A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive " z8 Z( V3 I" ^ y5 Y& ?. d v
Dynamic Programming
5 \0 i9 f- ^' l$ K5 ^3 h/ S" X
! \, S1 w. ]! F( Z" ~5 d* \- f, L2 F& R8 h) l
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
4 V4 A) M8 T. M7 U$ iis an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
- {1 U" n2 s: Z) Qthe road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
( { Q: k7 q- u* V& P, Uof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
~" x% G! a7 g2 ^( Soptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
8 G9 A0 O, G. ]( s2 t0 m( C2 ?9 V- eMatlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
& [' w: h: l# h1 i) ^controller for autonomous vehicles' system.
( K0 r8 e$ M$ ^3 P" F+ y
9 H6 f: V. e; ^$ X+ u5 e0 m+ K( D: \8 W1 ]0 I; B
|