Yongxiong Wang

University of Shanghai for Science and Technology, Shanghai Jiao Tong University

Papers

Total Citations

177

H-Index

About

Dr. Yongxiong Wang is a leading researcher in intelligent robotics and computer vision, with a primary focus on autonomous navigation and anomaly detection. His most influential work, "Path Planning via an Improved DQN-Based Learning Policy" (2019), has garnered 149 citations and represents a breakthrough in applying deep reinforcement learning to robotic navigation. By enhancing Deep Q-Network algorithms, Wang developed a framework that enables robots to learn optimal paths through experience, mimicking human skill acquisition—a critical advancement for autonomous systems operating in complex, dynamic environments. Wang has also made significant contributions to visual anomaly detection, pioneering probabilistic and ensemble methods to address the challenge of imbalanced data in robot vision systems. His 2016 probabilistic framework and ensemble detection approach, while less cited, laid essential groundwork for robust inspection technologies. Earlier in his career, Wang developed a rapid cascade condition assessment system for ductwork using robot vision, demonstrating his long-standing commitment to practical, real-world applications. His work bridges the gap between theoretical reinforcement learning and deployable robotic intelligence, making him a key figure in the evolution of autonomous navigation and industrial inspection.