Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition

Huy Ha, Pete Florence, Shuran Song

Keywords: skill learning, language, diffusion

TL;DR: We present a framework for language-model guided data generation over robot utilities, and multi-task language-conditioned diffusion policy distillation.

Abstract: We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy. For (1), we use a large language model (LLM) to guide high-level planning, and sampling-based robot planners (e.g. motion or grasp samplers) for generating diverse and rich manipulation trajectories. To robustify this data-collection process, the LLM also infers a code-snippet for the success condition of each task, simultaneously enabling the data-collection process to detect failure and retry as well as the automatic labeling of trajectories with success/failure. For (2), we extend the diffusion policy single-task behavior-cloning approach to multi-task settings with language conditioning. Finally, we propose a new multi-task benchmark with 18 tasks across five domains to test long-horizon behavior, common-sense reasoning, tool-use, and intuitive physics. We find that our distilled policy successfully learned the robust retrying behavior in its data collection procedure, while improving absolute success rates by 33.2% on average across five domains. Code, data, and additional qualitative results are available on https://www.cs.columbia.edu/~huy/scalingup/.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://www.cs.columbia.edu/~huy/scalingup/static/videos/scalingup.mp4

Website: https://www.cs.columbia.edu/~huy/scalingup/

Code: https://github.com/real-stanford/scalingup

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/scaling-up-and-distilling-down-language/code)