Hu Tianrun

About Me

I am a Research Engineer at the Smart System Institute (SSI), National University of Singapore, supervised by Prof. David Hsu. My research interests include robotics learning, manipulation, perception, planning, and Human Robot Interaction (HRI). Previously, I was an undergraduate in Computer Engineering at the College of Computing and Data Science (CCDS), Nanyang Technological University under the guidance of Prof. Lam Siew Kei.

Research Interests

My research spans several interconnected areas of robotics and artificial intelligence, focusing on enabling robots to learn generalizable behaviors and plan effectively under uncertainty, particularly by leveraging human guidance:

• Learning from Human Demonstration
  • Imitation learning and behavior cloning
  • Learning robust policies from imperfect demonstrations
• HRI (Human-Robot Interaction)
  • Intuitive teleoperation interfaces
  • Natural interaction paradigms for robot teaching
• TAMP (Task and Motion Planning)
  • Demonstration-aware planning algorithms
  • Integration of learned behaviors with classical planning
• Uncertainty Modeling in Environments and States
  • POMDP (Partially Observable Markov Decision Process) and decision-making
  • Efficient state representation from noisy observations and human demonstrations

My long-term research vision centers on developing demonstration-aware task and motion planning systems that are robust to real-world uncertainty. This involves creating robots that can effectively learn from human demonstrations while explicitly modeling the complexities and uncertainties of dynamic environments and internal states.