Fuzzy logic obstacle identity declaration and fusion in the autotaxi system

The Autotaxi system is a safety critical sensor system developed to perform the sensing required for an autonomous vehicle to drive safely along a dedicated paved giddeway network. The host vehicle is equipped with a set of sensors used to detect and track any object of interest in the field of view. In this work a multiple-sensor obstacle identification and fusion approach for the Autotaxi system is proposed. Based on the knowledge about the vehicles, the obstacles to be detected, and the guideway network system, two obstacle classifier systems are designed using the principles of fuzzy logic. In Classifier 1 the classification process is carried out based on the obstacle's width and kind of road in which the host vehicle is navigating. In Classifier 2 the classification process is carried out based on the obstacle's width and height together with the kind of road in which the host vehicle is navigating. Furthermore, as different declarations of identity can be performed by using information from different sensors, a method to fuse these identity declarations is proposed. The viability of the proposed approach is demonstrated through a simulated example. Promising results are reported.