AI and human partnership modeling for emergency dispatch

Interdisciplinary Areas: Autonomous and Connected Systems, Human-Machine/Computer Interaction, Human Factors, Human-Centered Design

Project Description:

When emergencies like wildfires or hurricanes happen, fast and targeted responses with dispatching and relocation of rescue teams, vehicles, helicopters, or even UVAs are needed. New emergency response technologies make use of advancements in AI (including ML and autonomous systems) to increase the success of targeted dispatching. Meanwhile, with the ability to trace emergency-related data at scale, digital twins offer new ways to prepare for future emergency responses in the “virtual” but “very real” representation of distinct emergency response systems. However, given the complex socio-technical nature and social dynamics in emergency response decision-making, it is important to consider the “human-in-the-loop” and optimize the collaboration between AI and humans. This post-doctoral interdisciplinary research project aims to develop new theories, models, and technologies that advance science on modeling human-in-the-loop AI and translate it into emergency response practice. The project team will advance existing emergency response systems with the help of AI/ML and digital twin technologies, and perform large-scale AI-human partnership experiments with the goal to optimize the decisions of humans in partnership with AI-decision support considering human biases and social dynamics. The research will be performed in collaboration with industry partners and citizens.

Start Date:

Between January 2023 and June 2023; negotiable based on graduation and personal needs of applicant

Postdoc Qualifications:

The ideal candidate holds a PhD in areas such as Computer Science, Industrial Engineering, Systems Engineering, or other Engineering disciplines, Management Sciences, Information systems, Information Sciences, Computational Social Science, Complexity Science, or Network Science. We expect the candidate to be trained in ML/AI and data science, with the ability to mine and model large volumes of behavioral trace data, geospatial data, etc. Experience in agent-based modeling and network analytics is appreciated but not required. We would expect that irrespective of the candidate’s training he/she has a solid understanding of behavioral theories of social dynamics, team coordination, and/or human decision-making under risk. Experience in performing large-scale human experiments (e.g. via online platforms) interfacing with digital technologies or experience in smart interface design and quantitative evaluation is a plus.


Nan Kong, Professor of Biomedical Engineering, Weldon of Biomedical Engineering
Sabine Brunswicker, Professor of Digital Innovation, Polytechnic Institute and Brian Lamb School of Communication

Outside Collaborators:

Dengfeng Sun, Purdue AAE,
Nosh Contractor, Northwestern University:
Jane S. & William J. White Professor of Behavioral Sciences in the McCormick School of Engineering & Applied Science, the School of Communication and the Kellogg School of Management and Director of the Science of Networks in Communities (SONIC) Research Group at Northwestern University.
Sabine Hausert, University of Bristol, Associate Professor in Swarm Engineering,


Aaron Guo, Hanyao Hu, Linzhe Wang, Dengfeng Sun and Jerry Gu. Gazebo-Based Simulation Environment Integration for UAS, AIAA 2021-3011. AIAA AVIATION 2021 FORUM. August 2021.

Brunswicker S, Bertino E, Matei S (2015) Big Data for Open Digital Innovation – A Research Roadmap. Big Data Research 2(2):53–58.

Hohenstein J, Larson LE, Hou YTY, Harris AM, Schecter A, Dechurch L, Contractor N, Jung MF (2022) Vero: A Method for Remotely Studying Human-AI Collaboration. Hawaii International Conference on System Sciences 2022.

Kong, N., Paz, J. C., & Gao X. EMS Operations management: simulation, optimization, and new service models. In Proceedings of the 2022 Winter Simulation Conference, B. Feng, G. Pedrielli, Y. Peng, S. Shashaani, E. Song, C.G. Corlu, L.H. Lee, E.P. Chew, T. Roeder, and P. Lendermann, eds. December 2022.

Mohammadi N, Taylor JE (2021) Thinking fast and slow in disaster decision-making with Smart City Digital Twins. Nat Comput Sci 1(12):771–773.

Schecter A, Nohadani O, Contractor N (2022) A Robust Inference Method for Decision Making in Networks. Management Information Systems Quarterly 46(2):713–738.