merlresearch/unic: UNIC: Learning Unified Multimodal Extrinsic Contact Estimation ·
github.com · 531 words · saved by 1 readers
UNIC: Learning Unified Multimodal Extrinsic Contact Estimation
Abstract Contact-rich manipulation requires reliable estimation of extrinsic contacts—the interactions between a grasped object and its environment—which provide essential contextual information for planning, control, and policy learning. However, existing approaches often rely on restrictive assumptions, such as predefined contact types, fixed grasp configurations, or camera calibration, that hinder generalization to novel objects and deployment in unstructured environments. UNIC is a unified multimodal framework for extrinsic contact estimation that operates without any prior knowledge…
saved by
related reading
- LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestionpku-epic.github.io
- Introducing Robostral Navigatemistral.ai
- [2602.06001] Visuo-Tactile World Modelsarxiv.org
- 2412.02676arxiv.org
- Homepalanc.github.io
- FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningjasonjzliu.com
- Robot Synesthesia: In-Hand Manipulation with Visuotactile Sensingarxiv.org
- Differentiable Robot Renderingdrrobot.cs.columbia.edu
- Animesh Gargscholar.google.com
- [2606.19161] HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Visionarxiv.org
- UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robotsarxiv.org
- OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transferarxiv.org