paper-with-me

홈 › Papers

FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning

2025-02-24 · Jason Jingzhou Liu, Yulong Li, Kenneth Shaw, Tony Tao, Ruslan Salakhutdinov, Deepak Pathak

Many contact-rich tasks humans perform, such as box pickup or rolling dough, rely on force feedback for reliable execution. However, this force information, which is readily available in most robot arms, is not commonly used in teleoperation and policy learning. Consequently, robot behavior is often limited to quasi-static kinematic tasks that do not require intricate force-feedback. In this paper, we first present a low-cost, intuitive, bilateral teleoperation setup that relays external forces of the follower arm back to the teacher arm, facilitating data collection for complex, contact-rich tasks. We then introduce FACTR, a policy learning method that employs a curriculum which corrupts the visual input with decreasing intensity throughout training. The curriculum prevents our transformer-based policy from over-fitting to the visual input and guides the policy to properly attend to the force modality. We demonstrate that by fully utilizing the force information, our method significantly improves generalization to unseen objects by 43\% compared to baseline approaches without a curriculum. Video results and instructions at https://jasonjzliu.com/factr/

📄 PDF Abstract BibTeX arXiv:2502.17432

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

2026-06-10 · Steven Oh, Jason Jingzhou Liu, Tony Tao, Philip Han 외 arxiv

Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates exte…

CRAFT: Adapting VLA Models to Contact-rich Manipulation via Force-aware Curriculum Fine-tuning

2026-02-13 · Yike Zhang, Yaonan Wang, Xinxin Sun, Kaizhen Huang 외 arxiv

Vision-Language-Action (VLA) models have shown a strong capability in enabling robots to execute general instructions, yet they struggle with contact-rich manipulation tasks, where success requires precise alignment, sta…

FactReview: Evidence-Grounded Peer Review with Execution-Based Claim Verification

2026-04-05 · Ling Yue, Chaoqian Ouyang, Hang Xu, Ruijun Huang 외 arxiv

LLM-based reviewing systems typically take only the manuscript as input, leaving literature and code-based claims hard to verify. We present FactReview, a system that extracts review-relevant claims, grounds them in rela…

ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation

2025-03-11 · DongHeun Han, Byungmin Kim, RoUn Lee, KyeongMin Kim 외

Realistic Hand manipulation is a key component of immersive virtual reality (VR), yet existing methods often rely on kinematic approach or motion-capture datasets that omit crucial physical attributes such as contact for…

Accelerating Robot Learning of Contact-Rich Manipulations: A Curriculum Learning Study

2022-04-27 · Cristian C. Beltran-Hernandez, Damien Petit, Ixchel G. Ramirez-Alpizar, Kensuke Harada

The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount o…

Contact-rich ManipulationReinforcement Learning (RL)