基于TAM-HRL的水下航行器三维隐蔽路径规划方法及系统
By using the TAM-HRL method, combining three-dimensional terrain and acoustic detection probability field, and employing a multi-layer network structure for path planning, the problems of insufficient acoustic risk distribution and multi-target coupling in existing technologies are solved, enabling safe, stealthy, and smooth navigation of underwater vehicles.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ANHUI UNIV
- Filing Date
- 2026-05-26
- Publication Date
- 2026-07-17
AI Technical Summary
Existing underwater vehicle path planning methods cannot accurately reflect the acoustic risk distribution in real marine environments, leading to unstable training, policy oscillations, and uneven trajectories. Furthermore, multi-objective coupling results in frequent sub-task switching.
A three-dimensional covert path planning method based on TAM-HRL is adopted. By constructing a three-dimensional terrain field and an acoustic detection probability field, and combining multiple low-level sub-policy networks and high-level temporal decision networks, a weighted fusion of action probability distributions and responsibility allocation are performed to generate a safe, covert and smooth navigation path.
It improves the stability and security of path planning, reduces the learning difficulty of multi-objective coupling, and enhances the robustness and continuity of path planning in complex environments.
Smart Images
Figure CN122258932B_ABST