Abstract
This paper presents a two-layer controller for accurate and robust lateral path tracking control of highly automated vehicles. The upper-layer controller, which produces the front wheel steering angle, is implemented with a Linear Time-Varying MPC (LTV-MPC) whose prediction and control horizon are both optimized offline with particle swarm optimization (PSO) under varying working conditions. A constraint on the slip angle is imposed to prevent lateral forces from saturation to guarantee vehicle stability. The lower layer is a radial basis function neural network proportion-integral-derivative (RBFNN-PID) controller that generates electric current control signals executable by the steering motor to rapidly track the target steering angle. The nonlinear characteristics of the steering system are modeled and are identified on-line with the RBFNN so that the PID controller’s control parameters can be adjusted adaptively. The results of CarSim-Matlab/Simulink joint simulations show that the proposed hierarchical controller achieves a good level of path tracking accuracy while maintaining vehicle stability throughout the path tracking process, and is robust to dynamic changes in vehicle velocities and road adhesion coefficients.
Highlights
Despite significant advances made in recent years, highly or fully automated driving of vehicles remains challenging in arbitrarily complex environments, due to numerous non-trivial issues to be addressed, among which is the path tracking control [1]
To develop a path tracking controller that is robust to dynamic changes in working conditions and yet still benefits from the low computation burden with Linear Time-Varying Model predictive control (MPC) (LTV-MPC), a nonlinear tire model with a constraint imposed on the slip angle is incorporated into the prediction model in this study
With the aim to design a control strategy that is capable of handling the nonlinear time-varying (NTV) characteristics of the SBW system and outputs control signals that are executable by steering actuators, a RBFNN-PID controller is built as the lower-layer controller
Summary
Despite significant advances made in recent years, highly or fully automated driving of vehicles remains challenging in arbitrarily complex environments, due to numerous non-trivial issues to be addressed, among which is the path tracking control [1]. To develop a path tracking controller that is robust to dynamic changes in working conditions and yet still benefits from the low computation burden with LTV-MPC, a nonlinear tire model with a constraint imposed on the slip angle is incorporated into the prediction model in this study. This study proposes to optimize both parameters with regard to various vehicle speeds and road adhesion coefficients using the particle swarm optimization (PSO) algorithm Another major gap between previously proposed path tracking controllers and practical lateral control of autonomous vehicles is the absence of a precise model that depicts the nonlinear characteristics of the steering system. The nonlinearin prediction and the control horizonelectric of the LTV-MPC algorithm conditions characteristics of the steering system are identified on-line with the RBFNN, and the PID controller’s terms of vehicle velocities and road adhesion coefficients are optimized offline with PSO.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
