Xiaowei Xing

Korea Advanced Institute of Science and Technology

Papers

Total Citations

H-Index

About

Xiaowei Xing is a robotics researcher specializing in deep reinforcement learning for autonomous navigation and robotic manipulation. Her work focuses on developing intelligent control systems that enable mobile robots and robotic arms to operate effectively in complex environments. In her most cited paper, "GRU-Attention based TD3 Network for Mobile Robot Navigation" (2022, 19 citations), she introduced a novel goal-oriented navigation framework that integrates gated recurrent units and attention mechanisms with the Twin Delayed DDPG algorithm, using lidar data and target-relative state inputs to achieve robust, continuous control. This work addresses critical challenges in sample efficiency and decision-making for autonomous robots. Her earlier research, "Deep Reinforcement Learning Based Robot Arm Manipulation with Efficient Training Data through Simulation" (2019, 6 citations), proposed an adaptive replay buffer update strategy to accelerate training for suction tasks in simulated environments, reducing the data burden of reinforcement learning. Xing’s contributions are particularly valuable for bridging simulation-to-reality transfer in robotics, offering practical solutions for deploying learned policies in real-world applications. Her work continues to influence researchers exploring attention-based architectures and efficient training paradigms in robot learning.