A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive Dynami...

杨利霞

A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive

# U- f8 g7 R  {( f0 X" z

Dynamic Programming  

+ |% S# H7 w  L. N. ?, C
2 K  U, T/ w: h2 D' [
) G# X  a1 Q4 v) k1 R
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
0 X/ B2 ^& Y7 \9 l- O' ^is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
) ?6 D" q# j: w+ B8 d- e/ G9 ^/ dof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
! A6 {) M" ]0 D$ F9 Loptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
5 H7 `$ ^; J/ R% {( m/ KMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
controller for autonomous vehicles' system.
# j, `; i0 y& q' z% I* b
6 l/ z9 \, x6 _- Y; I