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

0 x9 ~8 X3 u" T

Dynamic Programming

: r- H; o  ^, j
. A" y/ S" N: y: O+ n* F


! U1 d) ?5 D7 u3 j  P4 b
1 l) E3 N: D9 n6 U4 UA novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
. r0 o% n. F; yis 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
! J+ |: \" x/ T: a# C  _: |& p- nof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
2 v; i0 T9 z' W3 }6 A/ `optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
5 M0 R( g5 Z7 W2 j4 YMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
. G1 b3 U0 P' {controller for autonomous vehicles' system.
) q$ O) X4 U0 Z; O3 V/ t& i4 m+ x2 Q