DeepAI
Log In Sign Up

Solving Rubik's Cube with a Robot Hand

10/16/2019
by   OpenAI, et al.
9

We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key components: a novel algorithm, which we call automatic domain randomization (ADR) and a robot platform built for machine learning. ADR automatically generates a distribution over randomized environments of ever-increasing difficulty. Control policies and vision state estimators trained with ADR exhibit vastly improved sim2real transfer. For control policies, memory-augmented models trained on an ADR-generated distribution of environments show clear signs of emergent meta-learning at test time. The combination of ADR with our custom robot platform allows us to solve a Rubik's cube with a humanoid robot hand, which involves both control and state estimation problems. Videos summarizing our results are available: https://openai.com/blog/solving-rubiks-cube/

READ FULL TEXT

page 2

page 4

page 5

page 6

page 8

page 9

page 17

page 24

10/25/2022

DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality

Recent work has demonstrated the ability of deep reinforcement learning ...
11/11/2021

Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation

Learning complex manipulation tasks in realistic, obstructed environment...
02/13/2019

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup

We present a method for fast training of vision based control policies o...
11/01/2021

Robot Learning from Randomized Simulations: A Review

The rise of deep learning has caused a paradigm shift in robotics resear...
12/05/2022

Learning Representations that Enable Generalization in Assistive Tasks

Recent work in sim2real has successfully enabled robots to act in physic...
08/03/2022

Learning Fast and Precise Pixel-to-Torque Control

In the field, robots often need to operate in unknown and unstructured e...
07/27/2018

Adapting control policies from simulation to reality using a pairwise loss

This paper proposes an approach to domain transfer based on a pairwise l...

Code Repositories

functional-rubiks-solver

Deterministic Rubik's Cube solver written in the Functional Programming style with Haskell.


view repo