Auton Robot (2006) 21:15–28 DOI 10.1007/s10514-005-6066-z Information based indoor environment robotic exploration and modeling using 2-D images and graphs Vivek A. Sujan · Marco A. Meggiolaro · Felipe A. W. Belo Published online: 22 April 2006 C  Springer Science + Business Media, LLC 2006 Abstract As the autonomy of personal service robotic sys- tems increases so has their need to interact with their en- vironment. The most basic interaction a robotic agent may have with its environment is to sense and navigate through it. For many applications it is not usually practical to pro- vide robots in advance with valid geometric models of their environment. The robot will need to create these models by moving around and sensing the environment, while minimiz- ing the complexity of the required sensing hardware. Here, an information-based iterative algorithm is proposed to plan the robot’s visual exploration strategy, enabling it to most efficiently build a graph model of its environment. The al- gorithm is based on determining the information present in sub-regions of a 2-D panoramic image of the environment from the robot’s current location using a single camera fixed on the mobile robot. Using a metric based on Shannon’s information theory, the algorithm determines potential loca- tions of nodes from which to further image the environment. Using a feature tracking process, the algorithm helps navi- gate the robot to each new node, where the imaging process V. A. Sujan Advanced Controls Division, Cummins Engine Company, Columbus, IN 47201 e-mail: vivek.a.sujan@cummins.com M. A. Meggiolaro Department of Mechanical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, RJ-Brazil e-mail: meggi@alum.mit.edu F. A. W. Belo Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro 22453-900, RJ-Brazil e-mail: felipe-belo@uol.com.br is repeated. A Mellin transform and tracking process is used to guide the robot back to a previous node. This imaging, evaluation, branching and retracing its steps continues un- til the robot has mapped the environment to a pre-specified level of detail. The set of nodes and the images taken at each node are combined into a graph to model the environment. By tracing its path from node to node, a service robot can navigate around its environment. This method is particularly well suited for flat-floored environments. Experimental re- sults show the effectiveness of this algorithm. Keywords Mobile robots . Localization . Map building . SLAM . Information theory 1. Introduction In recent years, mobile service robots have been introduced into various non-industrial application areas such as entertainment, building services, and hospitals. They are relieving humans of tedious work with the prospect of 24-hour availability, fast task execution, and cost-effectiveness. The market for medical robots, underwater robots, surveillance robots, demolition robots, cleaning robots and many other types of robots for carrying out a multitude of services has grown significantly (Thrun, 2003). The sales of mobile robots are projected to exceed the sales of factory floor robots by a factor of four, exceeding US$2 billion within this decade (Lavery, 1996). And unlike the factory floor robot market, the sources for the vast majority of these machines could be U.S. companies. Service robots for personal and private use are mainly found in the areas of domestic (household) robots, which include vacuum cleaning and lawn-mowing robots, and en- tertainment robots, including toy and hobby robots. If the Springer