|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive $ |; r8 I% s0 y6 C
Dynamic Programming $ B. }$ {; l2 k6 v# j! o0 d
0 e4 i6 q2 |" b9 c$ Y% G8 x( q( s# p
7 U7 X5 Z( a( r0 L3 _( H; ?( I0 V
/ s! ~3 N ]- V: n, X& B! w/ P6 o$ P* X2 q
. A; [' K2 e: t/ e# V$ C0 c: i
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
! \- u& m; d1 pis an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
! e5 f, {7 X- ^ c9 `the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network 7 f" }% V8 Y$ {$ D y; I4 h
of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the, ~% ?8 W& l0 r& B( [; }
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using % X& C. Z% T7 s4 ]1 U; E) ?! p
Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
+ @) H& s, I9 J& d }controller for autonomous vehicles' system.
' [- B4 L1 f6 @. L: ?# o" W0 h/ L% Q
$ W; Z5 b2 N% ? | 
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
