Xiang Teng

Papers

Total Citations

H-Index

About

Xiang Teng is a robotics researcher whose work sits at the intersection of machine learning, human-robot interaction, and motor skill acquisition. His research focuses on enabling robots to learn and generalize complex movements more efficiently, with particular emphasis on learning from demonstration (LfD) and reinforcement learning. Teng’s major contributions include developing novel frameworks for robot motor skill transfer that operate across multiple learning spaces, allowing robots to adapt previously acquired skills to new tasks with greater autonomy. His work on adaptive multi-task human-robot interaction, which incorporates human behavioral intention into Probabilistic Movement Primitives (ProMPs), has been cited 11 times and represents a significant step toward more intuitive collaboration between humans and machines. Additionally, Teng has advanced the field of policy improvement through compound heuristic information, proposing algorithms like PI2-CMA-KCCA that accelerate robot motor skill acquisition by discovering and leveraging implicit patterns in movement data. With over 26 citations across his most prominent works, Teng’s research is helping to bridge the gap between theoretical reinforcement learning and practical robotic applications, making him a rising contributor to the next generation of adaptive, collaborative robots.