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

TL;DR

This paper introduces an uncertainty-aware deep learning framework for tactile robotics, enhancing edge pose estimation and control robustness in tactile servo tasks by integrating uncertainty estimation with Kalman filtering.

Contribution

It applies uncertainty-aware deep learning to tactile sensing, demonstrating improved pose estimation and control robustness over deterministic methods in robotic tactile applications.

Findings

Uncertainty-aware DL reduces pose estimation error by a factor of two.

The approach smooths robot trajectories and reduces noisy behaviors.

Uncertainty estimation enhances tactile servo control robustness.

Abstract

This work investigates uncertainty-aware deep learning (DL) in tactile robotics based on a general framework introduced recently for robot vision. For a test scenario, we consider optical tactile sensing in combination with DL to estimate the edge pose as a feedback signal to servo around various 2D test objects. We demonstrate that uncertainty-aware DL can improve the pose estimation over deterministic DL methods. The system estimates the uncertainty associated with each prediction, which is used along with temporal coherency to improve the predictions via a Kalman filter, and hence improve the tactile servo control. The robot is able to robustly follow all of the presented contour shapes to reduce not only the error by a factor of two but also smooth the trajectory from the undesired noisy behaviour caused by previous deterministic networks. In our view, as the field of tactile robotics matures in its use of DL, the estimation of uncertainty will become a key component in the control of physically interactive tasks in complex environments.