| At present,with the rapid development of unmanned technology,the study of intelligent vehicle control system has vital theoretical and practical application significance.Aiming at the two main characteristics of intelligent vehicles,nonlinear and susceptible to external interference,in this thesis an intelligent vehicle direction control method based on fuzzy and sliding mode adaptive control is proposed to solve the problem of intelligent vehicle to identify paths and perform path tracking.In this thesis,the combination of image processing and trajectory tracking is used to achieve the accurate identification of lane lines by intelligent vehicles and the direction control on the lane lines.And the effectiveness of the proposed method is verified by simulation experiments.The main work in this thesis is as follows.The pre-processing of the target lane line image are carried out.Firstly,the image is extracted from the region of interest to obtain the information of useful lanes.A weighted median filtering algorithm is used to suppress and eliminate the noise of the target image while preserving the image detail features as much as possible.The overall or local characteristics of the image are purposefully emphasized using equalization and grayscale stretching to make the image features more straightforward.The inverse perspective transformation is performed on the pre-processed image to eliminate perspective errors.For the lane line detection,the traditional Canny algorithm is improved for lane line detection by using the eight-neighborhood model to calculate the gradient method.The simulation experimental results show that the performance of the eight-neighborhood Canny operator is improved better,and the improved Canny operator is highly accurate and adaptable,while the lane line using the four-neighborhood Canny operator is blurred.In addition,the traditional Otsu algorithm is improved by increasing the suspected foreground region to achieve multi-level threshold segmentation and adaptive selection of dual thresholds.In this thesis,the fuzzy sliding mode adaptive control method for intelligent vehicle direction control is proposed,and then the Matlab simulation experimental model is builded to verify the fuzzy sliding mode adaptive controller for intelligent vehicle.The simulation experimental results illustrate that the control performance of the proposed controller in this thesis is better,with high precision,fast response and smoother,which can ensure the intelligent vehicle to drive normally along the lane line,and prove that the fuzzy sliding mode controller can control intelligent vehicle effectively. |
