ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks

2026-09-20

AI Summary

为解决高精度连接器插入难题，提出ContactDP方法，融合视觉、触觉及力矩信息指导接触反馈，实现稳定精准的插件操作。

Abstract

High-precision connector insertion remains challenging for robotic systems due to tight mechanical tolerances, partial observability during contact, and multimodal uncertainty arising from occlusion and contact ambiguity. Successful insertion requires closed-loop contact guidance that continuously integrates global alignment cues with local contact feedback to produce stable corrective actions under interaction. In this work, we present ContactDP (Contact-Guided Diffusion Policy for Tight Insertion Tasks), a multimodal diffusion-policy framework for contact-rich insertion. ContactDP jointly integrates wrist RGB observations, fingertip tactile sensing, and wrist-mounted force-torque measurements to infer contact state and generate temporally consistent corrective motions during insertion. To ensure stable execution under contact, the learned policy operates together with a hybrid position-force controller that provides compliant low-level interaction. We evaluate our approach on a suite of industrial-grade connector insertion tasks with varying connector geometries, grasp conditions, and initial misalignment. Across all tasks, ContactDP significantly outperforms vision-only diffusion policies for performance, reliability and generalization.

Problem

• high-precision connector insertion
• tight mechanical tolerances
• partial observability
• multimodal uncertainty

Innovation

• multimodal diffusion-policy
• contact-rich insertion
• temporally consistent corrective motions
• hybrid position-force controller