目标定位方法、对接目标的方法及装置
By setting spaced reflective zones on the target and calculating the pose using laser reflection angles and point cloud data, the problem of low accuracy in close-range robot recognition was solved, achieving high-precision target docking.
CN116953719BActive Publication Date: 2026-07-17ZHEJIANG HUARAY TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG HUARAY TECH CO LTD
- Filing Date
- 2023-06-30
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing robot target recognition methods show a significant drop in recognition accuracy when the distance to the target to be docked is very close, making it difficult to accurately determine the pose.
Method used
At least three spaced first reflection zones are set on the target. Point cloud data is generated by scanning with a laser. The pose of the target in the laser reference frame is determined by filtering and calculating the reflection angle and spacing. Path planning is performed in combination with compensation values to improve recognition accuracy.
Benefits of technology
It improves the positioning accuracy of the target in close-range situations, ensuring that the robot can accurately identify and dock with the target's pose, thus improving docking accuracy.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116953719B_ABST
Abstract
本申请公开了一种目标定位方法、对接目标的方法及装置。目标上至少设置有三个间隔分布的第一反射区，每两个相邻的第一反射区之间的区域为第二反射区，第一反射区的反光性能不同于第二反射区的反光性能，该目标定位方法包括：方法包括：获取由激光器对目标上的第一反射区及第二反射区进行扫描而生成的点云数据；基于点云数据中各点的反射强度，从点云数据中筛选出三个第一反射区的点云；基于每个第一反射区的点云，计算每个第一反射区中心的激光反射角度；基于三个第一反射区中心的激光反射角度以及相邻两个第一反射区中心之间的间距，计算出目标在激光参考系下的位姿。本申请在与目标距离较近时也能较为精确地识别出目标的位姿。
Need to check novelty before this filing date? Find Prior Art