PHASE: Compliance-Enabled Tactile Phase Retrieval for Few-Shot Insertion Learning

2026-09-25

AI Summary

This study addresses the challenge of effectively retrieving relevant historical experiences from few-shot demonstrations to facilitate policy learning in contact-rich assembly tasks. To this end, it introduces tactile phase awareness into retrieval-augmented imitation learning for the first time. Specifically, the proposed method leverages flexible wrist-mounted tactile signals to perform variable-length phase segmentation, thereby revealing the underlying insertion stage structure. This is integrated with multimodal contact representation learning and phase-consistent retrieval to achieve precise experience matching. Evaluated on real-world peg-in-hole tasks, the approach improves overall success rates by 13 percentage points and yields a 30-percentage-point gain under unseen initial configurations, significantly enhancing policy robustness.

Abstract

Contact-rich assembly tasks such as peg-in-hole insertion remain difficult to learn from limited demonstrations. While retrieval-augmented imitation learning, which augments target demonstrations with relevant prior data, offers a promising direction, its applicability to contact-rich manipulation remains largely unexplored. Contact-rich insertion unfolds over multiple phases from search to insert, and retrieving phase-specific experience from prior data in principled ways remains an open question. Our key insight is that a compliant wrist enables the robot to sustain contact throughout execution, producing rich tactile and force signals that naturally reveal the phase structure of insertion and inform what should be retrieved. Based on this insight, we present PHASE (PHase-Aware Segmentation and REtrieval), a framework for compliance-enabled tactile phase retrieval that integrates multimodal contact-aware representation learning, variable-length phase segmentation from tactile signals, and phase-consistent retrieval for policy learning. We evaluate PHASE on real-world peg-in-hole insertion across five peg geometries, comparing against retrieval strategies drawn from state-of-the-art methods under a shared policy architecture. PHASE improves the overall success rate by 13 percentage points over the strongest non-phase-aware baseline, and improves performance under unseen initial positions by 30 percentage points. These results demonstrate that aligning retrieval with interaction-defined contact phases substantially improves robustness in few-shot insertion learning.

Problem

• Few-shot learning
• Contact-rich manipulation
• Peg-in-hole insertion
• Phase retrieval
• Retrieval-augmented imitation learning

Innovation

• Tactile Phase Retrieval
• Few-Shot Imitation Learning
• Compliant Manipulation
• Contact-Rich Assembly
• Variable-Length Segmentation