This work has as purpose the implementation of a path planning algorithm used for autonomous driving car on a mobile differential drive robot. Since the algorithm is based on the use of G2-spline for the path computation, these have been used also for our purpose, realizing a planner able to first compute some candidates paths, and then choose the best one according to different criteria taken into account. In dynamic environments, moreover, lots of obstacles, that could be people or objects, are present, then the mobile robot must be able to navigate in this type of environments. The state of art on these topics is quite huge, however, here the challenging task is the adaptation on a mobile robot of an algorithm realized for autonomous driving cars, aiming at give to the robot natural, human-like behaviour. The main purpose is to have, in the end, a robot able to approach people and interact with them without causing disturbances.