Active Exploration for Real-Time Haptic Training

TL;DR

This paper introduces an active learning method for real-time tactile perception training in robots, using entropy-based exploration and ergodic control to efficiently learn perceptual models from tactile scenes.

Contribution

It presents a novel active exploration framework that improves tactile perceptual model training efficiency and identifies salient tactile scene features in real-time.

Findings

Models trained with active exploration outperform random data collection.

Entropy maps highlight high-salience regions in tactile scenes.

Real-time training enables rapid tactile perception learning.

Abstract

Tactile perception is important for robotic systems that interact with the world through touch. Touch is an active sense in which tactile measurements depend on the contact properties of an interaction--e.g., velocity, force, acceleration--as well as properties of the sensor and object under test. These dependencies make training tactile perceptual models challenging. Additionally, the effects of limited sensor life and the near-field nature of tactile sensors preclude the practical collection of exhaustive data sets even for fairly simple objects. Active learning provides a mechanism for focusing on only the most informative aspects of an object during data collection. Here we employ an active learning approach that uses a data-driven model's entropy as an uncertainty measure and explore relative to that entropy conditioned on the sensor state variables. Using a coverage-based ergodic controller, we train perceptual models in near-real time. We demonstrate our approach using a biomimentic sensor, exploring "tactile scenes" composed of shapes, textures, and objects. Each learned representation provides a perceptual sensor model for a particular tactile scene. Models trained on actively collected data outperform their randomly collected counterparts in real-time training tests. Additionally, we find that the resulting network entropy maps can be used to identify high salience portions of a tactile scene.