Open Source
TaF-Foundation: Wrench-Grounded Cross-Sensor Tactile Representations
arXiv cs.RO0 views
arXiv:2611.20718v1 Announce Type: new Abstract: Tactile sensing is essential for contact-rich manipulation, yet heterogeneous sensing mechanisms and observation formats hinder cross-hardware transfer. Since physical contact is governed by Newtonian mechanics, we ground tactile representations in six-dimensional wrenches, establishing a common physical reference across sensing mechanisms. Specifically, we pair tactile observations from all sensors with wrench measurements, enabling shared physical supervision without requiring direct tactile-to-tactile pairing between sensors. To support learning at scale, we develop a dedicated acquisition platform and collect over 100 million paired tactile observations and wrench measurements from 24 sensors spanning four families of sensing principles. Building on this dataset, our framework combines sensor-specific input adaptation with a shared tactile encoder. By learning to reconstruct wrenches, the encoder maps observations from different sensors into a shared, continuous feature space grounded in contact physics. To leverage these representations for manipulation, we introduce TaF-Policy, which integrates tactile features with visual observations and robot states to generate action chunks. We evaluate the learned representations through wrench estimation, cross-sensor retrieval, few-shot adaptation to unseen sensors, and robotic manipulation. On the core benchmark, our method reduces single-frame force RMSE by 17.1% and improves cross-sensor retrieval R@1 by 13.11 percentage points over the strongest baseline. In manipulation experiments, TaF-Policy achieves average success rates of 51.33% across three simulated tasks and 46.25% across four real-world tasks, compared with 47.33% and 23.75%, respectively, for the strongest baselines evaluated on the same task sets. Project page: https://mrjiangjm.github.io/TaF-Foundation/.
Source:https://arxiv.org/abs/2611.20718PreviousSG-ODOM: Event-Driven Proprioceptive State Estimation with Stability-Gated Contact Updates for Legged RobotsNextACiT: Proprioceptive-Prior Action Chunking with Inverted Transformers
Related posts
Open-source Minecraft launcher. Speed and local
0dev.to GitHub
How to choose where to launch your side project
0dev.to Discuss
Pathology Randomization for Synthetic Priors and Zero-Shot Detection
0arXiv eess.IV

Devin.ai.. Stop Leaving Free Money on the Table: Why Every Developer Must Hammer Devin.ai in This Global 10-Day Window
0dev.to OpenSource
SG-ODOM: Event-Driven Proprioceptive State Estimation with Stability-Gated Contact Updates for Legged Robots
0arXiv cs.RO
WTR-Drive: World-Task Decomposition with Structured Risk Supervision for End-to-End Driving
0arXiv cs.RO