Research

---

My main research interests are focused on physical AI, organized into four interconnected directions:

• Reliable Robot Learning We develop robust and efficient learning methods for manipulation and humanoid control, enabling robots to adapt to disturbances, learn from execution feedback, and operate reliably in dynamic environments.

• Human–Robot Interaction We study how robots can understand human intentions, attention, and natural instructions to collaborate effectively and recognize ambiguity or insufficient information.

• Multimodal Robot Perception We integrate vision, LiDAR, mmWave radar, WiFi, and other sensing modalities, allowing robots to understand humans, objects, and affordances in complex real-world environments.

• Physical Agents We connect foundation-model reasoning with physical environments, sensors, devices, and robots, enabling AI agents to perceive, reason, and act in the real world.

Our recent research is illustrated in MARS Lab Homepage.

---

Collaborations

I am interested in collaboration on the topics mentioned above. Apart from AI and IoT, I am also interested in AI-enabled interdisciplinary research, e.g., bioinformatics. Please drop me an email if you are interested in collaboration with a cool idea.