Zhenjie Hou

Papers

Total Citations

H-Index

About

Zhenjie Hou is a leading researcher in intelligent robotics and autonomous navigation, with a primary focus on deep reinforcement learning for path planning in complex environments. Their most influential work, "DM-DQN: Dueling Munchausen deep Q network for robot path planning" (2022), has garnered 49 citations and represents a significant breakthrough in collision-free mobile robot navigation. Hou's key contribution lies in enhancing the Munchausen deep Q-learning network (M-DQN) by integrating a scaled log-policy into the immediate reward structure, building upon Soft-DQN foundations to enable more robust decision-making for autonomous agents. This innovative approach addresses critical challenges in real-world robotic applications, allowing robots to learn optimal trajectories in dynamic, obstacle-rich settings. Beyond this flagship paper, Hou's research portfolio demonstrates a sustained commitment to advancing reinforcement learning algorithms for practical robotics, with their work serving as a foundational reference for subsequent studies in autonomous navigation. Their contributions continue to influence both academic research and industrial applications in intelligent transportation and service robotics, making Hou a notable figure in the intersection of machine learning and robotic control systems.