Grasp and Motion Planning for Dexterous Manipulation for the Real Robot Challenge
This work provides a competitive solution for dexterous manipulation of rectangular objects on the TriFinger Platform, demonstrating strong performance in a real-world robotics challenge.
This paper details the winning submission to the Real Robot Challenge, a dexterous manipulation competition using the TriFinger Platform to manipulate rectangular objects. Their method, which combines motion planning with motion primitives and a learned residual policy for Phases 1 and 2, secured first place in Phases 2 and 3 of the competition.
This report describes our winning submission to the Real Robot Challenge (https://real-robot-challenge.com/). The Real Robot Challenge is a three-phase dexterous manipulation competition that involves manipulating various rectangular objects with the TriFinger Platform. Our approach combines motion planning with several motion primitives to manipulate the object. For Phases 1 and 2, we additionally learn a residual policy in simulation that applies corrective actions on top of our controller. Our approach won first place in Phase 2 and Phase 3 of the competition. We were anonymously known as `ardentstork' on the competition leaderboard (https://real-robot-challenge.com/leader-board). Videos and our code can be found at https://github.com/ripl-ttic/real-robot-challenge.