2025-03-07 00:00:00 +0000 - By Sipu Ruan
Instant Grasping Framework of Textured Objects via Precise Point Matches and Normalized Target Poses发表在机器人领域国际知名期刊Journal of Mechanisms and Robotics - ASME Transactions (JMR)！论文提出了基于高精度点云配准及位姿估计的机器人快速抓取新方法，可帮助机器人在不同光照条件、环境及人为扰动中完成物品抓取任务，提升了计算效率、抓取鲁棒性及成功率。
Our article entitled Instant Grasping Framework of Textured Objects via Precise Point Matches and Normalized Target Poses has been published in Journal of Mechanisms and Robotics - ASME Transactions (JMR)! This work proposes a novel two-stage robotic grasping method that instantly achieves accurate grasping without prior training. It is based on precise point cloud registration and normalized grasping pose estimation. Experiments demonstrate that the proposed method achieves high efficiency, robustness and success rates for grasping daily objects in various lighting conditions and disturbances.