Collision Avoidance Decision-Making Method for Unmanned Surface Vehicles Considering Uncertain Navigation Intent of Target Ships
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 27 (4) , 4750-4765
Abstract
In complex and dynamic maritime environments, the uncertain navigation intent of target ships (TS) poses a significant challenge for the collision avoidance strategies of unmanned surface vehicles (USVs). To address above issue, an autonomous collision avoidance method that integrates recursive Bayesian estimation, a masked attention mechanism, and the soft actor-critic (SAC) algorithm is proposed in this paper. Specifically, the recursive Bayesian model is employed to estimate the navigation intentions of TS in real time, for enabling the construction of intent-aware state representations that enhance the modeling capability for uncertain target behaviors. In addition, a maximum target count is predefined, and the masked attention mechanism is incorporated into the actor and critic networks of SAC to resolve the mismatch between the fixed input dimensionality of neural networks and the dynamically varying number of TS. Simulation demonstrates that the proposed method outperforms traditional collision avoidance methods and other state-of-the-art deep reinforcement learning (DRL)-based strategies in terms of key performance metrics such as collision avoidance success rate, minimum distance, and average risk. Furthermore, real-field experiments validate the proposed method’s adaptability to real-world maritime environments and its potential for practical deployment.Keywords
Funding Information
- National Natural Science Foundation of China (52571348)
- National Natural Science Foundation of China (52171309)
- Natural Science Foundation of Fujian Province, China, (2022J06025)
- Fujian Provincial Young Top-Notch Talent Plan
This publication has 41 references indexed in Scilit:
- Deep reinforcement learning for collision avoidance in unmanned surface vehicles: State-of-the-artApplied Ocean Research, 2025
- Real-time distributed decision-making for simultaneous target assignment and path planning in multiple unmanned surface vehiclesExpert Systems with Applications, 2025
- USV formation navigation decision-making through hybrid deep reinforcement learning using self-attention mechanismExpert Systems with Applications, 2024
- COLREGs-compliant unmanned surface vehicles collision avoidance based on improved differential evolution algorithmExpert Systems with Applications, 2023
- Spatial–temporal recurrent reinforcement learning for autonomous shipsNeural Networks, 2023
- Risk-based implementation of COLREGs for autonomous surface vehicles using deep reinforcement learningNeural Networks, 2022
- Path planning and dynamic collision avoidance algorithm under COLREGs via deep reinforcement learningNeurocomputing, 2022
- Local path planning for autonomous mobile robots by integrating modified dynamic‐window approach and improved follow the gap methodJournal of Field Robotics, 2021
- A path planning strategy unified with a COLREGS collision avoidance function based on deep reinforcement learning and artificial potential fieldApplied Ocean Research, 2021
- Collision risk assessment for shipsJournal of Marine Science and Technology, 2010