Person tracking and following by a mobile robotic platform

Robots integrated into a social environment with humans need the ability to locate persons in their surrounding area. This is also the case for the WelcomeBot which is developed at the Fraunhofer Institute IAIS. In the future, the robot should follow persons in the buildings and guide them to certain areas. Therefore, it needs the capability to detect and track a person in the environment. In this master thesis, an approach for fast and reliable tracking of a person via a mobile robotic platform is presented. Based on the investigation of different methods and sensors, a laser scanner and a camera are selected as the primary two sensors. For the laser scanner, a classification and tracking method is implemented utilizing the laser scanner distance values as well as the remission values. For the camera, a very successful person detection algorithm is used and combined with some fast tracking algorithms known in the _eld of computer vision. Finally, a combined approach for both the camera and the laser scanner is presented. All methods are evaluated in different environments and have also been tested in a scenario where the robot is following a person automatically.