|
A Novel Steering Control for Real Autonomous Vehicles via PI Adaptive % p) i8 S+ J1 W* @8 r2 D$ L" M- Q
Dynamic Programming
9 T3 g9 F/ N& \
8 l/ [6 H* ]* j: h
8 B/ l/ I2 B( C" _; C( i' W# N3 s, j# b, ~, b/ P( X
A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency # d2 f1 @& ~7 ^
is an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
0 A/ d, _, A! H: C) d7 rthe road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network 1 G$ T r r+ J" v1 R+ c) |4 P0 I( M
of vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
& \4 s5 J1 D/ [$ L7 uoptimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using / n) M- [, T/ \- |0 A
Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
; z+ g4 U4 C- `' Pcontroller for autonomous vehicles' system. y2 S, s, e, ?3 [* q4 o
3 g' ]: R; u, A1 g4 f' m$ ~+ C+ ?
, _3 T5 G1 x' H: p6 I- X
|