Car-like mobile robot navigation in unknown urban areas

Abstract

This paper implements an automated transportation system allowing passengers on a car-like robot to reach their destination safely, intelligently and autonomously. Different components of the system are described such as localization based on Hector SLAM, humans detection based on HOG (Histograms of Oriented Gradient) descriptor and intelligent navigation based on FNN (Fuzzy neural networks) approach. To show the whole system effectiveness for the car-like mobile robot Robucar, experimentations were done in ROS, in an unknown human environment.