Towards Effective Utilization of Mixed-Quality Demonstrations in Robotic Manipulation via Segment-Level Selection and Optimization

TL;DR

This paper introduces S2I, a framework that effectively utilizes mixed-quality demonstration data for robotic manipulation by segmenting, selecting, and optimizing segments to improve policy training.

Contribution

The paper presents a novel segment-level selection and optimization framework, S2I, for leveraging mixed-quality demonstrations in robotic manipulation tasks.

Findings

S2I improves policy performance with only 3 expert demonstrations as reference.

Segment selection via contrastive learning effectively identifies high-quality data.

Trajectory optimization refines suboptimal segments, enhancing learning outcomes.

Abstract

Data is crucial for robotic manipulation, as it underpins the development of robotic systems for complex tasks. While high-quality, diverse datasets enhance the performance and adaptability of robotic manipulation policies, collecting extensive expert-level data is resource-intensive. Consequently, many current datasets suffer from quality inconsistencies due to operator variability, highlighting the need for methods to utilize mixed-quality data effectively. To mitigate these issues, we propose "Select Segments to Imitate" (S2I), a framework that selects and optimizes mixed-quality demonstration data at the segment level, while ensuring plug-and-play compatibility with existing robotic manipulation policies. The framework has three components: demonstration segmentation dividing origin data into meaningful segments, segment selection using contrastive learning to find high-quality segments, and trajectory optimization to refine suboptimal segments for better policy learning. We evaluate S2I through comprehensive experiments in simulation and real-world environments across six tasks, demonstrating that with only 3 expert demonstrations for reference, S2I can improve the performance of various downstream policies when trained with mixed-quality demonstrations. Project website: https://tonyfang.net/s2i/.