Application of a Bio-inspired Localization Model to Autonomous Vehicles

In this paper, we propose an approach to tackle the localization challenge for autonomous vehicles by taking inspiration from biological models. We present a neural architecture based on a neurobotic model of the place cells found in the hippocampus of mammals. This model is based on an attentional mechanism and only takes into account visual information from a mono-camera and the orientation information to self-localize. Such a localization model has already been integrated in a robot control architecture which allows for successful navigation both in indoor and small outdoor environments. The contribution of this paper is to study how it passes the scale change by evaluating the performance of this model over much larger outdoor environments. Six experiments, taken from the KITTI datasets, using real data (image and orientation) grabbed by a moving vehicle are studied. The results show the strong adaptability of the model to different kinds of environments.