Optimal Deep Learning for Robot Touch

03/04/2020
by   Nathan F. Lepora, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 5

research
12/04/2020

Pose-Based Servo Control with Soft Tactile Sensing

This paper describes a new way of controlling robots using soft tactile ...
research
04/29/2021

Uncertainty-aware deep learning for robot touch: Application to Bayesian tactile servo control

This work investigates uncertainty-aware deep learning (DL) in tactile r...
research
03/05/2023

Tac-VGNN: A Voronoi Graph Neural Network for Pose-Based Tactile Servoing

Tactile pose estimation and tactile servoing are fundamental capabilitie...
research
12/03/2020

Goal-Driven Robotic Pushing Using Tactile and Proprioceptive Feedback

In robots, nonprehensile manipulation operations such as pushing are a u...
research
06/22/2022

Vision- and tactile-based continuous multimodal intention and attention recognition for safer physical human-robot interaction

Employing skin-like tactile sensors on robots enhances both the safety a...
research
08/26/2022

Semi-Supervised Disentanglement of Tactile Contact Geometry from Sliding-Induced Shear

The sense of touch is fundamental to human dexterity. When mimicked in r...

Please sign up or login with your details

Forgot password? Click here to reset