Joined ASU Interactive Robotics Lab
Beginning doctoral research on robot learning, in-context adaptation, reinforcement learning, and embodied AI systems.
About Me
Hsiang “Sean” Fu
Computer Science Ph.D. student at Arizona State University, building learning-driven robotics systems that perceive, adapt, and collaborate in real-world environments.
- Role
- Computer Science Ph.D. Student
- Lab
- Interactive Robotics Laboratory @ ASU
- Research areas
- Robotics, In-Context Learning, Reward Models, Agentic AI, Reinforcement Learning
What my work focuses on
My work explores how learning-based methods can help robots perceive, reason, adapt, and collaborate in complex environments. I am especially interested in algorithms that fuse machine learning, human-centered design, and embodied intelligence.
Before ASU, I completed a B.S. in Informatics with a specialization in Human-Centered Data Science at the University of Texas at Austin. Projects in reinforcement learning, multimodal systems, human-AI interaction, and applied machine learning shaped the way I think about useful intelligent systems.
News + Highlights
Learning from messy real-world data
Exploring methods that help robots generalize from demonstrations, multimodal context, and changing human goals.
Publications and projects are live
Browse recent research outputs, applied machine learning systems, robotics experiments, and project notes.
What I'm currently working on
I’m focusing on learning-driven robotics systems that can adapt from examples, respond to human intent, and stay useful in messy real-world settings.
Embodied Learning
Learning policies from demonstration-rich data
Robots should turn examples into behavior that survives contact with noisy environments, incomplete instructions, and changing human goals.
Learning from Demonstrations
Turning examples and large-scale data into policies that transfer beyond scripted settings.
Human-Robot Collaboration
Designing interaction loops where robots can adapt to people, intent, and context.
Policy Optimization
Studying reinforcement learning and decision-making under noisy, changing constraints.
Multimodal Robot AI
Using generative and multimodal models for perception, control, and real-time adaptation.
Academic Timeline
Arizona State University
Graduate research in the Interactive Robotics Lab, exploring in-context learning, reinforcement learning, and embodied AI systems.
University of Texas at Austin
B.S. in Informatics, Human-Centered Data Science, with projects across applied ML and human-AI interaction.
Industry and Applied Systems
Experience in cybersecurity, analytics, automation, product testing, and data pipelines.
Let’s connect