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

2 R$ t9 d7 L0 l( K2 Y  N/ q

Dynamic Programming

, D+ u7 v7 a( `( }9 W% [" w
$ a8 D# Z% J# X, L/ q/ `1 }


4 t3 W( ~  d! @3 y% g6 H6 R7 J; N
3 O) b: J0 }- ^) }! X/ C( uA novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
" X; k- e% F! C% b& Pis an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
9 d* t4 L5 E+ y' J/ n' `the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
- Z' B% K* f& v5 Yof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
6 w$ g4 P" |7 h9 J0 B; m, ioptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
/ C+ h. m' |9 D& G! [; ^Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
! Z7 k2 a" B$ ]# r$ Fcontroller for autonomous vehicles' system.