Back to Search Start Over

Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance

Authors :
Zhang, Kaifeng
Yin, Zhao-Heng
Ye, Weirui
Gao, Yang
Publication Year :
2024

Abstract

Defining reward functions for skill learning has been a long-standing challenge in robotics. Recently, vision-language models (VLMs) have shown promise in defining reward signals for teaching robots manipulation skills. However, existing works often provide reward guidance that is too coarse, leading to inefficient learning processes. In this paper, we address this issue by implementing more fine-grained reward guidance. We decompose tasks into simpler sub-tasks, using this decomposition to offer more informative reward guidance with VLMs. We also propose a VLM-based self imitation learning process to speed up learning. Empirical evidence demonstrates that our algorithm consistently outperforms baselines such as CLIP, LIV, and RoboCLIP. Specifically, our algorithm achieves a $5.4 \times$ higher average success rate compared to the best baseline, RoboCLIP, across a series of manipulation tasks.

Subjects

Subjects :
Computer Science - Robotics

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2405.13573
Document Type :
Working Paper