Intelligent vehicle (IV) is one of the core components of Intelligent Transportation System. From the view of pattern-covering & embedding, the robust improvement mechanism of noise-add is described, and then the controller design method based on noise-add is presented. Fuzzy logic is applied to partition and cover vehicle motion pattern space. The controller's ability to cover and embed vehicle motion patterns is improved by adding noise in the design. Thus the robustness of the control system is enhanced. Simulation results show the designed controller can adapt to non-linear structure with time-variant parameters and measure noise.

Based on analyzing the pure geometry and possibility statistics map matching algorithms, a hybrid map matching algorithm based on fuzzy comprehensive judgment is proposed by synthesizing the merits of two methods and the topology relation of the real road network, and using the concept of the fuzzy theory. The simulation results show the new algorithm can provide more reasonable matched result for vehicle positioning information.

A kind of second2order algorithm---recursive approximate Newton algorithm was given by Karayian2 nis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi2layer feed2forward neural networks, the second2order back2propagation recursive algorithm based generalized costcriteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second2order convergent rate. The performance and application prospect are analyzed. Lots of simulation ex2periments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multi2ple algorithm. The algorithm and selection of networks parameters are significant and the performance is more ex2cellent than BP algorithm and the second2order learning algorithm that was given by Karayiannis.

There exist some flaws in current intelligent vehicle lateral controller design methods. Aim at the flaws, a new kind of robust design method was proposed. In the new method, longitudinal velocity, cornering stiffness of the tires, time constant of steering actor and path's effects on vehicle lateral dynamic pattern were fully considered. Fuzzy logic was used as control strategy. Key parameters, that can exert dominant on vehicle lateral dynamics, were reasonably selected to produce design pattern, which is more complete and has more dynamics information than real pattern. GA was used to automatically search and optimize fuzzy logical controller under the design pattern. The simulations show that the new method is effective.

A practical route planning algorithm for vehicle navigation system is proposed in this paper. the shortest path algorithm with the restricted searching area. The algorithm takes advantage of the adjacent list data structure and the mechanism of restricted searching area, that is, the algorithm uses the spatial distribution feature of the real road network to restrict the searching area in reason. Finally, combining with its practical application in Real-Time Vehicle Navigation System (RTVNS), one example is given, the analysis in theory and the experimental results show that compared with the Dijkstra algorithm, the new algorithm can greatly approve the searching speed, and satisfy the needs of RTVNS.