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

Dynamic Programming

* V& O/ d. M/ W' v) e! l


& B! I/ B; Y$ o$ X& [( i, @. X

A novel steering controller for autonomous vehicles is proposed in this paper. For autonomous vehicles, the efficiency
2 ?3 i* M" U% `2 |) }0 \, Uis an important indicator, in order to reduce the training cost and improve the real-time performance while the car is running on
! X5 X' r) P  L5 ^7 Z1 Lthe road, Offline plus online training is proposed in this paper. Offline plus online training is presented to build a model network
5 {- r, A* W6 s# u' Bof vehicle steering and correct it in real time. Then we adopt a policy iteration adaptive dynamic programming (ADP) to get the
optimal control law and deploy it to autonomous vehicles. Eventually, the performance of the controller was evaluated using
! E/ \: e- e' h2 H2 ?* Y! f: `Matlab simulation. Results verify the feasibility of the theory and show the steering controller is one kind of effective, smooth
controller for autonomous vehicles' system.
% p( q) N+ i$ l' I0 a8 b8 Q