In the Arms of a Robot: Designing Autonomous Hugging Robots with Intra-Hug Gestures

Abstract

Hugs are complex affective interactions that often include gestures like squeezes. We present six new guidelines for designing interactive hugging robots, which we validate through two studies with our custom robot. To achieve autonomy, we investigated robot responses to four human intra-hug gestures: holding, rubbing, patting, and squeezing. Thirty-two users each exchanged and rated sixteen hugs with an experimenter-controlled HuggieBot 2.0. The robot’s inflated torso’s microphone and pressure sensor collected data of the subjects’ demonstrations that were used to develop a perceptual algorithm that classifies user actions with 88% accuracy. Users enjoyed robot squeezes, regardless of their performed action, they valued variety in the robot response, and they appreciated robot-initiated intra-hug gestures. From average user ratings, we created a probabilistic behavior algorithm that chooses robot responses in real time. We implemented improvements to the robot platform to create HuggieBot 3.0 and then validated its gesture perception system and behavior algorithm with sixteen users. The robot’s responses and proactive gestures were greatly enjoyed. Users found the robot more natural, enjoyable, and intelligent in the last phase of the experiment than in the first. After the study, they felt more understood by the robot and thought robots were nicer to hug.

A HUG taxonomy of humans with potential in human–robot hugs

“…Therefore, it is reasonable to simplify these similar hugs into one hug type in the HUG taxonomy. Adding subtle variations (maybe intra-hug gestures) offers the possibility for further hug-type distinction for huggers of different states 34 .…”

“…They 15,33 conducted a quantitative assessment of human evaluations of robot physical conditions (i.e., softness and temperature) and characteristics of hugging behaviors (i.e., duration and pressure). Further research 34,35 emphasized humans' particular sensitivity to elements of hugs, notably the intra-hug gesture of the robot and the hugging tightness.…”

“…To the best of our knowledge, the HUG taxonomy is the first well-defined taxonomy of hugs. Therefore, we compare the HUG taxonomy with the hugging behavior research (see 10,14,15,21,[24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] ), covering the domain of humans and robots. Most reviews of the human hugging behavior research only suggest taxonomic ideas without conducting any further classification.…”

Do digital hugs work? Re-embodying our social lives online with digital tact

“… 13 Recent work with hugging robots like HuggieBot 3.0 ( Block et al, 2022 ), which is capable of even sophisticated ‘intrahug gestures’ (e.g., squeezing, rubbing, patting) in response to the gestures of the user, confirms this. Although users typically enjoy the experience–some even prefer it–they experience it as very different from hugging another person.…”

Human Factors Considerations for Quantifiable Human States in Physical Human–Robot Interaction: A Literature Review

“…This emphasis on direct pHRI may be attributed to the fact that many of the applications that have emerged are socially oriented, as evidenced by the greater number of studies on non-functional touch compared to functional touch. For example, handshaking [59,60,71,77,78,80,83,85,87]; hugging [57,61,62,67,72]; clapping [27,54,55]; nursing [50,64,98,101,108]; and playing virtual games [19,38,94,111] [113] have received significant attention. This trend is consistent with the idea that touch can serve important social and emotional functions in HRI, which, in turn, contributes to the realization of the Society 5.0 vision to a certain extent.…”