VisTacAlign: Co-Training Dexterous Policies on Tactile Human and Robot Demonstrations using Visual-Tactile Alignment
cs.RO
Submitted: 2026-09-25
Updated: 2026-10-13
Project page: https://vis-tac-align.github.io
Terminology
Sources
- Generalizable Humanoid Manipulation with 3D Diffusion Policies
- Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
- Learning Visuotactile Skills with Two Multifingered Hands
- OSMO: Open-Source Tactile Glove for Human-to-Robot Skill Transfer
- TactAlign: Human-to-Robot Policy Transfer via Tactile Alignment
- ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
- DexCtrl: Towards Sim-to-Real Dexterity with Adaptive Controller Learning
- Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning
- OpenVLA: An Open-Source Vision-Language-Action Model
- Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play
- EgoMimic: Scaling Imitation Learning via Egocentric Video
- Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation
- UniTacHand: Unified Spatio-Tactile Representation for Human to Robotic Hand Skill Transfer
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies