Home
I am Zahra a Ph.D in Computer Science at Arizona State University. I work at Yochan research group directed by Prof. Subbarao Kambhampati. My general research interest is in developing cutting-edge computational models and frameworks for trust and understanding human cognitive states to enhance human-AI interaction. I have extensive research experience in diverse areas such as automated planning, AI, human-AI interaction, human-robot interaction, reinforcement learning, machine learning, behavior modeling of humans using data, statistical modeling, decision-making frameworks, and game theory. You can find the latest version of my CV here.
Publications
HRI Pioneer 2024
Under-review
ITSC 2023
XAI Workshop, IJCAI 2023
Accepted as a stand-alone video, ICRA 2023
Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS)
R2HCAI Workshop, AAAII 2023
Proceedings of 2022 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI)
XAIP and PlanRob Workshop, ICAPS 2021
R4P Workshop, R:SS 2021
Cooperative AI Workshop, NeurIPS 2020
21st International Workshop on Trust in Agent Societies (co-located with AAMAS), (2019)
HRI Late Breaking Report, (2019)
Journal of Vibration and Control, (2022)
Systems and Control Letters, (2019)
in proc. 2018 American Control Conference
25th Iranian Conference on Electrical Engineering (ICEE), published in IEEE Xplorer, May 2017
International Journal of Signal Processing Systems (IJSPS), vol. 4, no. 1, pp. 17-21, 2016
Journal of Electrical and Electronic Engineering, vol. 3, no. 2-1, pp. 58-61, 2015
6th International Conference on Signal Processing Systems (ICSPS), 2014
8th Symposium on Advances in Science & Technology, 2014 (Persian)
Experiences
In this role, I was responsible for developing modeling framework to understand and predict human cognitive states, modeling dynamics of human behavior for human-automation interactions, and creating and validating tools to optimize system performance based on predicted human states.
Awards and Honors
Current Research Projects
Mental model based framework of trust
- In this work, we contextualize the user’s trust and their consequent choice on whether or not to rely on the AI agent in terms of their mental model of the agent, and their preexisting expectations about the optimal way of solving the task. The agent on the other hand can either use behavior generated through its model, or explanations about its model, to influence both the user’s expectations about the agent and their expectations about the task.
Trust-Aware Planning in longitudinal human robot interaction
- In this work, we have propose a computational model for capturing and modulating trust in longitudinal human-robot interaction where the robot integrates human’s trust and their expectations into planning to build and maintain trust over the interaction horizon. By establishing the required level of trust, the robot can focus on maximizing the team goal by eschewing explicit explanatory or explicable behavior. The human also with a high level of trust in the robot, might choose not to monitor the robot, or not to intervene by stopping the robot and save their resources.
Game-theoretic model of trust
- In this work, we modeled a game theoretic model of trust in Human robot interaction setting and introduced a solution as a trust boundary which is a proper human’s monitoring strategy given the inferred trust. By choosing a monitoring strategy in that boundary, the human supervisor can assure that the robot or the artificial intelligent system will show a safe and interpretable behavior.
Negotiation-aware task allocation
- We considered a task-allocation problem where an AI Task Allocator (AITA) comes up with a fair allocation for a group of humans. And the AITA is able to provide explanation in the form of negotiation tree to convince humans who thinks a counterfactual allocation is more fair.