Collision avoidance for unmanned surface vehicles via adversarial inverse reinforcement learning with diffusion model
Authors:
- Yuqin LiYLYuqin Li
- Defeng WuDWDefeng Wu
- Gouqiang LiGLGouqiang Li
- Zhenhong FanZFZhenhong Fan
- Dongjie WuDWDongjie Wu
- Qijun LiuQLQijun Liu
- 14 January 2026
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 167
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Fujian Province (2022J06025)
- National Natural Science Foundation of China (52171309)
- National Natural Science Foundation of China (52571348)
This publication has 32 references indexed in Scilit:
- USV formation navigation decision-making through hybrid deep reinforcement learning using self-attention mechanismExpert Systems with Applications, 2024
- COLERGs-constrained safe reinforcement learning for realising MASS's risk-informed collision avoidance decision makingKnowledge-Based Systems, 2024
- A human-like collision avoidance method for USVs based on deep reinforcement learning and velocity obstacleExpert Systems with Applications, 2024
- Reinforcement learning based robot navigation using illegal actions for autonomous docking of surface vehicles in unknown environmentsEngineering Applications of Artificial Intelligence, 2024
- COLREGs-compliant unmanned surface vehicles collision avoidance based on improved differential evolution algorithmExpert Systems with Applications, 2023
- Human-like route planning for automatic collision avoidance using generative adversarial imitation learningApplied Ocean Research, 2023
- Dynamic anti-collision A-star algorithm for multi-ship encounter situationsApplied Ocean Research, 2022
- Path planning and dynamic collision avoidance algorithm under COLREGs via deep reinforcement learningNeurocomputing, 2022
- A path planning strategy unified with a COLREGS collision avoidance function based on deep reinforcement learning and artificial potential fieldApplied Ocean Research, 2021
- Automatic ship collision avoidance using deep reinforcement learning with LSTM in continuous action spacesJournal of Marine Science and Technology, 2020