|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive : O4 R* r6 }% o( S. f& [' ^
Dynamic Programming
; W! z7 H+ j' ?. j$ `5 S. E* B+ T( {; [. X' x& l
* F3 }) w3 Y' f
g. u+ R: N; {* o% |# ^; P: Z5 N5 T2 H: Q! \
' u$ Y! q( D; Z6 G( KA novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
" s( h' g3 H @7 ~is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on 4 B; W8 S( T$ ]' d6 v! V
the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
/ s7 Q( ]. b! x8 @- ?& D8 {of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the, ~2 Q# _+ r$ W% b
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using 0 |1 z$ w! l- u2 h$ [* P6 b( o
Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth 4 @" p9 I _: O3 J! ?% {
controller for autonomous vehicles' system. 6 F; n" m, T0 x# ]; r( z& Q
& O3 y' _/ \- P! [
7 X9 l0 S" z* I# {2 g7 N
|