一种水面无人船MPC控制器参数自适应整定方法及系统
By introducing a visual language model for semantic reasoning and risk quantification on unmanned surface vessels, and dynamically adjusting the parameters of the MPC controller, the problems of response lag and energy consumption contradictions of traditional controllers in complex waters are solved, achieving high-precision trajectory tracking and risk avoidance control, and reducing costs.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HARBIN ENG UNIV
- Filing Date
- 2026-05-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing unmanned surface vessels suffer from parameter adjustment lag and blindness in complex waters, making it impossible to balance trajectory tracking accuracy and control energy consumption. Furthermore, traditional controllers lack environmental semantic understanding, leading to untimely responses and collision risks.
A Visual Language Model (VLM) is introduced for semantic reasoning, extracting environmental semantic features and quantifying them into risk factors. The state and control weight matrix of the MPC controller are dynamically adjusted to construct a real-time closed-loop control system and achieve forward-looking parameter adaptive tuning.
It has achieved high-precision trajectory tracking and hazard avoidance control of unmanned vessels in complex waters, reduced energy consumption, improved control robustness and hazard avoidance capabilities, and reduced deployment and operating costs.
Smart Images
Figure CN122172589B_ABST