Xiaoqiang Ren

Papers

Total Citations

H-Index

About

Xiaoqiang Ren is a robotics researcher whose work bridges state estimation and intelligent manipulation, advancing how autonomous systems perceive and interact with their environments. His key research areas include ultra-wideband (UWB)-based localization and deep reinforcement learning for robotic grasping. Ren’s major contribution to state estimation is demonstrating that UWB can serve as a stand-alone solution for planar pose estimation, effectively correcting long-term drift without the computational overhead of loop closure detection—a significant step toward simpler, more robust autonomous navigation. In manipulation, he has pioneered learning frameworks that unify goal-agnostic and goal-oriented grasping, a challenge that typically requires separate strategies. His Fast-Learning Grasping (FLG) framework, which integrates pre-grasping actions like pushing with Q-map masking, enables robots to efficiently handle cluttered scenes. With his most-cited work accumulating 19 citations and his 2023 paper on bifunctional push-grasping strategies earning 14 citations, Ren’s impact is growing rapidly. His work is notable for making robotic systems both more perceptually reliable and more dexterous, directly addressing practical challenges in real-world deployment.