Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |