The tangential angle acquisition of the traditional geometric path tracking algorithm depends on high precision inertial navigation equipments. In order to solve the problem, a new path tracking algorithm based on cubic B-spline curve fitting was proposed. Firstly, the smooth path was generated by fitting the discrete path points in the priori map. Then, the discrete path points were regenerated by using an interpolation method according to the path equation, and the tangential angle at each point was calculated to realize the optimization and tracking of the multi-sensor fusion path. On the real intelligent vehicle experiment platform, the 20 km/h low-speed-circle and the 60 km/h high-speed-straight-path tracking tests for the proposed algorithm were carried out under the two real road scenes. Under the two typical test scenarios of low-speed-large-curvature and high-speed-straight-path, the maximum lateral error of path tracking of the proposed algorithm is kept within 0.3 m. The experimental results show that, the proposed algorithm can effectively solve the problem of traditional geometric path tracking algorithm's dependence on inertial navigation device, and maintain good tracking performance at the same time.

Aiming at the characteristics of high dimension and complexity of gastric mucosal tumor cell images, a new method based on Fisher Discrimination Dictionary Learning and Regularized Robust Coding (FDDL-RRC) was proposed for the recognition of tumor cell images, so as to improve the robustness of sparse representation for image recognition. Firstly, all the original stained tumor cell images were transformed into gray images, and then the Fisher discrimination dictionary learning method was used to learn the global features of training samples and obtain the structured dictionary with class labels; lastly, the new discriminative dictionary was used to classify the test samples by the model of RRC. The model of RRC was based on Maximum A Posterior (MAP) estimation, and the sparse fidelity was expressed by the MAP function of residuals, so the problem of identification was converted to the optimal regularized weighted norm approximation problem. The highest recognition accuracy rate of the proposed method for tumor cell images can reach 92.4%, which indicates that the presented method can effectively and quickly distinguish the tumor cell images.