Yucan Wang

University of Science and Technology Beijing

Papers

Total Citations

H-Index

About

Yucan Wang is a robotics researcher focused on advancing robot learning and task generalization through imitation and demonstration. Their key research areas include dynamic movement primitives (DMPs), complex task decomposition, and adaptive robot control in obstacle-rich environments. Wang’s most notable contribution is a method for robots to learn from demonstration by breaking down complex tasks into reusable movement primitives, enabling generalization to novel, cluttered settings—a significant step toward more versatile autonomous systems. This work, detailed in their highly cited 2020 paper “Research and Implementation of Complex Task Based on DMP,” has garnered 4 citations and addresses a critical limitation in strategy learning: poor task versatility. By proposing a DMP-based framework that segments demonstrations into manageable components, Wang has helped bridge the gap between controlled lab learning and real-world application, where obstacles and variability are the norm. Their research holds promise for industrial and service robotics, where adaptable, safe task execution is paramount. Wang’s contributions underscore a commitment to making robot learning more practical and scalable, earning recognition among peers working at the intersection of imitation learning and dynamic systems.