internet of Underwater ThingsIEEE Internet of Things Journal, 2024
- WToE: Learning When to Explore in Multiagent Reinforcement LearningIEEE Transactions on Cybernetics, 2023
- Nuclear Norm Maximization-Based Curiosity-Driven Reinforcement LearningIEEE Transactions on Artificial Intelligence, 2023
- A Multi-AUV Collaborative Ocean Data Collection Method Based on LG-DQN and Data ValueIEEE Internet of Things Journal, 2023
- Environment-Aware AUV Trajectory Design and Resource Management for Multi-Tier Underwater ComputingIEEE Journal on Selected Areas in Communications, 2022
- Design, Modeling, Control, and Experiments for Multiple AUVs FormationIEEE Transactions on Automation Science and Engineering, 2021