|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive
6 E( {- y5 Q9 A) TDynamic Programming 6 m2 U( Z6 {2 ^$ O. F
; ]( B2 k: H" L" J" R/ o6 I1 s6 p- }- n. n! B2 h
) p. N( }% ?) M9 d# @9 Q- ?
2 O, g' m' g; E o. f9 M0 l1 C: r! |& E3 l
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency ) Q% j* a8 ]# O9 s9 M
is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
3 U9 s- Z* @( J$ |/ i; Z( b! @; `the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network ; l$ o/ v# S8 _7 e
of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
! P+ m5 {; C/ Joptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
- p# J- k1 Z# `' \6 j2 ~Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
8 \6 `) _+ J( `controller for autonomous vehicles' system. 0 g; I$ L! p$ x' T3 V
/ _) {/ H2 v% Z; l# c9 u; Q$ t
7 Z7 h1 B) e. f8 h3 J3 b |