2018/04/11 by Balakumar Sundaralingam, Sundaralingam, Balakumar, Tucker Hermans +1 · 2 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotic Mechanisms and Dynamics #Robotic Path Planning Algorithms #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.1804.04292
openalex publication_date 2018/04/11 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28
This paper explores the problem of autonomous, in-hand regrasping--the\nproblem of moving from an initial grasp on an object to a desired grasp using\nthe dexterity of a robot's fingers. We propose a planner for this problem which\nalternates between finger gaiting, and in-grasp manipulation. Finger gaiting\nenables the robot to move a single finger to a new contact location on the\nobject, while the remaining fingers stably hold the object. In-grasp\nmanipulation moves the object to a new pose relative to the robot's palm, while\nmaintaining the contact locations between the hand and object. Given the\nobject's geometry (as a mesh), the hand's kinematic structure, and the initial\nand desired grasps, we plan a sequence of finger gaits and object reposing\nactions to reach the desired grasp without dropping the object. We propose an\noptimization based approach and report in-hand regrasping plans for 5 objects\nover 5 in-hand regrasp goals each. The plans generated by our planner are\ncollision free and guarantee kinematic feasibility.\n