Learning Keypoint Constraints from Visual Demonstrations for Safe Motion Planning

We present Keypoint Constraint Learning (KCL), a framework for learning task-relevant motion constraints from visual demonstrations and for planning safely with the extracted constraints. To make constraint learning tractable from RGB-D observations, we represent demonstrations using sparse 3D object-centric keypoints and semantic mask centroids extracted through segmentation, visual feature clustering, and point tracking.

초록에서 가져왔습니다. 요약을 준비 중입니다.