A Shared Control Framework for Enhanced Grasping Performance in Teleoperation

Remote teleoperation has shown significant advancements since the first system was proposed by Goertz in 1940s. In recent years, research on shared control methodologies which robot assists operators accomplishing desired tasks gained extensive attention. One such important task is object grasping. this paper, we propose a framework to enhance teleoperated grasping performance. The built upon virtual reality device-based direct system. framework, template matching-based point cloud compensation introduced for multi-angle pose generation. Then, feasible candidates are selected considering joint constraints-aware manipulability. Finally, assistance achieved trajectory blending with dynamic authority adjustment. To validate performance of carried out experimental evaluations. output results indicate improved terms reduced completion time, linear trajectory, and workload.