Résumé
Mobile robot navigation tasks can be applied in various domains, such as in space, underwater, and transportation industries, among others. In navigation, robots analyze their environment from sensors and navigate safely up to target points by avoiding obstacles. Numerous methods exist to perform each navigation task. In this work, we focus on robot localization based on feature extraction algorithms using images as sensory data. ORB, and SURF are state-of-the-art algorithms for featurebased robot localization thanks to their fast computation time, even if ORB lacks precision. SIFT is state-of-the-art for high precision feature detection but it is slow and not compatible with realtime robotic applications. Thus, in our work, we explore how to speed up SIFT algorithm for realtime robot localization by employing an unconventional computing paradigm with oscillatory neural networks (ONNs). We present a hybrid SIFT-ONN algorithm that replaces the computation of Difference of Gaussian in SIFT with ONNs by performing image edge detection. We report on SIFT-ONN algorithm performances, which are similar to the state-of-the-art ORB algorithm.