analiza aiqbench
This study tests whether an autonomous social robot that fuses speech, vision, and touch can match a human-teleoperated baseline in a VR setting. It falls short on naturalness and social appropriateness, and the authors point to conversational timing, clarifying ambiguous requests, and spatial coordination as the main gaps. For AI readers, the useful signal is the benchmark-style comparison against human operators, which shows where multimodal interaction still lags human performance.
Multimodal Socially Aware Framework for Human-Robot Interaction in Virtual Reality
De la arXiv
Text integralarXiv:2610.34534v1 Announce Type: new Abstract: Social robots must coordinate speech and movement while interpreting multimodal human input. We present a multimodal framework that integrates speech, vision, and touch to generate contextually appropriate robot speech and movement. We evaluated the framework in virtual reality with 18 participants across five social interaction scenarios, comparing its performance against a human-teleoperated baseline. Although participants rated the autonomous system above the neutral midpoint for both naturalness and social appropriateness, the teleoperated baseline received significantly higher ratings on both measures.
Behavioral coding and qualitative feedback revealed that conversational timing, clarification of ambiguous requests, and spatial coordination were important factors contributing to this performance gap. These findings highlight key challenges in developing autonomous robots capable of natural, multimodal social interaction.
Abstract:Social robots must coordinate speech and movement while interpreting multimodal human input. We present a multimodal framework that integrates speech, vision, and touch to generate contextually appropriate robot speech and movement. We evaluated the framework in virtual reality with 18 participants across five social interaction scenarios, comparing its performance against a human-teleoperated baseline. Although participants rated the autonomous system above the neutral midpoint for both naturalness and social appropriateness, the teleoperated baseline received significantly higher ratings on both measures.
Behavioral coding and qualitative feedback revealed that conversational timing, clarification of ambiguous requests, and spatial coordination were important factors contributing to this performance gap. These findings highlight key challenges in developing autonomous robots capable of natural, multimodal social interaction.
Robotics (cs.RO)
arXiv:2610.34534 [cs.RO]
(or arXiv:2610.34534v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.34534 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 211 cuvinte
Subiecte conexe
Information-Theoretic Decomposition for Multimodal Interaction Learning
arXiv · 12 iun. 2026
DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams
arXiv · 21 oct. 2026
Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning
arXiv · 6 nov. 2026
MIME: Multimodal Interactive Motion Encoder
arXiv · 28 iul. 2026