# Optimal Deep Learning for Robot Touch

arXiv: https://arxiv.org/abs/2003.01916 · HTML: https://mlsanity.com/paper/2003.01916/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Tactile Sim-to-Real Policy Transfer via Real-to-Sim Image Translation](https://mlsanity.com/paper/2106.08796/) (2021)
- [Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear](https://mlsanity.com/paper/2109.03615/) (2021)
- [Attention for Robot Touch: Tactile Saliency Prediction for Robust Sim-to-Real Tactile Control](https://mlsanity.com/paper/2307.14510/) (2023)
- [Semi-Supervised Disentanglement of Tactile Contact~Geometry from Sliding-Induced Shear](https://mlsanity.com/paper/2208.12500/) (2022)

## Abstract (arXiv)

This article illustrates the application of deep learning to robot touch by considering a basic yet fundamental capability: estimating the relative pose of part of an object in contact with a tactile sensor. We begin by surveying deep learning applied to tactile robotics, focussing on optical tactile sensors, which help bridge from deep learning for vision to touch. We then show how deep learning can be used to train accurate pose models of 3D surfaces and edges that are insensitive to nuisance variables such as motion-dependent shear. This involves including representative motions as unlabelled perturbations of the training data and using Bayesian optimization of the network and training hyperparameters to find the most accurate models. Accurate estimation of pose from touch will enable robots to safely and precisely control their physical interactions, underlying a wide range of object exploration and manipulation tasks.