![]() ![]() Others have chosen to create robots that hug in a “one-size-fits-most” model. In the past, researchers have avoided tackling these challenges by providing a huggable device that does not actively hug the user back, thereby entirely avoiding the challenges of reciprocating a hug. Īccurately replicating a human hug is a difficult problem because it requires real-time adaptation to a wide variety of users, close physical contact, and quick, natural responses to intra-hug gestures performed by the user. Lack of social touch can be detrimental to both our physical and mental health. During the current global pandemic of COVID-19, some family members have been unable to come into close contact with each other for more than one year, and the effects are showing. Many common examples where people lack access to human hugs stem from long-term physical separation. The broader goal of this research project is to provide an embodied affective robot that can supplement human hugs in situations when requesting this form of comfort from others is difficult or impossible. If a similar effect can be achieved through a robotic embrace, this helpful touch can benefit people who otherwise would not be able to experience hugs. Not everyone is fortunate enough to have close, positive relationships with people around them. Despite their importance during prolonged hugs between humans, no prior hugging robot has been able to detect and respond to intra-hug gestures. The four intra-hug gestures that our hugging robot, HuggieBot, can perform, either in response to a user action or proactively when it does not detect any user actions. After the study, they felt more understood by the robot and thought robots were nicer to hug.įig. Users found the robot more natural, enjoyable, and intelligent in the last phase of the experiment than in the first. The robot’s responses and proactive gestures were greatly enjoyed. We implemented improvements to the robot platform to create HuggieBot 3.0 and then validated its gesture perception system and behavior algorithm with 16 users. From average user ratings, we created a probabilistic behavior algorithm that chooses robot responses in real time. Users enjoyed robot squeezes, regardless of their performed action, they valued variety in the robot response, and they appreciated robot-initiated intra-hug gestures. ![]() 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. A Total of 32 users each exchanged and rated 16 hugs with an experimenter-controlled HuggieBot 2.0. ![]() To achieve autonomy, we investigated robot responses to four human intra-hug gestures: holding, rubbing, patting, and squeezing. We present six new guidelines for designing interactive hugging robots, which we validate through two studies with our custom robot. Hugs are complex affective interactions that often include gestures like squeezes. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |