Robotics: Science and Systems XX
DrEureka: Language Model Guided Sim-To-Real Transfer
Yecheng Jason Ma, William Liang, Hung-Ju Wang, Yuke Zhu, Linxi Fan, Osbert Bastani, Dinesh JayaramanAbstract:
Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale. However, sim-to-real approaches typically rely on manual design and tuning of the task reward function as well as the simulation physics parameters, rendering the process slow and human-labor intensive. In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design. Our LLM-guided sim-to-real approach, DrEureka, requires only the physics simulation for the target task and automatically constructs suitable reward functions and domain randomization distributions to support real-world transfer. We first demonstrate that our approach can discover sim-to-real configurations that are competitive with existing human-designed ones on quadruped locomotion and dexterous manipulation tasks. Then, we showcase that our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball, without iterative manual design.
Bibtex:
@INPROCEEDINGS{Ma-RSS-24, AUTHOR = {Yecheng Jason Ma AND William Liang AND Hung-Ju Wang AND Yuke Zhu AND Linxi Fan AND Osbert Bastani AND Dinesh Jayaraman}, TITLE = {{DrEureka: Language Model Guided Sim-To-Real Transfer}}, BOOKTITLE = {Proceedings of Robotics: Science and Systems}, YEAR = {2024}, ADDRESS = {Delft, Netherlands}, MONTH = {July}, DOI = {10.15607/RSS.2024.XX.094} }