Junxing Zhang
Papers
4
Total Citations
71
H-Index
3
About
Junxing Zhang is a leading researcher in advanced robotics control, specializing in adaptive fault-tolerant systems, visual servoing, and intelligent optimization for robotic manipulators. His work addresses critical challenges in ensuring robot stability and performance under real-world constraints, such as actuator failures and full-state limitations. Zhang’s most influential contribution is the development of neural-based adaptive fixed-time prescribed performance control for flexible-joint robots, which guarantees rapid, precise motion even when actuators fail—a breakthrough with 24 citations since 2023. He also pioneered the use of unscented particle filters for online image Jacobian matrix estimation in uncalibrated visual servoing, enabling robots to accurately track targets without pre-calibration (23 citations). His adaptive finite-time fault-tolerant control for full-state-constrained manipulators (21 citations) further advances safety and reliability in constrained environments. Most recently, Zhang has integrated Q-learning with exponential distribution optimization to solve complex engineering design problems and robot path planning, demonstrating his versatility in merging machine learning with metaheuristic algorithms. With a growing citation impact and a focus on practical, robust solutions, Zhang is shaping the future of autonomous, fault-resilient robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4