Kaixiang Peng
Papers
9
Total Citations
593
H-Index
8
About
Kaixiang Peng is a prominent researcher specializing in intelligent robotic control, fault diagnosis, and neural network-based adaptive systems. His work sits at the intersection of control theory, machine learning, and robotics, with a particular focus on making robotic systems more robust, reliable, and autonomous under real-world uncertainties. Peng's most influential contribution, "Adaptive Neural Control for Robotic Manipulators With Output Constraints and Uncertainties" (2018, 321 citations), established him as a leading voice in constrained adaptive control, employing barrier Lyapunov functions and Moore-Penrose pseudo-inverse techniques to ensure safe joint operation. Building on this foundation, his 2019 work on fault-tolerant control via fast terminal sliding mode (149 citations) demonstrated innovative use of Gaussian radial basis function neural networks to compensate for actuator failures in multi-link robotic systems. More recently, Peng has pioneered data-driven fault diagnosis, leveraging deep convolutional and residual neural networks to detect sensor and actuator anomalies in robot joints. His 2024 research extends his expertise into reinforcement learning-based optimal control for nonlinear systems, reflecting his evolving interests in intelligent autonomous decision-making. Across a career spanning over fifteen years, Peng's cumulative contributions have garnered nearly 600 citations, underscoring his sustained and meaningful impact on modern robotics research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Sensor and Actuator Fault Diagnosis for Robot Joint Based on Deep CNN49 citations · 2021
- 4Deep residual neural-network-based robot joint fault diagnosis method17 citations · 2022
- 5
- 6
- 7
- 8Robot Obstacle Avoidance based on an Improved Ant Colony Algorithm9 citations · 2009
- 9Robot visual servo control based on fuzzy adaptive PID8 citations · 2012