Recent advances in sensing technologies enable robots to capture rich multimodal human signals, including gaze, speech, motion, and physiological responses. However, most systems still rely on event-driven behaviors and predefined policies, limiting their ability to incorporate continuous estimates of human internal states into real-time control. This workshop addresses the integration of multimodal human state estimation with robotic decision making. It explores approaches that connect sensing, representation learning, and adaptive planning across cognitive and social dimensions of interaction, with a focus on dynamic states such as engagement, anxiety, and trust. By covering the full pipeline from data curation and multimodal fusion to real time deployment, the workshop also highlights challenges including noise, latency, and ethical concerns, aiming to advance robust, context aware, and human centered HRI systems.

Submission Guidelines

Submit work that connects multimodal human data to adaptive robot behavior—methods, datasets, studies, systems, or lessons learned. We particularly encourage contributions that address robustness, responsible data practices, and deployment in-the-wild.

• Full papers (up to 6 pages, including references)
• Extended abstracts/Short papers (2–4 pages, including references)

List of Topics

We invite submissions that address (but are not limited to) the following topics:

• Multimodal sensing for HRI (gaze, speech, motion, physiology)
• Human internal state estimation (engagement, stress, fatigue, mind wandering)
• Theories, models, methodologies, and tools for human internal state estimation
• Multimodal data fusion, alignment, missing data, dataset bias, robustness
• Learning adaptive interaction policies (supervised, RL, imitation, LLM-based)
• Online adaptation and human-in-the-loop learning
• Trustworthy robotics: calibration, over-reliance, transparency, agency
• Ethics of biosignals in the wild (privacy, consent, data governance)
• Applications: social robots, teleoperation, assistive robots, safety-critical HRI
• Responsible dataset sharing: de-identification, access control, and reproducibility best practices

Committees

Organizing Committee

• Xiaoxuan Hei, ENSTA, Institut Polytechnique de Paris
• Mohammed Al-Sada, Qatar University
• Nihan Karatas, Nagoya University
• Tamon Miyake, Waseda University
• Neziha.Akalin, Jönköping University
• Faisal Al-Jaber, Qatar University
• Prof. Shogo Okada, Japan Advanced Institute of Science and Technology
• Prof. Adriana Tapus, ENSTA, Institut Polytechnique de Paris

Contact

All questions about submissions should be emailed to workshop@qmic.com