|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive
g# p6 W. c1 zDynamic Programming
9 w" ^& {9 J+ B3 c5 e! a9 W1 ]+ k& u
* ^" }$ V% R+ I+ [+ D" o7 _; s" w
( O9 Y/ o4 W2 X/ s; d2 o( n+ E# ]
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency , E$ Z6 a) u; r/ `
is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on " g5 `; {4 V: [1 _, S/ O4 A
the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
+ ?' x2 G! R a; Rof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
2 r7 d2 y# h' K/ e+ f2 \( A/ Coptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
: N* o5 u+ J# J/ a, ~( VMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
; y1 J+ [4 s. G) vcontroller for autonomous vehicles' system.
9 @% u# J2 M% `5 u i' Q, O H/ e! T
* M0 Y6 q' w- X+ u- q$ s9 c8 j9 ~2 R% J/ ]/ @2 o1 y
|