Model Free Trajectory Tracking Control of Nonlinear Unmanned Vehicles

This paper investigates the trajectory tracking control problem for nonlinear unmanned vehicles. Traditional control approaches often depend heavily on the system's dynamic information. To mitigate this reliance, a data-driven trajectory tracking control scheme is proposed. First, dynamic linearization techniques are employed to establish a data-driven model for unmanned vehicles, while real-time dynamic information is estimated through adaptive strategies. The iterative learning framework leverages the system's repetitive task characteristics to enhance algorithm performance. Subsequently, convergence analysis of the control algorithm is conducted based on the principle of compressed mapping. Simulation experiments validate the effectiveness of the proposed approach. A key feature of this design is its ability to achieve precise trajectory tracking using only system input-output data, eliminating the need for explicit dynamic modeling.