Learning to Solve a Rubik’s Cube with a Dexterous Hand
Authors:
- 1 December 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1387-1393
Abstract
We present a learning-based approach to solving a Rubik’s cube with a multi-fingered dexterous hand. Despite the promising performance of dexterous in-hand manipulation, solving complex tasks which involve multiple steps and diverse internal object structure has remained an important, yet challenging task. In this paper, we tackle this challenge with a hierarchical deep reinforcement learning method, which separates planning and manipulation. A model-based cube solver finds an optimal move sequence for restoring the cube and a model-free cube operator controls all five fingers to execute each move step by step. To train our models, we build a high-fidelity simulator which manipulates a Rubik’s Cube, an object containing high-dimensional state space, with a 24-DoF robot hand. Extensive experiments on 1400 randomly scrambled Rubik’s cubes demonstrate the effectiveness of our method, achieving an average success rate of 90.3%. To benefit the community, we make our simulator and source code publicly available to advance future research 1 .Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- In-Hand Manipulation via Motion Cones2018
- A hybrid 3DoF pose estimation method based on camera and lidar data2017
- Springer Handbook of Robotics2016
- Optimal control with learned local models: Application to dexterous manipulation2016
- Simulation tools for model-based robotics: Comparison of Bullet, Havok, MuJoCo, ODE and PhysX2015
- Dexterous manipulation using both palm and fingers2014
- The Diameter of the Rubik's Cube Group Is TwentySIAM Review, 2014
- MuJoCo: A physics engine for model-based control2012
- Harnessing parallel disks to solve Rubik’s cubeJournal of Symbolic Computation, 2009
- Rubik's cube as a benchmark validating MRROC++ as an implementation tool for service robot control systemsIndustrial Robot: the international journal of robotics research and application, 2007