New research from the University of Glasgow suggests that giving robot companions animal-like or anime-style faces and voices could enhance their emotional appeal to users. This innovation could significantly impact the field of social robotics, where robots aim to provide companionship and comfort by imitating human or pet-like behaviors.
Despite the rapid growth of social robots in the tech industry, there has been minimal academic exploration on optimizing their designs to enhance their expressiveness and emotional engagement. Researchers at the University of Glasgow are working to bridge this research gap. They employed augmented reality technology to experiment with various combinations of faces and voices overlaid on a social robot named Qoobo, which features a plush body and a tail that moves.
Dr. Shaun Macdonald and Josh Yip, from the University of Glasgow’s School of Computing Science, conducted tests to gauge users’ responses to these virtual robots. They aimed to understand how users perceived the emotional states of the robots and how closely they resembled real creatures. Social robots have proven to be valuable for various groups, such as older individuals combating loneliness and those unable to keep real pets, who seek companionship from zoomorphic robots that mimic animals’ appearances and behavior.
The study emphasizes the importance of systematically designing the appearance of social robots. By leveraging augmented reality for rapid design tests, researchers gathered insights on what features make robots appealing to users. Dr. Macdonald’s previous work led to the development of a software system, AZRA, which facilitates overlaying sounds and animations onto real social robots for creating new appearances and functionalities.
The research team created five prototype faces inspired by animals, robots, emojis, anime, and simplistic designs. They also explored various vocalizations, such as cat noises, human-like sounds, abstract electronic noises, music, and ‘animalese’ from the game Animal Crossing. Tests with 24 volunteers wearing AR headsets revealed that combinations of animal-like faces and vocalizations resonated well with users, making the robots more engaging and immersive.
Surprisingly, anime-like faces were also well-received, showcasing their expressive potential. Participants found faces more effective than sounds in conveying emotions and establishing connections. The study indicated that users gravitated towards human sounds for emotional clarity but preferred animal sounds for likability. Interestingly, ‘animalese’ sounds, although unintelligible, were perceived positively, suggesting a higher sense of intelligence in the robot.
Furthermore, participants’ reactions to the prototypes were influenced by whether they owned real pets. Pet owners tended to view animal-like prototypes as real pets and robot-like faces as machines. The findings underline the impact of face-voice combinations on users’ perception of robots’ emotional communication.
The research aims to guide the future design of social robots, enabling users to personalize their robots with augmented reality overlays. The paper, ‘Anime, Animal or Animal Crossing? Comparing Aesthetic Styles for Zoomorphic Robot Faces and Sounds using Augmented Reality,’ will be presented at an upcoming conference in Swansea, Wales. Supported by funding from the University of Glasgow, this study sheds light on the potential of enhancing social robots’ emotional appeal and communication through innovative design approaches.
