Unified Visual-Tactile-Action Modeling from Human Demonstrations for Dexterous Manipulation

arXiv:2609.34182 · cs.RO, cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-09-28

Updated: 2026-09-29

Project page: https://uni-vta.github.io

Terminology

• Ablation — 10× in this paper · explained in 1 episode
• World Model — 7× in this paper · explained in 7 episodes
• Action Space — 6× in this paper · explained in 1 episode
• Representation Learning — 5× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Decode — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Reactive Diffusion Policy — 2× in this paper
• Benchmark — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Latent Dynamics — 1× in this paper · explained in 2 episodes
• Multimodal Learning — 1× in this paper · explained in 2 episodes
• Unified Visual Tactile Action — 1× in this paper
• Visual-Tactile-to-Piezoresistive Taxel Mapping — 1× in this paper

Sources

• Tactile Dexterity: Manipulation Primitives with Tactile Feedback
• See to Touch: Learning Tactile Dexterity through Visual Incentives
• DexTac: Learning Contact-aware Visuotactile Policies via Hand-by-hand Teaching
• T-Rex: Tactile-Reactive Dexterous Manipulation
• Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
• Ego4D: Around the World in 3,000 Hours of Egocentric Video
• HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
• Masked Visual Pre-training for Motor Control
• R3M: A Universal Visual Representation for Robot Manipulation
• MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
• DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
• DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
• EgoMimic: Scaling Imitation Learning via Egocentric Video
• DexImit: Learning Bimanual Dexterous Manipulation from Monocular Human Videos
• EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
• EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
• Learning Universal Policies via Text-Guided Video Generation
• Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
• RoboDreamer: Learning Compositional World Models for Robot Imagination
• Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving