SILS를 이용한 Lane Keeping Control 시스템의 성능평가

This study propose an Perception-Action Network (PAN) to estimate the vehicle pose parameters and control the vehicle motion for keeping the vehicle within given lane. The vehicle pose and the road curvature were calculated by geometrically fusing sensor data from camera image, tachometer and steering wheel encoder though the Perception Net, where not only the state variables, but also the corresponding uncertainties were propagated in forward and backward direction in such a way to satisfy the given constraint condition, maintain consistency, reduce the uncertainties, and guarantee robustness. The objective of the lane keeping control is to reduce a predicted tracking error of the vehicle, while the vehicle is traveling along the given lane. In this study, we calculated a required steering angle at the auction module of PAN. A series of experiments was conducted to evaluate the control performance, in which commercial software was utilized to quit unwanted safety problem.