Yusen Xie

Papers

Total Citations

H-Index

About

Yusen Xie is a robotics researcher whose work bridges the critical gap between perception and motion planning for autonomous manipulation. His primary research areas include trajectory optimization, collision avoidance, and robotic grasping, with a focus on enabling robots to operate safely and efficiently in cluttered, real-world environments. In his most impactful work, "Collision-Free Trajectory Optimization in Cluttered Environments Using Sums-of-Squares Programming" (2024, 9 citations), Xie introduced a novel approach that represents robot geometry as a semialgebraic set defined by polynomial inequalities. This allows robots with complex, non-spherical shapes to navigate tight spaces while provably avoiding collisions—a significant advance over traditional methods that rely on conservative approximations. His earlier work, "RGB-D Instance Segmentation-based Suction Point Detection for Grasping" (2022, 4 citations), tackled the practical challenge of industrial pick-and-place by developing a learning-based method to evaluate optimal suction positions on objects of arbitrary shape. By integrating instance segmentation with suction point evaluation, Xie’s approach improves the reliability and stability of robotic grasping in manufacturing settings. His contributions are shaping the future of autonomous robotics, from warehouse automation to assistive technologies.