Imperial College London
Portrait Picture

DrEdwardJohns

Faculty of Engineering, Department of Computing

Senior Lecturer
 
 
 
//

Contact

 

e.johns Website

 
 
//

Location

 

365ACE ExtensionSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Tsai:2021:10.1109/LRA.2021.3062311,
author = {Tsai, Y-Y and Xu, H and Ding, Z and Zhang, C and Johns, E and Huang, B},
doi = {10.1109/LRA.2021.3062311},
journal = {IEEE Robotics and Automation Letters},
pages = {3168--3175},
title = {DROID: minimizing the reality gap using single-shot human demonstration},
url = {http://dx.doi.org/10.1109/LRA.2021.3062311},
volume = {6},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment to real world, is the discrepancy between the dynamics of the two environments. In prior works, Domain Randomization (DR) has been used to address the reality gap for both robotic locomotion and manipulation tasks. In this letter, we propose Domain Randomization Optimization IDentification (DROID), a novel framework to exploit single-shot human demonstration for identifying the simulator's distribution of dynamics parameters, and apply it to training a policy on a door opening task. Our results show that the proposed framework can identify the difference in dynamics between the simulated and the real worlds, and thus improve policy transfer by optimizing the simulator's randomization ranges. We further illustrate that based on these same identified parameters, our method can generalize the learned policy to different but related tasks.
AU  - Tsai,Y-Y
AU  - Xu,H
AU  - Ding,Z
AU  - Zhang,C
AU  - Johns,E
AU  - Huang,B
DO  - 10.1109/LRA.2021.3062311
EP  - 3175
PY  - 2021///
SN  - 2377-3766
SP  - 3168
TI  - DROID: minimizing the reality gap using single-shot human demonstration
T2  - IEEE Robotics and Automation Letters
UR  - http://dx.doi.org/10.1109/LRA.2021.3062311
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000633394300002&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://ieeexplore.ieee.org/document/9363530
VL  - 6
ER  -
Download