The HAII Center develops and uses AI technology for improving the long-term autonomy and interaction capabilities of future AI systems, embodied and disembodied, that are embedded in human societies such as virtual agents based on foundation models (e.g., personal cognitive assistants on smart devices, advisor systems, large generative AI language models like ChatGTP, etc.) or assistive robots (e.g., for elder care, search and rescue, surveillance, manufacturing, health monitoring).
The employed technologies encompass various AI approaches (e.g., generative AI for language understanding and common sense, deep neural networks for perception and reinforcement learning, symbolic reasoning for task planning, hybrid methods for natural language understanding, etc.) to control the behavior of fully autonomous virtual and robotic agents and their interactions with humans. Novel methods and technologies are evaluated in human-AI interaction experiments to determine their suitability and utility. Most critically, the HAII Center has a focus on ethical AI and thus aims to establish the norm-confirming nature of all developed technologies.
Matthias Scheutz
Director of the Human-AI Interaction Center
Karol Family Applied Technology Professor
Matthias Scheutz has over 400 peer-reviewed publications in artificial intelligence, artificial life, agent-based computing, natural language understanding, cognitive modeling, robotics, human-robot interaction and foundations of cognitive science. His current research focuses on complex ethical cognitive robots with natural language interaction, problem-solving, and instruction-based learning capabilities in open worlds.
Publications and Grants
-
An Interactive Robot Platform for Introducing Reinforcement Learning to K-12 Students
Z Zhang, S Willner-Giwerc, J Sinapov, J Cross, C Rogers
Robotics in Education: RiE 2021 12, 288-301
Introducing Reinforcement Learning to K-12 Students with Robots and Augmented Reality
Z Zhang, K Lavigne, W Church, J Sinapov, C Rogers
International Conference on Robotics in Education (RiE), 351-365
Introductory Activities for Teaching Robotics with SmartMotors
M Dahal, L Kresin, C Rogers
International Conference on Robotics in Education (RiE), 229-241 -
Large Language Models Know What To Say But Not When To Speak
Muhammad Umair and Vasanth Sarathy and JP de Ruiter
Reasoning Requirements for Indirect Speech Act Interpretation
Vasanth Sarathy, Alexander Tsuetaki, Antonio Roque, Matthias Scheutz
When Exceptions Are the Norm: Exploring the Role of Consent in HRI
Vasanth Sarathy, Thomas Arnold, and Matthias Scheutz
-
Introduction to symbolic plan and goal recognition
Mirsky, R., Keren, S., & Geib, C. (2021)
San Rafael, CA, USA: Morgan & Claypool Publishers. (Vol. 16, pp. 1-190)
Recognition and Identification of Intentional Blocking in Social Navigation
Mirsky, R., & Shpiro, E. (2024, March)
Proceedings of the 2024 International Symposium on Technological Advances in Human-Robot Interaction (pp. 101-110)
A penny for your thoughts: The value of communication in ad hoc teamwork.
Mirsky, R., Macke, W., Wang, A., Yedidsion, H., & Stone, P. (2020)
International Joint Conference on Artificial Intelligence.
-
Dialogue-Based Task Instructions and Modifications for Industrial Robots
M. Scheutz and B. Oosterveld and J. Peterson and E. Wyss (2024)
Proceedings of ARCI 2024
The Limits of Robot Moderators: Evidence Against Robot Personalization and Participation Equalization in a Building Task
H. Owens, R. M. Aronson, E. Short.
IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Pasadena, August 2024
TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer
A. Allevato, E. Short, M. Pryor, and A. L. Thomaz
Conference on Robot Learning (CORL), Osaka, Japan, 2019 -
A Multi-Robot Architecture Framework for Effective Robot Teammates in Mixed-Initiative Teams
M. Scheutz and B. Oosterveld and J. Peterson and E. Wyss and E. Krause (2024)
Proceedings of Technical Advances in Human-Robot Interaction (THARI'24)
Large Language Models Know What To Say But Not When To Speak
Muhammad Umair and Vasanth Sarathy and JP de Ruiter (2024)
Keeping Humans in the Loop: Teaching via Feedback in Continuous Action Space Environments
I. Sheidlower, A. Moore, E. Short
International Conference on Intelligent Robots and Systems (IROS), Kyoto, October 2022