Andrew Lee

Hello, I am a Ph.D. student advised by Prof. Iman Soltani at LARA, University of California, Davis.

As a researcher, I am passionate about bridging the gap between robotics and human behavior. Specifically, I am interested in (i) leveraging insights from human behavior for robust robot learning and (ii) developing human-like active perception strategies for robots.

Most recently, I have been exploring how Large Vision-Language Models (LVLMs) can be leveraged to guide robots in learning human-like behaviors.

I am actively looking for internship opportunities for 2025! If you are interested in my research, please feel free to reach out to me.

Education
  • University of California, Davis
    University of California, Davis
    Ph.D. in Computer Science
    May. 2023 - Present
    Advisor: Iman Soltani
  • University of California, Davis
    University of California, Davis
    M.S. in Computer Science
    Sep. 2021 - Apr. 2023 (transition to Ph.D.)
  • Hanyang University
    Hanyang University
    B.S. in Mechanical Engineering
    Feb. 2020
    Thesis: Compact Motor-Driven Walk-Support Device for Reducing Muscle Load
Awards
  • Computer Science Graduate Group Summer Ph.D. Fellowship, UC Davis
    2024
Media
News
  • Conference Our "Active Vision Might Be All You Need" paper got accepted at ICRA 2025! Hope to see you in Atlanta, USA!
    Jan. 2025
  • Media UC Davis College of Engineering News featured our work on AV-ALOHA! Check out the article
    Nov. 2024
  • Workshop Our "Active Vision Might Be All You Need" paper got accepted at CoRL 2024 Workshop
    Oct. 2024
  • Code We released the code and code (VR) for AV-ALOHA
    Oct. 2024
  • Conference Our "InterACT" paper got accepted at CoRL 2024
    Sep. 2024
Research
Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation
Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation

Ian Chuang*, Andrew Lee*, Dechen Gao, Iman Soltani (* equal contribution)

Workshop on Whole-body Control and Bimanual Manipulation @ CoRL 2024
International Conference on Robotics and Automation (ICRA) 2025

We introduce AV-ALOHA, a new bimanual teleoperation robot system that extends the ALOHA 2 robot system with Active Vision. This system provides an immersive teleoperation experience, with bimanual first-person control, enabling the operator to dynamically explore and search the scene and simultaneously interact with the environment. We conduct imitation learning experiments and our results show significant improvements over fixed cameras in tasks with limited visibility.

Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation

Ian Chuang*, Andrew Lee*, Dechen Gao, Iman Soltani (* equal contribution)

Workshop on Whole-body Control and Bimanual Manipulation @ CoRL 2024
International Conference on Robotics and Automation (ICRA) 2025

We introduce AV-ALOHA, a new bimanual teleoperation robot system that extends the ALOHA 2 robot system with Active Vision. This system provides an immersive teleoperation experience, with bimanual first-person control, enabling the operator to dynamically explore and search the scene and simultaneously interact with the environment. We conduct imitation learning experiments and our results show significant improvements over fixed cameras in tasks with limited visibility.

InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation
InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation

Andrew Lee, Ian Chuang, Ling-Yuan Chen, Iman Soltani

Conference on Robot Learning (CoRL) 2024

InterACT is an imitation learning model that captures and extracts inter-dependencies between dual-arm joint positions and visual inputs. By doing so, InterACT guides the two arms to perform bimanual tasks with precision—independently yet in seamless coordination.

InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation

Andrew Lee, Ian Chuang, Ling-Yuan Chen, Iman Soltani

Conference on Robot Learning (CoRL) 2024

InterACT is an imitation learning model that captures and extracts inter-dependencies between dual-arm joint positions and visual inputs. By doing so, InterACT guides the two arms to perform bimanual tasks with precision—independently yet in seamless coordination.

All publications