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.

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, we present the Intelligcnt Freight Train ID Recognition Systein (IFTIRS), which is a kind of Intcliigent Transportation Systcin (ITS). It can be used at any place along the railway. Rccognizing the ID, including the scrial number and configuration paramcters of the carriages, enable convenient and autornatic managcmcnt of frcight train systcm. The systcm constinution and workflow are introduced, and the technique of image acquisition, charactcrs location, isotation of each character, character rccognition and database monagcment are also addresscd in details, At the end of this paper, capability under practical condition shows the effeetivcness of our IFTIRS.

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.

It is very necessary for Autonomous Land Vehicle (ALV) to hove a reliable abiliiy of obstacle detection. Unlike srructural highway, environmems, where only vehicles ahead of the ALV are needed to consider, small obstacles are more ofien seen in semi-structural environments. In this paper we described a small obstacle detection qsrem for ALV under such ein.iroiiinenrs. The system consists of hvo 2D Laser Range Finders (LRE) which are responsible for obstacle recognizing and tracking respectively. For iop LRF. a D-S evidence riieon, based ousiacle recognition algorithm is used to distringuish the obstacles from rhe brushwood on the roadsides. Based on that. an obstacle tracking process ir sraricd bj, uillsing the data from borrom LRF. Besides the obstacles, the distribution of the brushwood on roadsides, which could be used,ior path planning. is also obtained. The experimenral results demonstrate our success.