Fasheng Wang

Dalian Minzu University, Beijing Institute of Technology

Papers

Total Citations

H-Index

About

Fasheng Wang is a leading researcher in robotics and computer vision, with a primary focus on uncalibrated visual servoing and intelligent robot control. His most influential work, the 2019 paper "Unscented Particle Filter for Online Total Image Jacobian Matrix Estimation in Robot Visual Servoing" (23 citations), addresses a fundamental challenge in robotics: enabling robots to precisely control their motion using visual feedback without requiring complex camera calibration. Wang introduced an innovative unscented particle filter approach that dynamically estimates the image Jacobian matrix in real-time, significantly improving the robustness and adaptability of vision-based robot systems. In earlier foundational work (2006), he pioneered the use of neural network techniques for vision-based robot curve tracking—a critical capability for industrial applications such as automatic welding and incising. By eliminating the need for tedious calibration processes, Wang's neural network approach demonstrated how machine learning could simplify and enhance robot control in manufacturing environments. His research bridges the gap between theoretical estimation methods and practical robotic applications, offering elegant solutions to long-standing calibration challenges. With cumulative citations reflecting growing recognition, Wang's contributions continue to influence the development of more intelligent, self-calibrating robotic systems.