FUDAN UNIVERSITY · ARTIFICIAL INTELLIGENCE
Hi, I’m Fanbo, a second-year AI student at Fudan University. I’m interested in embodied intelligence and how perception guides action.
Second-year undergraduate
Open to research & internship opportunities
Through SmartFly, I explore how multimodal information supports embodied behavior.
CURRENT INTEREST / 01
How can vision, odor, and wind support autonomous navigation? I explore reinforcement learning, recurrent memory, and hierarchical control in simulated fly flight.
SmartFly aims to support visual obstacle navigation and vision–odor source seeking with a single policy. Full navigation performance remains under evaluation.
CURRENT INTEREST / 02
Comparing CNN and FlyVis visual encoders to investigate how visual priors relate to representations and behavior in embodied tasks.
The project includes shared-stimulus, trajectory-level probing, and closed-loop evaluation workflows. The full comparison across training seeds is still pending.
An ongoing research project, from questions and implementation to traceable experiments.
Explore my GitHub ↗
Fly-inspired multimodal embodied navigation
A dual-task navigation framework in a MuJoCo fly simulation, combining visual obstacle navigation and vision–odor source seeking, with CNN–RNN and FlyVis–RNN encoder variants.
The project spans hierarchical PPO control, forest and dynamic odor environments, curriculum training, and representation analysis. CNN–RNN stabilization replays are available in both observation modes; the full navigation comparison is ongoing.
Problems encountered, lessons learned, and things worth keeping.
All notes ↗This is a home for my academic work and projects, and a personal space that will grow with me. Alongside technical work, I hope to share everyday observations and reflections.
More glimpses of everyday life to come.
Have a research or internship opportunity in mind, or simply want to talk about AI? I’d love to hear from you.