Learning Extrinsic Dexterity with Parameterized Manipulation Primitives

arXiv:2310.17785v3 Announce Type: replace-cross
Abstract: Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first manipulate the object into a configuration that affords a grasp. We solve this problem by learning a sequence of actions that utilize the environment to change the object's pose. Concretely, we employ hierarchical reinforcement learning to combine a sequence of learned …

arxiv cs.lg cs.ro manipulation type