Map matching is a type of popular localization approaches for mobile robot autonomous navigation in indoor environment. Global localization is to fmd the best correspondence between current local map and the global map. Local map and global map are represented with comer points that are sorted counterclockwise. Relative position relation of comer points is computed in local and global map and used to search matched pairs. Map matching based on ordinal map improves the searchmg efficiency. Map matching based on relative position relation avoids frequent coordinates transformation. All these techniques have been implemented on our mobile robot ATRVII equipped with 2D laser range scanner SICK.

A novel preprocessing and localization method has been proposed for container auto recognition system. The method combines both linerar filters and nonlinera filters to reducs noises on an image. Selection method of the adaptive parameter of the filters in discussde thoroughly. Tests have been made based on the mehod, Character Lines can be properly located with a ratio of above 98%.

In this paper, a new method of initial localization for a mobile robot only employing a laser range finder is proposed. We accomplish this by the matching of "Complete Line Segments (CLS)" derived from current scan of range finder and the priori-map. The definition of "Complete Line Segments (CLS)" and "Sub-Complete Line Segments (SLS)" as well as their properties and decision rules are given. We confirm that, in the angle of theory, the initial localization can be accompli shed even if only one pair of CLS can be matched exactly since the CLS represent some basic but complete features of the environment. So compare with other ways, this method has simpler principle and can easily be implemented with less computational costs. The whole process of initial localization for a mobile robot is described in detail. At last promising real-world experiments involving the initial localization modules on our ATRV2 mobile robot are described.

The paper presents the improvement and enhancement to the existing video based traffic detecting system. The works are concentrated on the acquiring and update of background image, a new solution to segmentation of vehicles from the background and adding peripheral interfaces. The simulation and experimental results are effective.

method of map bullding for indoor envlronment is prescntcd. It is based on adaptive clustering and welghted averaging, Different threshold valuc Is sclccted to cluster these sompling points at different posltion. Clastering with varlant threshold is more reasonable than It with constant threshold. Line segments are extracted from these sampling polnts and are used to approximate the shape of environment, Parametcrs of llne segment are computed with a welght vector. Line segmcnts in envlronmental map are arrangcd according to their geometric posilion relation. This type of map is more accurate and more useful for mobile rohot navigation. All there technlques have been implemented on our mobllc robot ATRVII equipped with 2D laser range scanner SICK.