Harrison Huang
Portrait
Logo PhD Student at Rice University

I specialize in human-centered artificial intelligence, focusing on AI transparency and improving human-robot collaboration. Currently, I’m a researcher in the Teaming Lab at Rice University, where I explore how AI can help people better understand and work alongside intelligent systems. I aim to design AI that both supports people in their tasks and makes working with technology more intuitive and effective.

Currently: a PhD student in the Human-Centered AI and Robotics Lab, continuing my work on personalized, explainable robot behavior summaries.
Curriculum Vitae
Google Scholar GitHub LinkedIn
Education
  • Rice University
    Rice University
    Department of Computer Science
    Ph.D. in Computer Science
    Aug 2025 - Present
  • Rice University
    Rice University
    Department of Computer Science
    M.S. in Computer Science
    Jan 2024 - May 2025
  • Rice University
    Rice University
    Department of Computer Science
    B.S. in Computer Science
    Minor in Mathematics
    Aug 2020 - Dec 2023
Experience
  • Rice University
    Rice University
    Human-Centered AI and Robotics Lab Researcher
    Apr 2022 - Present
  • Rice University
    Rice University
    Lead Event Planner, CS Graduate Student Association
    Aug 2023 - Present
  • Delta Air Lines
    Delta Air Lines
    Artificial Intelligence Engineer Intern
    Jun 2024 - Aug 2024
  • Rice University
    Rice University
    Computer Science Teaching Assistant
    Aug 2021 - Present
  • Rice University
    Rice University
    Jones College Webmaster
    Mar 2022 - Dec 2023
Honors & Awards
  • IES Students and Young Professionals Paper Assistance Program (IES-SYPA)
    Aug 2026
  • 2025 NSF GRFP Honorable Mention
    Apr 2025
  • 2nd Place, IEEE Computer Society North America Student Challenge Competition
    Dec 2024
  • AIES 2024 Student Travel Award
    Oct 2024
  • Rice Engineering Alumni (REA) Graduate Student Travel Grant
    Oct 2024
  • Rice University MS Fellowship Award
    Jan 2024
  • President's Honor Roll
    Dec 2023
  • Segal AmeriCorps Education Award
    Aug 2021
News
2026
I received the IEEE IES Students and Young Professionals Paper Assistance (IES-SYPA) award
Aug 10
My paper, OOPS: Out-of-Distribution Policy Summarization, has been accepted to IROS 2026!
Jun 16
2025
I started my Ph.D. in Computer Science at Rice University!
Aug 18
I successfully defended my MS thesis! You can find it here: Personalized Explanations of Robot Behavior for Human Users
Apr 15
I’m excited to share that I’ve accepted an offer to join Rice University's Computer Science PhD program starting in Fall 2025!
Apr 10
Selected Publications (view all )
OOPS: Out-of-Distribution Policy Summarization
OOPS: Out-of-Distribution Policy Summarization

Harrison Huang, Yao Rong, Peizhu Qian, Vaibhav Unhelkar

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026

Robots are increasingly deployed across diverse real-world domains. As they assume critical roles, it becomes essential for humans to understand how they sense, reason, and act to ensure safe and responsible use. Recent advances in Explainable AI (XAI) have sought to support this understanding through the explanation-by-example paradigm. Specifically, policy summarization has emerged as a promising solution, generating summaries composed of representative examples of robot behavior for users. However, existing methods select examples only from the robot's training set (i.e., in-distribution scenarios). As such, they fail to capture a variety of scenarios that the robot would encounter in practice but are absent from its training set (i.e., out-of-distribution scenarios). We argue that holistic explanations, containing both in-distribution and out-of-distribution examples, are crucial for fostering human understanding of robot behavior. To address this gap, we introduce Out-of-Distribution Policy Summarization (OOPS), an explanation-by-example approach designed to jointly teach users how robots perceive, reason, and act in novel scenarios.

[Paper] [BibTeX]

OOPS: Out-of-Distribution Policy Summarization

Harrison Huang, Yao Rong, Peizhu Qian, Vaibhav Unhelkar

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026

Robots are increasingly deployed across diverse real-world domains. As they assume critical roles, it becomes essential for humans to understand how they sense, reason, and act to ensure safe and responsible use. Recent advances in Explainable AI (XAI) have sought to support this understanding through the explanation-by-example paradigm. Specifically, policy summarization has emerged as a promising solution, generating summaries composed of representative examples of robot behavior for users. However, existing methods select examples only from the robot's training set (i.e., in-distribution scenarios). As such, they fail to capture a variety of scenarios that the robot would encounter in practice but are absent from its training set (i.e., out-of-distribution scenarios). We argue that holistic explanations, containing both in-distribution and out-of-distribution examples, are crucial for fostering human understanding of robot behavior. To address this gap, we introduce Out-of-Distribution Policy Summarization (OOPS), an explanation-by-example approach designed to jointly teach users how robots perceive, reason, and act in novel scenarios.

[Paper]

PPS: Personalized Policy Summarization for Explaining Sequential Behavior of Autonomous Agents
PPS: Personalized Policy Summarization for Explaining Sequential Behavior of Autonomous Agents

Harrison Huang*, Peizhu Qian*, Vaibhav Unhelkar (* equal contribution)

AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2024 Spotlight

Policy summarization methods aim to showcase key examples of agent behaviors to their human users. Yet, existing methods produce “one-size-fits-all” summaries for a generic audience ahead of time. Drawing inspiration from research in pedagogy, we posit that personalized policy summaries can more effectively enhance user understanding. To evaluate this hypothesis, this paper presents and benchmarks a novel technique: Personalized Policy Summarization (PPS). PPS discerns a user’s mental model of the agent through a series of algorithmically generated questions and crafts customized policy summaries to enhance user understanding. Unlike existing methods, PPS actively engages with users to gauge their comprehension of the agent behavior, subsequently generating tailored explanations on the fly. Through a combination of numerical and human subject experiments, we confirm the utility of this personalized approach to explainable AI.

[Paper] [BibTeX]

PPS: Personalized Policy Summarization for Explaining Sequential Behavior of Autonomous Agents

Harrison Huang*, Peizhu Qian*, Vaibhav Unhelkar (* equal contribution)

AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2024 Spotlight

Policy summarization methods aim to showcase key examples of agent behaviors to their human users. Yet, existing methods produce “one-size-fits-all” summaries for a generic audience ahead of time. Drawing inspiration from research in pedagogy, we posit that personalized policy summaries can more effectively enhance user understanding. To evaluate this hypothesis, this paper presents and benchmarks a novel technique: Personalized Policy Summarization (PPS). PPS discerns a user’s mental model of the agent through a series of algorithmically generated questions and crafts customized policy summaries to enhance user understanding. Unlike existing methods, PPS actively engages with users to gauge their comprehension of the agent behavior, subsequently generating tailored explanations on the fly. Through a combination of numerical and human subject experiments, we confirm the utility of this personalized approach to explainable AI.

[Paper]

All publications