Max Robotics — Global Service Robot Directory + US Certification

About

Shile Li is a robotics and computer vision researcher whose work spans visual odometry, robot learning from demonstration, and scene understanding for autonomous systems. His most widely recognized contribution is a fast visual odometry method leveraging an intensity-assisted Iterative Closest Point (ICP) algorithm for RGB-D cameras, which has garnered 34 citations and demonstrated meaningful efficiency gains over conventional ICP approaches — a foundational tool for mobile robotics and autonomous navigation. Beyond localization, Li has made notable strides in robot learning, developing frameworks that enable dexterous robotic hands to mimic human hand motion through low-cost, demonstration-based pipelines. His work on semantic skill extraction from hand pose observations further advances the field of task programming, allowing robots to learn complex manipulation tasks directly from human visual demonstrations. More recently, Li has tackled practical challenges in stereo vision calibration for real-world autonomous vehicles and explored deep learning-driven global visual localization using implicit scene geometry. With a research portfolio bridging perception, manipulation, and learning, Li's contributions address core challenges in making robots more capable, adaptable, and deployable across real-world environments.