paper-with-me

Papers

Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections

2025-06-20 · Xiaomeng Xu, Yifan Hou, Zeyi Liu, Shuran Song

We address key challenges in Dataset Aggregation (DAgger) for real-world contact-rich manipulation: how to collect informative human correction data and how to effectively update policies with this new data. We introduce Compliant Residual DAgger (CR-DAgger), which contains two novel components: 1) a Compliant Intervention Interface that leverages compliance control, allowing humans to provide gentle, accurate delta action corrections without interrupting the ongoing robot policy execution; and 2) a Compliant Residual Policy formulation that learns from human corrections while incorporating force feedback and force control. Our system significantly enhances performance on precise contact-rich manipulation tasks using minimal correction data, improving base policy success rates by over 50\% on two challenging tasks (book flipping and belt assembly) while outperforming both retraining-from-scratch and finetuning approaches. Through extensive real-world experiments, we provide practical guidance for implementing effective DAgger in real-world robot learning tasks. Result videos are available at: https://compliant-residual-dagger.github.io/

📄 PDF Abstract BibTeX arXiv:2506.16685

Code (0)

등록된 구현이 없습니다.

Tasks

Contact-rich Manipulation

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control

2026-03-04 · Yiou Huang, Ning Ma, Weichu Zhao, Zinuo Liu 외 arxiv

Imitation learning (IL) has shown strong potential for contact-rich precision insertion tasks. However, its practical deployment is often hindered by covariate shift and the need for continuous expert monitoring to recov…

CompliantVLA-adaptor: VLM-Guided Variable Impedance Action for Safe Contact-Rich Manipulation

2026-01-21 · Heng Zhang, Wei-Hsing Huang, Qiyi Tong, Gokhan Solak 외 arxiv

We propose a CompliantVLA-adaptor that augments the state-of-the-art Vision-Language-Action (VLA) models with vision-language model (VLM)-informed context-aware variable impedance control (VIC) to improve the safety and …

FingerEye: Learning Dexterous Manipulation with Continuous Vision-Tactile Sensing

2026-04-22 · Zhixuan Xu, Yichen Li, Xuanye Wu, Tianyu Qiu 외 arxiv

Dexterous robotic manipulation requires perception that remains informative from pre-contact approach to contact initiation and post-contact control. We introduce FingerEye, a sensing and learning framework that strength…

Object Localization

Hard-Stop Synthesis for Multi-DOF Compliant Mechanisms

2025-07-17 · Dean Chen, Armin Pomeroy, Brandon T. Peterson, Will Flanagan 외 arxiv

Compliant mechanisms have significant potential in precision applications due to their ability to guide motion without contact. However, an inherent vulnerability to fatigue and mechanical failure has hindered the transl…

LAC: Linear and Angular Compliance for Humanoid Whole-body Control

2026-08-26 · Yang Liu, Zhongkai Gu, Wei Zhu, Mitsuhiro Hayashibe arxiv

Real-world humanoid tasks involve physical interaction with objects and humans, yet current controllers either reject external forces as disturbances or restrict compliance to limited body links while ignoring angular ef…

Reinforcement Learning