# Exploring Pose-Guided Imitation Learning for Robotic Precise Insertion

Source: [Exploring Pose-Guided Imitation Learning for Robotic Precise Insertion](<https://www.sota2.com/research/paper/68fa788f1e209131cea79123>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T05:00:04.121Z

Authors: Han Sun, Sheng Liu, Yizhao Wang, Zhenning Zhou, Shuai Wang, Haibo Yang, Jingyuan Sun, Qixin Cao

Published: 2025-05-14T14:25:32.000Z

## Abstract

Imitation learning is promising for robotic manipulation, but \\emph{precise insertion} in the real world remains difficult due to contact-rich dynamics, tight clearances, and limited demonstrations. Many existing visuomotor policies depend on high-dimensional RGB/point-cloud observations, which can be data-inefficient and generalize poorly under pose variations. In this paper, we study pose-guided imitation learning by using object poses in $\\mathrm{SE}(3)$ as compact, object-centric observations for precise insertion tasks. First, we propose a diffusion policy for precise insertion that observes the \\emph{relative} $\\mathrm{SE}(3)$ pose of the source object with respect to the target object and predicts a future relative pose trajectory as its action. Second, to improve robustness to pose estimation noise, we augment the pose-guided policy with RGBD cues. Specifically, we introduce a goal-conditioned RGBD encoder to capture the discrepancy between current and goal observations. We further propose a pose-guided residual gated fusion module, where pose features provide the primary control signal and RGBD features adaptively compensate when pose estimates are unreliable. We evaluate our methods on six real-robot precise insertion tasks and achieve high performance with only $7$--$10$ demonstrations per task. In our setup, the proposed policies succeed on tasks with clearances down to $0.01$~mm and demonstrate improved data efficiency and generalization over existing baselines. Code will be available at https://github.com/sunhan1997/PoseInsert.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Robotic Insertion on Cobot Mobile ALOHA In-distribution (train)](<https://www.sota2.com/research/sota/robotic-insertion-on-cobot-mobile-aloha-in-distribution-train.md>): Robotic Insertion; Cobot Mobile ALOHA In-distribution (train); Task 1 Success Rate: 100.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.09424>)

[PDF](<https://arxiv.org/pdf/2505.09424.pdf>)
