2014/11/19 by Martin Cooney, Martin D. Cooney, Shuichi Nishio +1
Psychology · #Action Observation and Synchronization #Affection #Artificial intelligence #Computer science #Emotion and Mood Recognition #Humanoid robot #Human–computer interaction #Human–robot interaction #Mobile robot #Modalities #Modality (human–computer interaction) #Psychology #Robot #Robot control #Social Robot Interaction and HRI #Social psychology #Social robot #Sociology
paper · doi:10.1142/s0219843615500024
openalex publication_date 2014/11/19 · crossref created 2014/11/19 · crossref issued 2015/03/01 · crossref published 2015/03/01 · crossref published-print 2015/03/01 · crossref published-online 2015/03/12 · crossref deposited 2019/08/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/11 · crossref indexed 2026/07/31
To be accepted as a part of our everyday lives, companion robots will require the capability to communicate socially, recognizing people's behavior and responding appropriately. In particular, we hypothesized that a humanoid robot should be able to recognize affectionate touches conveying liking or dislike because (a) a humanoid form elicits expectations of a high degree of social intelligence, (b) touch behavior plays a fundamental and crucial role in human bonding, and (c) robotic responses providing affection could contribute to people's quality of life. The hypothesis that people will seek to affectionately touch a robot needed to be verified because robots are typically not soft or warm like humans, and people can communicate through various other modalities such as vision and sound. The main challenge faced was that people's social norms are highly complex, involving behavior in multiple channels. To deal with this challenge, we adopted an approach in which we analyzed free interactions and also asked participants to rate short video-clips depicting human–robot interaction. As a result, we verified that touch plays an important part in the communication of affection from a person to a humanoid robot considered capable of recognizing cues in touch, vision, and sound. Our results suggest that designers of affectionate interactions with a humanoid robot should not ignore the fundamental modality of touch.