Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Han, Liu, Sheng, Wang, Yizhao, Zhou, Zhenning, Wang, Shuai, Yang, Haibo, Sun, Jingyuan, Cao, Qixin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.09424
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908907558928384
author Sun, Han
Liu, Sheng
Wang, Yizhao
Zhou, Zhenning
Wang, Shuai
Yang, Haibo
Sun, Jingyuan
Cao, Qixin
author_facet Sun, Han
Liu, Sheng
Wang, Yizhao
Zhou, Zhenning
Wang, Shuai
Yang, Haibo
Sun, Jingyuan
Cao, Qixin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Pose-Guided Imitation Learning for Robotic Precise Insertion
Sun, Han
Liu, Sheng
Wang, Yizhao
Zhou, Zhenning
Wang, Shuai
Yang, Haibo
Sun, Jingyuan
Cao, Qixin
Robotics
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.
title Exploring Pose-Guided Imitation Learning for Robotic Precise Insertion
topic Robotics
url https://arxiv.org/abs/2505.09424