Tianwei Ni

Hohai University, Mila - Quebec Artificial Intelligence Institute

Papers

Total Citations

H-Index

About

Tianwei Ni is a researcher at the forefront of robotics and artificial intelligence, with a primary focus on imitation learning, reinforcement learning, and motion control. His work addresses fundamental challenges in enabling robots to learn complex behaviors from demonstration and operate effectively in real-world environments. Ni’s most influential contribution is the 2020 paper "f-IRL: Inverse Reinforcement Learning via State Marginal Matching," which introduces a novel method for learning reward functions by aligning the agent’s state distribution with that of an expert. This approach has garnered 4 citations and provides a powerful framework for robotic tasks where explicit programming or cost specification is impractical. Earlier in his career, Ni explored motion control for soccer robots, publishing "Research on Optimized Motion Control of Soccer Robot Based on Fuzzy-PID Control" (2018, 3 citations), which tackled the nonlinear and uncertain dynamics of vision-based robotic systems. More recently, his 2023 work "Towards Disturbance-Free Visual Mobile Manipulation" (2 citations) advances deep reinforcement learning for embodied agents, emphasizing robustness over speed in visual navigation and manipulation tasks. Ni’s research consistently bridges theoretical innovation with practical robotic applications, making him a notable contributor to the field of intelligent robotics.