•  
  •  
 

Journal of System Simulation

Abstract

Abstract: Aiming at the nonlinear, time-varying and uncertain characteristics of the longitudinal motion of autonomous vehicles, a Radial Basis Function neural network(RBFNN) Proportional Integral Derivative(PID) controller base on Particle Swarm Optimization(PSO) is designed. A RBFNN is integrated into a PID controller so that parameters of the PID controller could be adjusted self-adaptively. To solve the problem that poor selection of initial parameters of RBFNN and PID might lead to overshoot or instability in the control system, PSO is adopted to optimize aforementioned initial parameters off-line. Finally, a closed-loop adaptive control system model is built in MATLAB/Simulink. Simulation results show that as compared to the traditional PID controller and a non-optimized RBFNN-PID controller, the proposed PSO-RBFNN-PID controller demonstrates a higher level of controlling accuracy and stability of speed control under the New European Driving Cycle (NEDC) test.

First Page

409

Revised Date

2019-11-25

Last Page

420

CLC

TP391.9;U46

Recommended Citation

Yin Zhishuai, He Jiaxiong, Nie Linzhen, Guan Jiayi. Longitudinal Adaptive Control of Autonomous Vehicles Base on Optimization Algorithm[J]. Journal of System Simulation, 2021, 33(2): 409-420.

DOI

10.16182/j.issn1004731x.joss.19-0372

Share

COinS