Abstract
An important aspect in Human–Robot Interaction is responding to different kinds of touch stimuli. To date, several technologies have been explored to determine how a touch is perceived by a social robot, usually placing a large number of sensors throughout the robot’s shell. In this work, we introduce a novel approach, where the audio acquired from contact microphones located in the robot’s shell is processed using machine learning techniques to distinguish between different types of touches. The system is able to determine when the robot is touched (touch detection), and to ascertain the kind of touch performed among a set of possibilities: stroke, tap, slap, and tickle (touch classification). This proposal is cost-effective since just a few microphones are able to cover the whole robot’s shell since a single microphone is enough to cover each solid part of the robot. Besides, it is easy to install and configure as it just requires a contact surface to attach the microphone to the robot’s shell and plug it into the robot’s computer. Results show the high accuracy scores in touch gesture recognition. The testing phase revealed that Logistic Model Trees achieved the best performance, with an F-score of 0.81. The dataset was built with information from 25 participants performing a total of 1981 touch gestures.
Highlights
The role that the sense of touch plays in emotional communication in humans and animals have been widely studied, finding relations to attachment, bonding, stress and even memory [1,2].Touch, as a common communicative gesture, is an important aspect of social interaction among humans [3]
Harrison and Hudson [19] introduced a system that allows, through audio analysis, recognizing touches on different objects, especially desks and walls. They claimed that this system can differentiate between six types of touches with an accuracy rate of about 89.5%, validated using a training set composed of 450 touches performed by 15 users
The performance of the classifiers was compared using the F-score, which is usually calculating taking into account precision and recall as shown in Equation (4)
Summary
The role that the sense of touch plays in emotional communication in humans and animals have been widely studied, finding relations to attachment, bonding, stress and even memory [1,2].Touch, as a common communicative gesture, is an important aspect of social interaction among humans [3]. Several works focus on using touch as a valid modality to ascertain the user’s intention, and claim about the evidence of the touch as a powerful way of communicating emotions. In this sense, Hertenstein [2] found that anger, fear, disgust, love, gratitude, and sympathy are easier to detect than happiness and sadness. Some works have focused on studying the way humans communicate their emotional state to the social robots and the expected reactions when the interaction modality is touch. Yohanan et al [5] presented a touch dictionary of 30 items extracted from social psychology and human-animal interaction literature, identifying which ones are more likely to be used to communicate
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
