Papers
3
Total Citations
23
H-Index
3
About
Xin Ji Gan is a researcher specializing in the control and path tracking of mobile and car-like robots, with a particular focus on overcoming the real-time computational challenges of advanced control systems. His major contributions lie in the innovative application of model predictive control (MPC) and neural networks to improve robot navigation. Notably, his most cited work (13 citations) proposes a novel neural network control method that uses Nonlinear Model Predictive Control (NMPC) as a learning sample, effectively bypassing the poor real-time performance typically associated with NMPC while maintaining its constraint-handling capabilities. Gan has also advanced the field by developing an MPC-based path tracking method for non-global coordinate systems—critical for environments like underground mining and indoor spaces—and by introducing a motion compensation method to address actuator saturation in multi-constraint systems. Through these works, Gan demonstrates a clear trajectory of solving practical, real-world constraints in autonomous navigation, making his research highly relevant for students and engineers working on the intersection of control theory and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3