Computational Theory of Mind
for Human-Machine Teams
AAAI Fall Symposium
(Virtual)
When the environment contains other people, humans use a skill called theory of mind (ToM) to infer their mental states from observed actions and context, and predict future actions from those inferred states. When humans form teams, these models can become extremely complex. High-performing teams naturally align key aspects of their models to create shared mental models of their environment, equipment, team, and strategies. ToM and the ability to create shared mental models are key elements of human social intelligence. Together, these two skills form the basis for human collaboration at all scales, whether the setting is a playing field or a military mission.
Artificial intelligence (AI) technologies have made little progress in understanding the most important component of the environments in which they operate: humans. This lack of understanding stymies efforts to create safe, efficient, and productive human-machine teams. The purpose of this symposium is to bring together researchers from computer science, cognitive science, and social science to discuss the creation of artificial intelligence systems that can generate theory of mind, exhibit social intelligence, and assist human teams.
Publication and Presentations
We accept the following types of submissions in AAAI format to the EasyChair site:
full papers (6-8 pages+references)
short papers (2-4 pages+references)
summaries of previously published papers (1 page)
Position papers about computational theory of mind and artificial social intelligence are welcome, as well as empirical studies.
Accepted papers will be assigned either a full length or lightning presentation slot.
The organizers will invite a subset of submissions to be included either in a Springer volume.
Dates
Aug 20, 2021: Abstract submission deadline
Aug 30, 2021: Paper submission deadline
Sept 20, 2021: Acceptance notifications
Oct 1, 2021: Author registration deadline
Oct 13, 2021: Camera ready paper deadline
Nov 4-6, 2021: Symposium
Update: the event is now scheduled to take place virtually only.
Example Topics
Research on artificial social intelligence
Computational theory of mind
Tasks and testbeds to evaluate theory of mind in agents
Algorithms to support human teamwork activities
Teamwork theories relevant for agent-support systems
Decision making models for teamwork
Collective intelligence models
Machine learning models of theory of mind
Neural networks
Inverse reinforcement learning
Multi-agent reinforcement learning
Nature and timing of agent advice
Natural language studies on team communication
Organizers
Joshua Elliott (DARPA)
Nik Gurney (University of Southern California)
Guy Hoffman (Cornell)
Lixiao Huang (Arizona State University)
Ellyn Maese (Gallup)
Ngoc Nguyen (Carnegie Mellon University)
Gita Sukthankar (University of Central Florida)
Katia Sycara (Carnegie Mellon University)
Main Contact:
Gita Sukthankar (gita.sukthankar@ucf.edu)