Saved in:
Bibliographic Details
Main Authors: Ma, Yecheng Jason, Liang, William, Wang, Hung-Ju, Wang, Sam, Zhu, Yuke, Fan, Linxi, Bastani, Osbert, Jayaraman, Dinesh
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01967
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909215954567168
author Ma, Yecheng Jason
Liang, William
Wang, Hung-Ju
Wang, Sam
Zhu, Yuke
Fan, Linxi
Bastani, Osbert
Jayaraman, Dinesh
author_facet Ma, Yecheng Jason
Liang, William
Wang, Hung-Ju
Wang, Sam
Zhu, Yuke
Fan, Linxi
Bastani, Osbert
Jayaraman, Dinesh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_01967
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DrEureka: Language Model Guided Sim-To-Real Transfer
Ma, Yecheng Jason
Liang, William
Wang, Hung-Ju
Wang, Sam
Zhu, Yuke
Fan, Linxi
Bastani, Osbert
Jayaraman, Dinesh
Robotics
Artificial Intelligence
Machine Learning
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.
title DrEureka: Language Model Guided Sim-To-Real Transfer
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.01967