A Large Area Robotic Skin with Sparsely Embedded Microphones for Human-Robot Tactile Communication

Abstract

A human can socially interact in a non-verbal manner by understanding the intention behind a tactile stimulus. Patting on one's back is one of tactile communications, which is considered as a sign of encouragement in most cultures. The majority of such tactile communication is carried out by a dynamic tactile on large passive body parts and differently interpreted by how and where on the body is touched. Thus any robotic system that physically interacts with a human requires a dynamic tactile sensor for further social interaction. This paper presents a large dynamic tactile sensor that could cover a robot's passive body parts using a few sparsely distributed microphones to cover a large area in an efficient manner. A porous structured mesh, neoprene, and loop fabric are used to form a sensor's skin that could well generate and transfer a signal to distributed microphones when a touch is introduced. TDOA source localisation algorithms are implemented to find the touch point locating in between the distributed microphones, and a simple convolutional neural network is trained to classify a type of the touch. A localising performance is qualitatively achieved in a testbed of the sensor and applied to a mannequin's back to show the applicability, which classified a touch into six classes with an accuracy of 88 %.