Adaptive energy-efficient reinforcement learning for AUV 3D motion planning in complex underwater environments
Authors:
- Jiayi WenJWJiayi Wen
- Anqing WangAWAnqing Wang
- Jingwei ZhuJZJingwei Zhu
- Fengbei XiaFXFengbei Xia
- Zhouhua PengZPZhouhua Peng
- Weidong ZhangWZWeidong Zhang
- 6 September 2024
- journal article
- research article
- Published by Elsevier in Ocean Engineering
- Vol. 312
Abstract
No abstract availableKeywords
Funding Information
- National Major Science and Technology Projects of China (2022ZD0119903)
- National Natural Science Foundation of China (52471372)
- National Natural Science Foundation of China (62203081)
- National Natural Science Foundation of China (52377037)
This publication has 49 references indexed in Scilit:
- An autonomous coverage path planning algorithm for maritime search and rescue of persons-in-water based on deep reinforcement learningOcean Engineering, 2023
- Deep hierarchical reinforcement learning based formation planning for multiple unmanned surface vehicles with experimental resultsOcean Engineering, 2023
- Improved reinforcement learning for collision-free local path planning of dynamic obstacleOcean Engineering, 2023
- Path planning for underwater gliders in time-varying ocean current using deep reinforcement learningOcean Engineering, 2022
- AUV path tracking with real-time obstacle avoidance via reinforcement learning under adaptive constraintsOcean Engineering, 2022
- COLREGs-abiding hybrid collision avoidance algorithm based on deep reinforcement learning for USVsOcean Engineering, 2022
- Safe deep reinforcement learning-based adaptive control for USV interception missionOcean Engineering, 2022
- Path planning and dynamic collision avoidance algorithm under COLREGs via deep reinforcement learningNeurocomputing, 2022
- Intelligent collision avoidance algorithms for USVs via deep reinforcement learning under COLREGsOcean Engineering, 2020
- Collision-avoidance under COLREGS for unmanned surface vehicles via deep reinforcement learningMaritime Policy & Management, 2020