# Learning efficient haptic shape exploration with a rigid tactile sensor array

## TL;DR

This paper introduces a novel neural network-based approach for efficient haptic shape exploration using a rigid tactile sensor array, inspired by human exploratory behavior, achieving near-perfect object contour recognition in simulation.

## Contribution

It presents the Haptic Attention Model, a new architecture that learns to optimize perception and action in haptic exploration through online data acquisition and integrated neural modules.

## Key findings

- Achieved nearly 100% accuracy in object contour exploration.
- Successfully tested on four different objects in simulation.
- Optimized for the sensor's morphology and exploration strategy.

## Abstract

Haptic exploration is a key skill for both robots and humans to discriminate and handle unknown objects or to recognize familiar objects. Its active nature is evident in humans who from early on reliably acquire sophisticated sensory-motor capabilities for active exploratory touch and directed manual exploration that associates surfaces and object properties with their spatial locations. This is in stark contrast to robotics. In this field, the relative lack of good real-world interaction models - along with very restricted sensors and a scarcity of suitable training data to leverage machine learning methods - has so far rendered haptic exploration a largely underdeveloped skill. In the present work, we connect recent advances in recurrent models of visual attention with previous insights about the organisation of human haptic search behavior, exploratory procedures and haptic glances for a novel architecture that learns a generative model of haptic exploration in a simulated three-dimensional environment. The proposed algorithm simultaneously optimizes main perception-action loop components: feature extraction, integration of features over time, and the control strategy, while continuously acquiring data online. We perform a multi-module neural network training, including a feature extractor and a recurrent neural network module aiding pose control for storing and combining sequential sensory data. The resulting haptic meta-controller for the rigid $16 \times 16$ tactile sensor array moving in a physics-driven simulation environment, called the Haptic Attention Model, performs a sequence of haptic glances, and outputs corresponding force measurements. The resulting method has been successfully tested with four different objects. It achieved results close to $100 \%$ while performing object contour exploration that has been optimized for its own sensor morphology.