Hongxu Zhang

Papers

Total Citations

H-Index

About

Hongxu Zhang is a leading researcher in intelligent robotics and deep reinforcement learning, with a primary focus on advancing robot manipulation and autonomous grasping systems. His most influential work, "Robot grasping method optimization using improved deep deterministic policy gradient algorithm of deep reinforcement learning" (2021, 26 citations), addresses a critical bottleneck in robotics: the inefficiency of traditional target detection algorithms for grasping tasks. By enhancing the deep deterministic policy gradient (DDPG) algorithm, Zhang developed a more adaptive and efficient framework that enables robots to learn optimal grasping strategies through trial-and-error interaction with their environment, significantly improving both speed and accuracy in real-world applications. This contribution has been widely recognized as a key step toward more autonomous and dexterous robotic systems, particularly in industrial automation and service robotics. Zhang’s research bridges the gap between theoretical reinforcement learning advances and practical robotic control, demonstrating how improved policy optimization can directly enhance hardware performance. His work continues to influence subsequent studies in robot learning, making him a notable figure in the intersection of artificial intelligence and robotics engineering.