BIM Based Indoor Navigation System of Hermes Mobile Robot
In this paper the problem of BIM based indoor navigation is considered. The purpose of the project is to develop the semantic navigation system of an autonomous robot using BIM (Building Information Modeling). The described representation enables semantic
- PDF / 475,678 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 56 Downloads / 247 Views
aw University of Technology, The Institute of Automatic Control and Robotics, Warsaw, Poland Abstract In this paper the problem of BIM based indoor navigation is considered. The purpose of the project is to develop the semantic navigation system of an autonomous robot using BIM (Building Information Modeling). The described representation enables semantic robot navigation with a goal specified at a various levels of abstraction. The concept of hierarchical action planning is presented, where the plan is a time-optimized path combined with a sequence of actions required for robot movement across the whole building. The navigation process is supported by semantic localization which utilizes two methods: object detection based on point clouds (the 3D camera data acquired and converted into a point cloud) and visual object detection (based on the image taken from two color cameras placed on the sides of the robot).
1
Introduction
The aim of our project is to build the navigation system of an autonomous mobile robot which performs delivery tasks in an indoor environment. The problem of autonomous transport has been already solved in industrial environments but the adaptation of such a system to office or hospital environment is very difficult. The building adaptation process for moving autonomous platforms Fahimi (2009) (eg. appropriate markers on the floor, wide corridors, etc.) is usually very expensive and time consuming. Such robots move in partially known space which is frequented by employees and customers, so the objects can change their states M.Przybylski and B.Siemi¸atkowska (2012); Shiller et al. (2007). Usually the goal given to a robot is described using natural language, for example ”go to the library” or ”go to the kitchen”. These facts have to be included in the robot motion control system Borenstein et al. (1996).
V. Padois, P. Bidaud, O. Khatib (Eds.), Romansy 19 – Robot Design, Dynamics and Control, CISM International Centre for Mechanical Sciences, DOI 10.1007/978-3-7091-1379-0_46, © CISM, Udine 2013
B. Siemiatkowska et al. ˛
376
Most of the navigation systems use a global metric map of the environment. This kind of representation is convenient for a small flat area but is inefficient in a large building. Metric maps require a lot of memory and the algorithm of path planning based on a metric map is highly time consuming. Some authors suggest using topological-metric representation Thrun et al. (2005); Harmelen et al. (2008). This kind of a map is usually represented as a graph. The nodes of the graph correspond to particular elements of the building (for example a hall, a kitchen etc.). The edges of the graph reflect accessibility relations between corresponding places. Representing an environment as a simple graph seems to be natural but it is insufficient in large buildings. In our approach a hierarchical BIM-based graph is used. Building Information Modeling (BIM) gives a useful tool for environment representation Siemi¸atkowska et al. (2011a). It is the object-based parametric modeling te
Data Loading...
