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

arXiv: https://arxiv.org/abs/2409.19917 · HTML: https://mlsanity.com/paper/2409.19917/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2024.

## Built on by (most cited first, 8 of 8)

- [AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletons](https://mlsanity.com/paper/2503.03081/) (2025)
- [SIME: Enhancing Policy Self-Improvement with Modal-level Exploration](https://mlsanity.com/paper/2505.01396/) (2025)
- [AoE: Always-on Egocentric Human Video Collection for Embodied AI](https://mlsanity.com/paper/2602.23893/) (2026)
- [An Efficient Metric for Data Quality Measurement in Imitation Learning](https://mlsanity.com/paper/2605.01544/) (2026)
- [Task Robustness via Re-Labelling Vision-Action Robot Data](https://mlsanity.com/paper/2606.10918/) (2026)
- [See and Switch: Vision-Based Branching for Interactive Robot-Skill Programming](https://mlsanity.com/paper/2603.08057/) (2026)
- [Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulation](https://mlsanity.com/paper/2609.26672/) (2026)
- [Learning from Mixed-Quality Deployment Experience for Robot Manipulation](https://mlsanity.com/paper/2609.29000/) (2026)

## Abstract (arXiv)

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/.