Wheelchair real-time obstacle prediction and avoidance system and method based on multi-target tracking
By adopting an obstacle prediction and evasion system based on multi-objective tracking on an intelligent driving wheelchair, the problem of insufficient dynamic obstacle recognition and prediction in the prior art is solved, and efficient evasion and safe driving in complex environments are achieved.
Patent Information
- Application Number
- CN202510197113.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-21
- Publication Date
- 2025-05-13
AI Technical Summary
Existing intelligent driving wheelchairs are difficult to effectively identify and predict dynamic obstacles in complex environments, resulting in limited performance and application potential in complex dynamic environments.
A wheelchair real-time obstacle prediction and avoidance system based on multi-objective tracking is adopted. The system includes a data acquisition and processing module, an obstacle detection and tracking module, a decision control module, an interaction module and a communication module. Through technical means such as multi-dimensional feature generation, dynamic obstacle similarity calculation, credibility score and path evaluation function, real-time monitoring and avoidance of obstacles are achieved.
It realizes efficient obstacle detection and avoidance under the premise of low computing volume, improves the performance and application potential of intelligent driving wheelchairs in complex dynamic environments, and ensures the safety of users.