|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive
8 k* j" T& h8 w# j# O; @Dynamic Programming 6 f+ O" S2 S. T3 V) N
' Q4 _9 t" }3 M" p
2 p6 D/ [. V! ^% i, F' t2 s$ L
3 ^! V, A9 T% @# c, p: u$ _- ~; \
+ R& F. r( Y7 ]$ J( T; C$ S
& \( x- K3 {/ l+ k c
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency & `8 i, {) X% f: d
is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
2 f' X( H* A% w+ c- |, Wthe road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network % y: H& w/ ]* I/ W- h9 X% z
of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the) E% _. z! G/ _8 E+ f: z
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
% s( Y" D' v! e. O4 {& KMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
7 R4 V. Q( ^, _7 q: s" `controller for autonomous vehicles' system.
2 R7 h" i2 G7 B0 u J
' S5 j3 T2 z7 l- c) r" s' ?: L3 l* E* q. L+ M
| 
IP卡
狗仔卡
发表于 2020-11-12 16:35
转播
淘帖
分享
收藏
支持
反对
微信
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
抢沙发
显身卡
