Affordable Access

deepdyve-link
Publisher Website

Evolving robot empathy towards humans with motor disabilities through artificial pain generation

Authors
  • Anshar, Muh
  • Williams, Mary-Anne
Type
Published Article
Journal
AIMS Neuroscience
Publisher
AIMS Press
Publication Date
Jan 30, 2018
Volume
5
Issue
1
Pages
56–73
Identifiers
DOI: 10.3934/Neuroscience.2018.1.56
PMID: 32341951
PMCID: PMC7181891
Source
PubMed Central
Keywords
Disciplines
  • Research Article
License
Unknown

Abstract

In contact assistive robots, a prolonged physical engagement between robots and humans with motor disabilities due to shoulder injuries, for instance, may at times lead humans to experience pain. In this situation, robots will require sophisticated capabilities, such as the ability to recognize human pain in advance and generate counter-responses as follow up emphatic action. Hence, it is important for robots to acquire an appropriate pain concept that allows them to develop these capabilities. This paper conceptualizes empathy generation through the realization of synthetic pain classes integrated into a robot's self-awareness framework, and the implementation of fault detection on the robot body serves as a primary source of pain activation. Projection of human shoulder motion into the robot arm motion acts as a fusion process, which is used as a medium to gather information for analyses then to generate corresponding synthetic pain and emphatic responses. An experiment is designed to mirror a human peer's shoulder motion into an observer robot. The results demonstrate that the fusion takes place accurately whenever unified internal states are achieved, allowing accurate classification of synthetic pain categories and generation of empathy responses in a timely fashion. Future works will consider a pain activation mechanism development.

Report this publication

Statistics

Seen <100 times