|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive 2 {5 m$ {/ F0 r' z1 b& f# T1 [8 c
Dynamic Programming - d/ D b; m7 u. p
* X* i; K; ^/ p
% j' ^- b% D' [% z
) L: S9 ^( ]9 b" g9 E& M4 K" a1 U
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
7 m7 \: c5 K! l0 `2 x5 S5 [is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
0 C6 y1 D3 ]; [, n/ ]1 ?the road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network ; d1 L6 q$ I+ c
of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the6 o2 X8 @1 T. N, ]0 T9 ]3 f
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
6 D' x) g |; a/ NMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth * {. z+ b; C$ @ \8 ~% f. F+ r
controller for autonomous vehicles' system.
- r8 m4 r- J3 v2 T. R5 L, T9 j7 @4 C3 X
& f2 ^! U0 j5 }5 ?; R |