Qingmeng Wen

Papers

Total Citations

H-Index

About

Qingmeng Wen is a rising researcher at the intersection of robotics, geometric modeling, and human-robot interaction. Their work focuses on two key areas: enabling robots to perform precise manipulation tasks through reinforcement learning, and developing advanced shape descriptors for robotic reasoning. Wen’s most notable contribution is the affordance-based human-robot interaction framework, which uses reinforcement learning to help robots plan and execute complex grasp-and-release operations in collaboration with humans—a challenging problem in modern robotics. This work has garnered 14 citations since 2023, reflecting its growing influence. More recently, Wen introduced GLSkeleton, a geometric Laplacian-based skeletonization method for object point clouds, which extracts intuitive curve skeletons that reveal topological properties of objects. This framework, already cited 5 times in 2024, shows promise for enhancing robotic perception and reasoning by bridging geometric modeling and practical robotics. Wen’s research elegantly combines theoretical rigor with applied problem-solving, making significant strides toward more capable and intuitive robotic systems. Their work is particularly relevant for students and researchers interested in manipulation, human-robot collaboration, and geometric computing.