EXI-Net: EXplicitly/Implicitly Conditioned Network for Multiple Environment Sim-to-Real Transfer

Takayuki Murooka, Masashi Hamaya, Felix von Drigalski, Kazutoshi Tanaka, Yoshihisa Ijiri
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:1221-1230, 2021.

Abstract

Sim-to-real transfer is attractive for robot learning, as it avoids the high cost of collecting data with real robots, but transferring agents from simulation to the real world is challenging. Previous studies have presented promising methods to solve this problem, but they may fail when a wider range of dynamics has to be considered. In this study, we propose a network architecture with explicit and implicit dynamics parameters for sim-to-real transfer from multiple environments. Using this method, we can simultaneously estimate the dynamics of the real world and optimize the action in various kinds of environments. The core novelty lies in the simultaneous dynamics estimation and action optimization, as well as the use of explicit (physically quantifiable) and implicit (latent) dynamics parameters to condition the network input. We apply our method to the object pushing task and verify its effectiveness by comparing it with previous methods and real-world experiments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-murooka21a, title = {EXI-Net: EXplicitly/Implicitly Conditioned Network for Multiple Environment Sim-to-Real Transfer}, author = {Murooka, Takayuki and Hamaya, Masashi and Drigalski, Felix von and Tanaka, Kazutoshi and Ijiri, Yoshihisa}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {1221--1230}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/murooka21a/murooka21a.pdf}, url = {https://proceedings.mlr.press/v155/murooka21a.html}, abstract = {Sim-to-real transfer is attractive for robot learning, as it avoids the high cost of collecting data with real robots, but transferring agents from simulation to the real world is challenging. Previous studies have presented promising methods to solve this problem, but they may fail when a wider range of dynamics has to be considered. In this study, we propose a network architecture with explicit and implicit dynamics parameters for sim-to-real transfer from multiple environments. Using this method, we can simultaneously estimate the dynamics of the real world and optimize the action in various kinds of environments. The core novelty lies in the simultaneous dynamics estimation and action optimization, as well as the use of explicit (physically quantifiable) and implicit (latent) dynamics parameters to condition the network input. We apply our method to the object pushing task and verify its effectiveness by comparing it with previous methods and real-world experiments.} }
Endnote
%0 Conference Paper %T EXI-Net: EXplicitly/Implicitly Conditioned Network for Multiple Environment Sim-to-Real Transfer %A Takayuki Murooka %A Masashi Hamaya %A Felix von Drigalski %A Kazutoshi Tanaka %A Yoshihisa Ijiri %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-murooka21a %I PMLR %P 1221--1230 %U https://proceedings.mlr.press/v155/murooka21a.html %V 155 %X Sim-to-real transfer is attractive for robot learning, as it avoids the high cost of collecting data with real robots, but transferring agents from simulation to the real world is challenging. Previous studies have presented promising methods to solve this problem, but they may fail when a wider range of dynamics has to be considered. In this study, we propose a network architecture with explicit and implicit dynamics parameters for sim-to-real transfer from multiple environments. Using this method, we can simultaneously estimate the dynamics of the real world and optimize the action in various kinds of environments. The core novelty lies in the simultaneous dynamics estimation and action optimization, as well as the use of explicit (physically quantifiable) and implicit (latent) dynamics parameters to condition the network input. We apply our method to the object pushing task and verify its effectiveness by comparing it with previous methods and real-world experiments.
APA
Murooka, T., Hamaya, M., Drigalski, F.v., Tanaka, K. & Ijiri, Y.. (2021). EXI-Net: EXplicitly/Implicitly Conditioned Network for Multiple Environment Sim-to-Real Transfer. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:1221-1230 Available from https://proceedings.mlr.press/v155/murooka21a.html.

Related Material