A tactile system recovers 6-DoF object pose from one contact pair by coarse-to-fine localization of point clouds on a known model followed by normal-aware SVD.
Transferable tactile transformers for representa- tion learning across diverse sensors and tasks
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
FTP-1 is the first foundation tactile policy pretrained on ~3000 hours of data from 26 sources across 21 sensors that improves performance on seen setups by 17.2% and transfers to unseen sensors with 31% success rate gain.
Touch-R1 applies GRPO reinforcement learning on a new 1M tactile dataset and benchmark to train a Qwen2.5-VL-7B model that outperforms baselines on tactile perception and visual-tactile conflict tasks.
HT-Bench is a large egocentric vision-plus-full-hand-tactile benchmark with four evaluation tasks; the proposed HandTouch encoder improves Recall@5 from 74.65% to 85.23%, reduces inpainting RMSE from 0.022 to 0.010, and raises OOD cIoU from 0.628 to 0.705.
Large multi-source tactile data plus question-guided Gaussian temporal MoE yields ~7-point gains over VTV-LLM on tactile property and commonsense reasoning tasks, with improved unseen-sensor generalization.
MiTaS fuses multi-resolution tactile data from GelSight and Evetac sensors with vision using modality-specific stems and transformer fusion to condition flow-matching policies, reporting 80% average success on five contact-rich tasks versus 31-54% baselines.
The model uses dense visuo-tactile feature interactions and material-diversity pairing on expanded datasets to generate tactile saliency maps for material segmentation, outperforming prior global-alignment methods.
A vision-language-action policy that predicts future tactile images and uses that predicted touch to refine its actions reaches up to 95% success on contact-rich manipulation.
Presents arm-worn AetheRock hardware for multi-modal data collection and ForceVT learning method to improve tactile inference robustness despite sensor variations.
citing papers explorer
-
You Only Touch Once: 6-DoF Object Pose Estimation from Single Tactile Contact
A tactile system recovers 6-DoF object pose from one contact pair by coarse-to-fine localization of point clouds on a known model followed by normal-aware SVD.
-
FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation
FTP-1 is the first foundation tactile policy pretrained on ~3000 hours of data from 26 sources across 21 sensors that improves performance on seen setups by 17.2% and transfers to unseen sensors with 31% success rate gain.
-
Touch-R1: Reinforcing Touch Reasoning in MLLMs
Touch-R1 applies GRPO reinforcement learning on a new 1M tactile dataset and benchmark to train a Qwen2.5-VL-7B model that outperforms baselines on tactile perception and visual-tactile conflict tasks.
-
HT-Bench: Benchmarking and Learning Dexterous Full-Hand Tactile Representations with Egocentric Vision
HT-Bench is a large egocentric vision-plus-full-hand-tactile benchmark with four evaluation tasks; the proposed HandTouch encoder improves Recall@5 from 74.65% to 85.23%, reduces inpainting RMSE from 0.022 to 0.010, and raises OOD cIoU from 0.628 to 0.705.
-
TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware Representation
Large multi-source tactile data plus question-guided Gaussian temporal MoE yields ~7-point gains over VTV-LLM on tactile property and commonsense reasoning tasks, with improved unseen-sensor generalization.
-
Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation
MiTaS fuses multi-resolution tactile data from GelSight and Evetac sensors with vision using modality-specific stems and transformer fusion to condition flow-matching policies, reporting 80% average success on five contact-rich tasks versus 31-54% baselines.
-
Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions
The model uses dense visuo-tactile feature interactions and material-diversity pairing on expanded datasets to generate tactile saliency maps for material segmentation, outperforming prior global-alignment methods.
-
Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulation
A vision-language-action policy that predicts future tactile images and uses that predicted touch to refine its actions reaches up to 95% success on contact-rich manipulation.
-
AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning
Presents arm-worn AetheRock hardware for multi-modal data collection and ForceVT learning method to improve tactile inference robustness despite sensor variations.