Xiaowen Yang

Papers

Total Citations

H-Index

About

Xiaowen Yang is a robotics researcher whose work bridges reinforcement learning, grasp pose estimation, and lightweight robotic manipulation. Yang’s most-cited paper, "Reinforcement learning path planning method incorporating multi-step Hindsight Experience Replay for lightweight robots" (2024, 5 citations), introduces a novel approach that enhances sample efficiency in robotic path planning—critical for deploying agile, low-inertia robots in dynamic environments. Another key contribution, "6-DoF grasp pose estimation based on instance reconstruction" (2023, 4 citations), advances robotic dexterity by enabling precise six-degree-of-freedom grasping through object instance reconstruction, a fundamental challenge in industrial and service robotics. Though early in their career, Yang’s work has already garnered attention for its practical focus on improving robot autonomy and manipulation accuracy. By integrating hindsight replay mechanisms with reinforcement learning, Yang addresses the long-standing difficulty of sparse reward signals in real-world robotic tasks. Their research holds promise for applications in manufacturing, logistics, and assistive robotics, where lightweight, adaptive systems are increasingly vital. Yang’s trajectory signals a rising contributor to the intersection of learning-based control and physical robot interaction.