Distance computing between general shape preprocessed obstacles and general segments-based robot

We present in this paper a method for distance computing in an encoded environment. The proposed method allows to find the closest point between a general polygonal shape obstacle (a robot) and some complex general shapes objects (the obstacles). Due to the discretized aspect of the model, the algorithm complexity does not depend on the obstacles number and shape. In order to have a preprocessed model, the multivalue number coding has been used. Such a distance computing can be used in mobile robotics field as a basic tool in local path planning algorithms or in more sophisticated general paths planners. All the proposed algorithms follow a general schema which makes their implementation easier in an oriented object language, using a series of class.