一种AMR机器人避障急停的智能控制方法、系统和介质
By predicting the encounter time based on obstacle position and motion information from image and point cloud data, and dynamically adjusting the emergency stop control of the AMR, the problem of improper handling of dynamic obstacles in the prior art is solved, and a balance between safety and efficiency of the AMR in complex environments is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN JINGZHI HI TECH ROBOT CO LTD
- Filing Date
- 2025-08-25
- Publication Date
- 2026-07-17
AI Technical Summary
Existing obstacle avoidance methods for AMR robots rely on fixed safety distance thresholds, which cannot effectively handle dynamic obstacles. This can lead to premature emergency stops affecting efficiency or untimely obstacle avoidance causing collision risks, resulting in an imbalance between safety and efficiency.
Based on the raw image data and point cloud data of the AMR robot in the target scene, the position coordinates of the obstacle are determined. Combined with real-time positioning information, the speed and direction of the obstacle are calculated, the shortest encounter time is predicted, and the emergency stop control command is dynamically adjusted to ensure a balance between safety and efficiency.
By combining obstacle location, motion information, and AMR real-time positioning, collision risk is quantified, achieving a balance between safety and efficiency of AMR in dynamic environments and avoiding problems such as premature emergency stops or untimely obstacle avoidance.
Smart Images
Figure CN121050425B_ABST