Changyi Lin
@changyi_lin1 • 1,014 subscribers
PhD @CarnegieMellon | Student Researcher @GoogleDeepMind. Dexterity & Tactile Sensing & Robot Learning.
Videos
Manipulation happens through surfaces. To understand contact-rich dexterous interaction, motion alone is not enough. We also need to know surface properties and contact state. Excited to share ART-Glove, an articulated tactile glove that captures contact-grounded information while preserving human dexterity. It provides: - Known Geometry: 16 rigid functional surfaces - Surface Motion: 22 anatomically aligned joints - Tactile Contact: 2048 piezoresistive taxels Huge thanks to my advisor Ding Ding Zhao, and to Yuxiang Yuxiang Yang, Maria Maria Bauza Villalonga, Marissa, and Peide Peide Huang for the valuable advice and discussions. Paper:
Changyi Lin88,013 görüntüleme • 3 ay önce
Introducing LocoTouch: Quadrupedal robots equipped with tactile sensing can now transport unsecured objects — no mounts, no straps. The tactile policy transfers zero-shot from sim to real. Core Task-Agnostic Features: 1. High-fidelity contact simulation for distributed tactile sensors 2. Adaptive gait reward for symmetric, frequency-adaptive locomotion Website: Paper:
Changyi Lin38,494 görüntüleme • 1 yıl önce
Open-sourcing three repos from our CoRL paper LocoTouch ( 1. Perceptive Learning in IsaacLab ( 2. Policy Deployment (MoCap or onboard sensors) ( 3. Mac Mini for Onboard Robotics ( Yuxiang Yang and I have used the compact Mac Mini and stable deployment pipeline across several legged robot projects (
Changyi Lin20,087 görüntüleme • 1 yıl önce
Daha fazla içerik yok.