Building robots that navigate the open world — without a map.
PhD candidate in Computer Science at the National University of Singapore, advised by Harold Soh. In my “first life” I was a serial entrepreneur (one startup acquired) and spent a gap year at Oxford studying theology and philosophy. Now I build AI and robotics systems for spatial perception and mapping, long-term robot memory, autonomous navigation, and manipulation.
Champion · 1st place
2026
Won the inaugural challenge with an end-to-end robot learning and deployment system — through simulation, real-robot rounds, and an on-site physical-robot final. Team NUS-CLEAR: Jiaming Wang, Jizhuo Chen, Diwen Liu; advisor Harold Soh.
Led the GeNIE autonomous navigation system: low-cost rovers operated remotely across real-world environments in seven countries, navigating with just an RGB camera and noisy GPS.
Robots that leave the lab: perceiving, remembering, and acting in places they have never seen.
Maps and memories that stay reliable as the world changes — topological mapping that relocalizes under perceptual aliasing, reasoning over pose hypotheses in continuous SE(3), and memory matched to the timescale of the task so robots can act on what they saw minutes, hours, or days ago.
Map-free navigation that survives the real world — deployed across seven countries — plus social navigation among people and language-guided navigation.
Learning manipulation from real-robot data and deploying it reliably on physical robots — from task-oriented grasping and mobile base placement to uncertainty-aware trajectory diffusion.
Robots as agents that reason, plan, and improve themselves — using world models to imagine outcomes and agentic optimization to search for better behavior, instead of relying on a single fixed policy.
Open-world robot navigation, robustness of foundation-model-based navigation systems, failure detection and recovery, and navigation benchmarks.
Social navigation, human–robot interaction, dynamic crowd understanding, robot planning, evaluation, and real-world deployment.
I'm actively looking for motivated students to work on cutting-edge problems in robot navigation and embodied AI in general. My research has won two international robotics challenges at ICRA and two Best Paper Awards at IROS workshops. I approach research with an entrepreneurial mindset—prioritizing rapid prototyping, real-world deployment, and practical impact.
My past students have gone on to excellent opportunities, including PhD offers from CUHK and NUS, as well as collaborations with leading research groups. I emphasize hands-on mentorship, giving students real ownership of projects and fostering both technical depth and independent thinking.