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

5 H/ w7 k' X1 F, b" I3 r

Dynamic Programming

0 C8 d7 z$ Q5 ~$ z  z0 R4 x* }
) P9 w; v1 E7 v" Q
7 u& m6 i7 s2 {9 H
. j4 r( l& ^: v8 r

+ F. C8 P6 `; j% C! i6 aA novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
3 N  \0 G2 M' p. y  @/ Tis 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
5 g- x! K# g3 ?5 {0 x1 u5 [of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
/ v' u: Q. E% I4 T% \! qoptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
1 Y- I2 w) t: q: R  ^6 N. lMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
controller for autonomous vehicles' system.
. \, y& j- q# L6 K  H

2 R5 `( b! f  p0 Y9 c