A Robust CNN Training Approach to Address Hierarchical Localization with Omnidirectional Images
J.J. Cabrera, S. Cebollada, L. PayŠ, M. Flores, O. Reinoso
ICINCO 2021. 18th International Conference on Informatics in Control, Automation and Robotics  (Online streaming, 6-8 July, 2021)
Ed. SCITEPRESS - Science and Technology Publications, Lda.  ISBN:978-989-758-522-7  ISSN:2184-2809  - 302-310


This paper reports and evaluates the training optimization process of a Convolutional Neural Network (CNN) with the aim of addressing the localization of a mobile robot. The proposed method addresses the localization problem by means of a hierarchical approach by using a visual sensor that provides omnidirectional images. In this sense, AlexNet is adapted and re-trained with a twofold purpose. First, the rough localization step consists of a room retrieval task. Second, the fine localization step within the retrieved room is carried out by means of a nearest neighbour search by comparing a holistic descriptor obtained from the CNN with the visual model of the retrieved room. The novelty of the present work lies in the use of a CNN and holistic descriptors obtained from raw omnidirectional images as captured by the vision system, with no panoramic conversion. In addition, this work proposes the use of a data augmentation technique and a Bayesian optimization to address the training process of the CNN. These approaches constitute an efficient and robust solution to the localization problem, as shown in the experimental section even in presence of substantial changes of the lighting conditions.