A Trained Humanoid Robot can Perform Human-Like Crossmodal Social Attention and Conflict Resolution

Bibliographic Data

ID21199265
AuthorsDi Fu (0000-0002-5385-2982, Universität Hamburg, corresponding author), Fares Abawi (0000-0002-4240-5351, Universität Hamburg), Hugo Carneiro (0000-0001-5094-5908, Universität Hamburg), Matthias Kerzel (0000-0002-1378-0435, Universität Hamburg), Ziwei Chen (0000-0001-8295-7444, Institute of Psychology, Chinese Academy of Sciences), Erik Strahl (0009-0009-7858-8274, Universität Hamburg), Xun Liu (0000-0003-4732-5390, Institute of Psychology, Chinese Academy of Sciences, corresponding author), Stefan Wermter (0000-0003-1343-4775, Universität Hamburg)
Year2023
Volume15
Issue8
Pages1325-1340
Publication date2023-08-01
Open AccessYes
TypeARTICLE
VenueInternational Journal of Social Robotics (JOURNAL)
Journal identifiersISSN: 1875-4791 • E-ISSN: 1875-4805
PublisherSpringer Science and Business Media LLC (PUBLISHER)
DOI10.1007/s12369-023-00993-3
PMID37359433
OpenAlexW4362591460
LanguageEN
Citations received2
References cited72

To enhance human-robot social interaction, it is essential for robots to process multiple social cues in a complex real-world environment. However, incongruency of input information across modalities is inevitable and could be challenging for robots to process. To tackle this challenge, our study adopted the neurorobotic paradigm of crossmodal conflict resolution to make a robot express human-like social attention. A behavioural experiment was conducted on 37 participants for the human study. We designed a round-table meeting scenario with three animated avatars to improve ecological validity. Each avatar wore a medical mask to obscure the facial cues of the nose, mouth, and jaw. The central avatar shifted its eye gaze while the peripheral avatars generated sound. Gaze direction and sound locations were either spatially congruent or incongruent. We observed that the central avatar’s dynamic gaze could trigger crossmodal social attention responses. In particular, human performance was better under the congruent audio-visual condition than the incongruent condition. Our saliency prediction model was trained to detect social cues, predict audio-visual saliency, and attend selectively for the robot study. After mounting the trained model on the iCub, the robot was exposed to laboratory conditions similar to the human experiment. While the human performance was overall superior, our trained model demonstrated that it could replicate attention responses similar to humans

Cognitive psychology · Computer vision · Conflict resolution · Crossmodal · Human–computer interaction · Human–robot interaction · Humanoid robot · Mechatronics · Mobile robot · Perception · Robot · Robot control · Robotics · Social robot · Sociology · Visual perception · Computer Science · Language, Metaphor, and Cognition · Neuroscience · Psychology · Social Robot Interaction and HRI · Speech and dialogue systems · Artificial Intelligence

Tools

Open DOIOpen Access