Yang yunxiao

Papers

Total Citations

H-Index

About

Yunxiao Yang is a researcher focused on advancing reinforcement learning and deep neural network methods for autonomous robotic navigation and path planning. His most-cited work, "Path planning of mobile robot based on improved DDQN" (2021), tackles two critical challenges in deep Q-network algorithms—overestimation bias and sparse reward signals—by proposing the HER-DDQN algorithm. This approach integrates hindsight experience replay with a deep convolutional neural network that processes raw RGB images, enabling more efficient and reliable mobile robot path planning in complex environments. With 2 citations, this paper represents a targeted contribution to improving sample efficiency and stability in reinforcement learning for robotics. Yang’s research sits at the intersection of artificial intelligence, computer vision, and autonomous systems, addressing practical limitations in real-world robotic decision-making. His work is particularly relevant for students and researchers exploring deep reinforcement learning applications in robotics, offering a clear example of how algorithmic modifications can enhance performance in tasks requiring spatial awareness and sequential decision-making.