Search

This paper describes the RGB depth (RGB-D) map building for mobile robots based on accurate outdoor localization and perception sensors consisting of wheel odometer, global positioning system (GPS), and camera and laser range finder (LRF). A localization method based on Particle Filter (PF) is used to integrate the sensor data and the topological map. The sensors data include geo-locations, the relative moving positions and the traffic mark positions measured by GPS, odometer and camera. The topological map has information for converting domains between geo- and metric- locations of GPS and odometer. And it also gives the actual positions of traffic marks extracted from aerial or satellite images. In addition, we used also a 2D RGB-D map building method by matching information between RGB and depth by camera and LRF at estimated position from PF. An experiment has been performed in outdoor environment to validate the proposed method. Experimental results show the high accuracy RGB-D map that is able to use for navigation of mobile robot in outdoor environments. [ABSTRACT FROM PUBLISHER]

This paper presents an efficient method for building a topological map for robots in urban environments based on satellite image maps acquired from a geographic information system (GIS). In urban space, mobile robots need a special map, such as a topological map, to generate a path toward their goal. A topological map for mobile robot navigation should include semantic data, e.g., the width and type of road. We divide the satellite image based topological map building process into two steps. The first step is defining the topological map model to fit the mobile robot navigation in an urban environment. The second step is generating a topological map from existing satellite image maps downloaded from the GIS to reduce the cost and improve the accuracy in building the map. If a GIS-based topological map is constructed once, it is possible to use the map for the navigation of various robots as common spatial data. To validate the proposed mapping method, we show details of its implementation in map building as well as in a navigation experiment in real outdoor environments, such as a campus or city district. [ABSTRACT FROM PUBLISHER]

This paper presents the navigation technique for service mobile robots in large scale environment using artificial landmark. The robot navigation is comprised of three major components; localization, mapping, and path planning. To implement the stable navigation system of mobile robots, many developers could use the artificial landmark to measure the accurate position of robot in large scale environment. When the mobile robots obtains the position based on the artificial landmark, they need to have the map which contains information about the positions of artificial landmarks. In this paper, Grid-based Simultaneous Localization And Mapping (Grid SLAM) method is employed to construct the map of artificial landmark using a specially made mapping cart. The artificial landmark map has been used for the real operation of four kinds of robots; patrol, guidance, delivery, cafeteria serving, relying on the artificial landmark map for their navigation at the large scale indoor environment named Tomorrow City (T-City) where the artificial landmark system is installed for the robotic technologies. The implementation results show that it is possible for mobile robots to provide various services based on the artificial landmark in large indoor environment. [ABSTRACT FROM PUBLISHER]