Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation

Alex Church, John Lloyd, raia hadsell, Nathan F. Lepora
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1645-1654, 2022.

Abstract

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its direct relation to environment interaction. In this work, we present a suite of simulated environments tailored towards tactile robotics and reinforcement learning. A simple and fast method of simulating optical tactile sensors is provided, where high-resolution contact geometry is represented as depth images. Proximal Policy Optimisation (PPO) is used to learn successful policies across all considered tasks. A data-driven approach enables translation of the current state of a real tactile sensor to corresponding simulated depth images. This policy is implemented within a real-time control loop on a physical robot to demonstrate zero-shot sim-to-real policy transfer on several physically-interactive tasks requiring a sense of touch.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-church22a, title = {Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation}, author = {Church, Alex and Lloyd, John and hadsell, raia and Lepora, Nathan F.}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1645--1654}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/church22a/church22a.pdf}, url = {https://proceedings.mlr.press/v164/church22a.html}, abstract = {Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its direct relation to environment interaction. In this work, we present a suite of simulated environments tailored towards tactile robotics and reinforcement learning. A simple and fast method of simulating optical tactile sensors is provided, where high-resolution contact geometry is represented as depth images. Proximal Policy Optimisation (PPO) is used to learn successful policies across all considered tasks. A data-driven approach enables translation of the current state of a real tactile sensor to corresponding simulated depth images. This policy is implemented within a real-time control loop on a physical robot to demonstrate zero-shot sim-to-real policy transfer on several physically-interactive tasks requiring a sense of touch. } }
Endnote
%0 Conference Paper %T Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation %A Alex Church %A John Lloyd %A raia hadsell %A Nathan F. Lepora %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-church22a %I PMLR %P 1645--1654 %U https://proceedings.mlr.press/v164/church22a.html %V 164 %X Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its direct relation to environment interaction. In this work, we present a suite of simulated environments tailored towards tactile robotics and reinforcement learning. A simple and fast method of simulating optical tactile sensors is provided, where high-resolution contact geometry is represented as depth images. Proximal Policy Optimisation (PPO) is used to learn successful policies across all considered tasks. A data-driven approach enables translation of the current state of a real tactile sensor to corresponding simulated depth images. This policy is implemented within a real-time control loop on a physical robot to demonstrate zero-shot sim-to-real policy transfer on several physically-interactive tasks requiring a sense of touch.
APA
Church, A., Lloyd, J., hadsell, r. & Lepora, N.F.. (2022). Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1645-1654 Available from https://proceedings.mlr.press/v164/church22a.html.

Related Material