DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality
Authors:
Top Cited Papers
- 29 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5977-5984
Abstract
Recent work has demonstrated the ability of deep reinforcement learning (RL) algorithms to learn complex robotic behaviours in simulation, including in the domain of multi-fingered manipulation. However, such models can be challenging to transfer to the real world due to the gap between simulation and reality. In this paper, we present our techniques to train a) a policy that can perform robust dexterous manipulation on an anthropomorphic robot hand and b) a robust pose estimator suitable for providing reliable real-time information on the state of the object being manipulated. Our policies are trained to adapt to a wide range of conditions in simulation. Consequently, our vision-based policies significantly outperform the best vision policies in the literature on the same reorientation task and are competitive with policies that are given privileged state information via motion capture systems. Our work reaffirms the possibilities of sim-to-real transfer for dexterous manipulation in diverse kinds of hardware and simulator setups, and in our case, with the Allegro Hand and Isaac Gym GPU-based simulation. Furthermore, it opens up possibilities for researchers to achieve such results with commonly-available, affordable robot hands and cameras. Videos of the resulting policy and supplementary information, including experiments and demos, can be found on the website.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Learning agile and dynamic motor skills for legged robotsScience Robotics, 2019
- Sim-to-Real Transfer of Robotic Control with Dynamics Randomization2018
- Mask R-CNN2017
- Optimal control with learned local models: Application to dexterous manipulation2016
- MuJoCo: A physics engine for model-based control2012
- Long Short-Term MemoryNeural Computation, 1997
- Noise and the reality gap: The use of simulation in evolutionary robotics1995
- Grasping and Coordinated Manipulation by a Multifingered Robot HandThe International Journal of Robotics Research, 1989
- Articulated HandsThe International Journal of Robotics Research, 1982