Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
cs.RO, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: 21 pages, 6 figures. Accepted to the 10th Conference on Robot Learning (CoRL 2026)
Project page: https://vista-paper.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation
- Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Spherical CNNs on Unstructured Grids
- On-Robot Learning With Equivariant Models
- Steerable CNNs
- EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning
- ET-SEED: Efficient Trajectory-Level SE(3) Equivariant Diffusion Policy
- Canonical Policy: Learning Canonical 3D Representation for SE(3)-Equivariant Policy
- Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
- Equivariant Diffusion Policy
- Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
- ManiFeel: Benchmarking and Understanding Visuotactile Manipulation Policy Learning
- 3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing
- Touch and Go: Learning from Human-Collected Vision and Touch
- Residual Rotation Correction using Tactile Equivariance
- EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Policy for Spatially Generalizable Contact-rich Tasks
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
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