Multi-Contact Task and Motion Planning Guided by Video Demonstration

Kateryna Zorina,David Kovar,Florent Lamiraux,Nicolas Mansard,Justin Carpentier,Josef Sivic,Vladimir Petrik,Kateryna Zorina,David Kovar,Florent Lamiraux,Nicolas Mansard,Justin Carpentier,Josef Sivic,Vladimir Petrik

This work aims at leveraging instructional video to guide the solving of complex multi-contact task-and-motion planning tasks in robotics. Towards this goal, we propose an extension of the well-established Rapidly-Exploring Random Tree (RRT) planner, which simultaneously grows multiple trees around grasp and release states extracted from the guiding video. Our key novelty lies in combining contact...