A more complete list is available on Google Scholar.
Failure detectors can tell a robot that something went wrong, but not why. We ground failure prediction in causal concept bottleneck models, using vision-language models to extract failure-relevant concepts and their causal structure from rollout videos, so the robot can explain which concepts drove a predicted failure and reason counterfactually about what would change the outcome.
Mihir Parekh, Michelle Zhao
Human teachers correcting a robot observe its behavior, but not the visual representations driving its policy. We characterize what a visuomotor policy’s internal attention encodes across task stages, failures, and interventions, and use it to give teachers stage-relevant visual guidance during interactive corrections.
Jiahe Liu, Michelle Zhao
Workshop on Rethinking Uncertainty for Modern Robotics Paradigms at IROS, 2026 · [PDF]
Collaborative robots must keep adapting to new tasks and user preferences without overburdening the person they work with. We cast multi-task interactive learning as a facility location problem, planning a sequence of human interventions that is near-optimal across a whole stream of tasks rather than greedy on the current one.
Shivam Vats, Michelle Zhao, Patrick Callaghan, Mingxi Jia, Maxim Likhachev, Oliver Kroemer, George Konidaris
When feedback arrives only intermittently, robots can use conformal prediction to ensure their uncertainty estimates are well-calibrated, so they can know when to trust their learned policy and when to ask for more guidance in interactive imitation learning.
Michelle Zhao, Reid Simmons, Henny Admoni, Aaditya Ramdas, Andrea Bajcsy
International Conference on Learning Representations (ICLR), 2025
Assistive arms have far more degrees of freedom than a joystick can express, so learned interfaces must guess at the operator’s intent. We calibrate that mapping with conformal prediction, giving the robot a principled signal for when its inferred action is trustworthy and when it is not.
Michelle Zhao, Reid Simmons, Henny Admoni, Andrea Bajcsy
People care not only about whether a task gets done but about which parts of it they do themselves. We model and learn these contribution preferences, so a robot can divide collaborative work in the way its partner actually wants.
Michelle D. Zhao, Reid Simmons, Henny Admoni
For people to coordinate with robots, they need an accurate picture of how the robot will act. We generate explanations of a joint multi-agent strategy and show they improve how well people can predict and work with a robot partner.
Ravi Pandya, Michelle Zhao, Changliu Liu, Reid Simmons, Henny Admoni
IEEE International Conference on Robotics and Automation (ICRA), 2024
In human-robot collaborative settings, we infer a human partner’s high-level strategy from a handful of observed actions and adapt the robot’s policy to match it.
Michelle Zhao, Reid Simmons, Henny Admoni
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Why Did the Robot Fail? Causal Concept Bottlenecks for Failure Detection and Explanation
Mihir Parekh, Michelle Zhao
Workshop on Human-Robot Dialogue at IROS, 2026 · [PDF]
Show Me What You See: Communicating Visuomotor Policy Attention for Interactive Robot Learning
Jiahe Liu, Michelle Zhao
Workshop on Rethinking Uncertainty for Modern Robotics Paradigms at IROS, 2026 · [PDF]
Optimal Interactive Learning on the Job via Facility Location Planning
Shivam Vats, Michelle Zhao, Patrick Callaghan, Mingxi Jia, Maxim Likhachev, Oliver Kroemer, George Konidaris
Robotics: Science and Systems (RSS), 2025
Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
Michelle Zhao, Reid Simmons, Henny Admoni, Aaditya Ramdas, Andrea Bajcsy
International Conference on Learning Representations (ICLR), 2025
Conformalized Teleoperation: Confidently Mapping Human Inputs to High-Dimensional Robot Actions
Michelle Zhao, Reid Simmons, Henny Admoni, Andrea Bajcsy
Robotics: Science and Systems (RSS), 2025
Learning Human Contribution Preferences in Collaborative Human-Robot Tasks
Michelle D. Zhao, Reid Simmons, Henny Admoni
Conference on Robot Learning (CoRL), 2023
Multi-Agent Strategy Explanations for Human-Robot Collaboration
Ravi Pandya, Michelle Zhao, Changliu Liu, Reid Simmons, Henny Admoni
IEEE International Conference on Robotics and Automation (ICRA), 2024
Coordination with Humans via Strategy Matching
Michelle Zhao, Reid Simmons, Henny Admoni
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Integrating Learning and Collaboration for Human-Robot Alignment
Michelle Zhao
PhD thesis, Carnegie Mellon University, 2026
Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI): Evolving Assistance for Everyday Life
Bahar Irfan, Nikhil Churamani, Michelle Zhao, Rajat Kumar Jenamani, Ali Ayub, Silvia Rossi
Companion of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2026
Bi-Directional Mental Model Reconciliation for Human-Robot Interaction with Large Language Models
Nina Moorman, Michelle Zhao, Matthew B. Luebbers, Sanne Van Waveren, Reid Simmons, Henny Admoni, Sonia Chernova, Matthew Gombolay
arXiv:2503.07547, 2025
Leveraging LLMs for Preference-Based Sequence Prediction
Michelle Zhao, Reid Simmons, Henny Admoni
International Conference on Agents and Artificial Intelligence (ICAART), 2025
Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI): Overcoming Inequalities with Adaptation
Bahar Irfan, Nikhil Churamani, Michelle Zhao, Ali Ayub, Silvia Rossi
Companion of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2025
HRI’24: Workshop on Aging in Place
Nina M. Moorman, Michelle Zhao, Henny Admoni, Reid Simmons, Matthew Gombolay
Companion of the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2024
The Role of Adaptation in Collective Human-AI Teaming
Michelle Zhao, Fade R. Eadeh, Thuy-Ngoc Nguyen, Pranav Gupta, Henny Admoni, Cleotilde Gonzalez, Anita Williams Woolley
Topics in Cognitive Science, 2022
Teaching Agents to Understand Teamwork: Evaluating and Predicting Collective Intelligence as a Latent Variable via Hidden Markov Models
Michelle Zhao, Fade R. Eadeh, Thuy-Ngoc Nguyen, Pranav Gupta, Henny Admoni, Cleotilde Gonzalez, Anita Williams Woolley
Computers in Human Behavior, 2022
Adapting Language Complexity for AI-Based Assistance
Michelle Zhao, Reid Simmons, Henny Admoni
Lifelong Learning Workshop at the ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2021
Distributed Control of an Evolving Satellite Assembly During In-Orbit Construction
Rebecca Foust, Michelle Zhao, Suzanne Oliver, Soon-Jo Chung, Fred Y. Hadaegh
International Astronautical Congress (IAC), 2017
* denotes equal contribution.
RIA Lab