Centre de documentation
scientifique

Application of machine learning techniques for evidential 3D perception, in the context of autonomous driving / Edouard Capellier (2020)  

Public Titre : Application of machine learning techniques for evidential 3D perception, in the context of autonomous driving Type de document : Thèse/HDR Auteurs : Edouard Capellier, Auteur ; Véronique Berge-Cherfaoui, Directeur de thèse ; Franck Davoine, Directeur de thèse Editeur : Compiègne : Université de Technologie de Compiègne UTC Année de publication : 2020 Importance : 123 p. Format : 21 x 30 cm Note générale : bibliographie Thèse présentée pour l'obtention du grade de Docteur de l'UTC, Robotique et Sciences et Technologies de l'Information et des Systèmes Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] apprentissage profond [Termes IGN] carte routière [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] données lidar [Termes IGN] image RVB [Termes IGN] intelligence artificielle [Termes IGN] navigation autonome [Termes IGN] segmentation sémantique [Termes IGN] théorie de Dempster-Shafer [Termes IGN] vision par ordinateur [Termes IGN] visualisation 3D Index. décimale : THESE Thèses et HDR Résumé : (auteur) The perception task is paramount for self-driving vehicles. Being able to extract accurate and significant information from sensor inputs is mandatory, so as to ensure a safe operation. The recent progresses of machine-learning techniques revolutionize the way perception modules, for autonomous driving, are being developed and evaluated, while allowing to vastly overpass previous state-of-the-art results in practically all the perception-related tasks. Therefore, efficient and accurate ways to model the knowledge that is used by a self-driving vehicle is mandatory. Indeed, self-awareness, and appropriate modeling of the doubts, are desirable properties for such system. In this work, we assumed that the evidence theory was an efficient way to finely model the information extracted from deep neural networks. Based on those intuitions, we developed three perception modules that rely on machine learning, and the evidence theory. Those modules were tested on real-life data. First, we proposed an asynchronous evidential occupancy grid mapping algorithm, that fused semantic segmentation results obtained from RGB images, and LIDAR scans. Its asynchronous nature makes it particularly efficient to handle sensor failures. The semantic information is used to define decay rates at the cell level, and handle potentially moving object. Then, we proposed an evidential classifier of LIDAR objects. This system is trained to distinguish between vehicles and vulnerable road users, that are detected via a clustering algorithm. The classifier can be reinterpreted as performing a fusion of simple evidential mass functions. Moreover, a simple statistical filtering scheme can be used to filter outputs of the classifier that are incoherent with regards to the training set, so as to allow the classifier to work in open world, and reject other types of objects. Finally, we investigated the possibility to perform road detection in LIDAR scans, from deep neural networks. We proposed two architectures that are inspired by recent state-of-the-art LIDAR processing systems. A training dataset was acquired and labeled in a semi-automatic fashion from road maps. A set of fused neural networks reaches satisfactory results, which allowed us to use them in an evidential road mapping and object detection algorithm, that manages to run at 10 Hz Note de contenu : 1- Introduction 2- Machine learning for perception in autonomous driving 3- The evidence theory, and its applications in autonomous driving 4- A synchronous evidential grid mapping from RGB images and LIDAR scans 5- Evidential LIDAR object classification 6- Road detection in LIDAR scans 7- Application of RoadSeg:evidential road surface mapping 8- Conclusion Numéro de notice : 25895 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Robotique et Sciences et Technologies de l'Information et des Systèmes : UTC : 2020 Organisme de stage : Laboratoire Heudiasyc nature-HAL : Thèse DOI : sans En ligne : https://hal.science/tel-02897810v1 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96013