The ability to accurately determine the position of an agent in an unknown environment is of crucial importance for the Simultaneous Localization And Mapping (SLAM) problem. Better localization and odometry estimates lead to improved map generation. This map forms the basis of most robot navigation stacks and is essential for driving without human interference. With the increase in automation along with the use of robotics, there is an increased need to refine the SLAM related methodologies. While indoor navigation usually lacks access to reliable Global Positioning System (GPS) data, it has the advantage of having a known building model in most cases. This extra level of information can be exploited to boost the quality of both the localization and mapping modules. As the real environment usually differs significantly from the theoretical model, a methodology that is resilient to outliers and scan model differences is proposed. This approach is added on top of Lidar Odometry And Mapping (LOAM) and also made open source to the public.     «

The ability to accurately determine the position of an agent in an unknown environment is of crucial importance for the Simultaneous Localization And Mapping (SLAM) problem. Better localization and odometry estimates lead to improved map generation. This map forms the basis of most robot navigation stacks and is essential for driving without human interference. With the increase in automation along with the use of robotics, there is an increased need to refine the SLAM related methodologies. Whi...     »