홈 › Papers

Direction Matters: Learning Force Direction Enables Sim-to-Real Contact-Rich Manipulation

2026-02-15 · Yifei Yang, Anzhe Chen, Zhenjie Zhu, Kechun Xu, Yunxuan Mao, Yufei Wei, Lu Chen, Rong Xiong, Yue Wang arxiv

Sim-to-real transfer for contact-rich manipulation remains challenging due to the inherent discrepancy in contact dynamics. While existing methods often rely on costly real-world data or utilize blind compliance through fixed controllers, we propose a framework that leverages expert-designed controller logic for transfer. Inspired by the success of privileged supervision in kinematic tasks, we employ a human-designed finite state machine based position/force controller in simulation to provide privileged guidance. The resulting policy is trained to predict the end-effector pose, contact state, and crucially the desired contact force direction. Unlike force magnitudes, which are highly sensitive to simulation inaccuracies, force directions encode high-level task geometry and remain robust across the sim-to-real gap. At deployment, these predictions configure a force-aware admittance controller. By combining the policy's directional intent with a constant, low-cost manually tuned force magnitude, the system generates adaptive, task-aligned compliance. This tuning is lightweight, typically requiring only a single scalar per contact state. We provide theoretical analysis for stability and robustness to disturbances. Experiments on four real-world tasks, i.e., microwave opening, peg-in-hole, whiteboard wiping, and door opening, demonstrate that our approach significantly outperforms strong baselines in both success rate and robustness. Videos are available at: https://yifei-y.github.io/project-pages/DirectionMatters/.

📄 PDF Abstract BibTeX arXiv:2602.14174

Code (0)

등록된 구현이 없습니다.

Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration

2026-05-12 · Youwei Yu, Jionghao Wang, Zhengming Yu, Wenping Wang 외 arxiv

Designing learnable information-theoretic objectives for robot exploration remains challenging. Such objectives aim to guide exploration toward data that reduces uncertainty in model parameters, yet it is often unclear w…

Reinforcement Learning

UniReflex: Plug-and-Play Force Control for Pretrained Generative Policies via Fast-Slow Reflex

2026-08-18 · Yan Huang, Shoujie Li, Ziwu Song, Wenbo Ding arxiv

Generative imitation learning policies excel at trajectory planning but lack closed-loop force regulation, while directly incorporating force modalities often requires redesigning or retraining the network. We present Un…

Trajectory Planning

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

2026-09-12 · Fei Yuan, Changjiang Gao, Yilei Tu, Yifeng Liu 외 hf

Fine-tuning instruct models often improves target performance while inducing behavioral drift from the reference model, which can degrade existing capabilities. Rather than treating this drift as an uncontrolled conseque…

Reinforcement Learning

GelSphere: An Omnidirectional Rolling Vision-Based Tactile Sensor for Online 3D Reconstruction and Normal Force Estimation

2026-03-14 · Seoyeon Lee, Mohammad Amin Mirzaee, Wenzhen Yuan arxiv

We present GelSphere, a spherical vision-based tactile sensor designed for real-time continuous surface scanning. Unlike traditional vision-based tactile sensors that can only sense locally and are damaged when slid acro…

3D Reconstruction

Embarrassingly Simple Self-Distillation Improves Code Generation

2026-04-01 · Ruixiang Zhang, Richard He Bai, Huangjie Zheng, Navdeep Jaitly 외 arxiv

Can a large language model (LLM) improve at code generation using only its own raw outputs, without a verifier, a teacher model, or reinforcement learning? We answer in the affirmative with simple self-distillation (SSD)…

Reinforcement Learning Code Generation