In research areas of agents, it is a problem to evaluate the behavior of multi agent systems. Because agents' behavior is influenced with the environment of the agents. The evaluation depends on the environment of agents. So, we need to clear a relation between the environment and agents, in order to evaluate agents' behavior based on situations of the environment. In a previous research, we analyze some relations between an evaluation of agents and features of a map as an environment. And we defined indexes that show features of map. In this research, we predict an evaluation of agents using the defined indexes. Furthermore, we consider accuracy of the prediction using the indexes.

We propose protocol and system of map creating and information sharing for mobile robots. The system we propose can saveng data from sensor such as laser rangefinder on mobile robot and create map by providing user defined coordinate reference system translations.

We propose an algorithm to extract sidewalk regions and recognize components of sidewalk border, width of sidewalk, and existence of bottleneck points and opening points from outdoor road images obtained from a stereo vision camera mounted on a low-speed vehicle. The elevation map is constructed by removing noises from the inputted stereo images. The probability that each point belongs to the sidewalk border is calculated from the map, and the closed loop that is considered to be corresponding to the sidewalk border is extracted. Then, the type (such as curb and wall) of border component is determined. The sidewalk attributes such as width, components of borderline, presence of bottleneck point, and opening point are obtained by integrating these results among a series of inputted images. We applied this algorithm to the images obtained from a low-speed, outdoor vehicle (based on a commercial electric scooter) and calculated its efficiency.