|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive
|6 r- d5 W; s6 V uDynamic Programming * R" b' B$ Z: v
0 A& ~3 Q( {1 R6 r% m6 P2 y9 }- X+ u
' v C- x6 m, `% e
0 t! _# s8 J, f0 V) ]6 @* v1 ]( K5 }) O5 N# M T+ w8 S$ V
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency / {* b/ C) P+ ?1 w3 J5 j4 G
is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on / w* T$ t- H4 u% U) R7 p" p
the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
: W4 {1 b8 M5 C& X% j, S9 Mof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the3 k y- q, P+ D; X! c+ }1 J9 u
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using ! c5 p" Z/ Q D) U6 Z
Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth ' H* M- q6 S5 F i- B+ m
controller for autonomous vehicles' system. : d" |; P% E1 X; U) a
6 C b, W( P! \% D0 d4 B- d3 ?8 ]8 k. ?6 }* t% l; K$ @
| 
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
