The defense will take place on Wenesday, July 6 at 2 pm, in the amphitheatre of the Telecommunications Department (Claude Chappe building), INSA Lyon, Villeurbanne.

The presentation will be available online: https://insa-lyon-fr.zoom.us/j/91599742042

Title

User Association in Flexible and Agile Mobile Networks

Abstract

The user association process in cellular networks consists in choosing the base station with which the user equipment will negotiate radio resources. The current association is based on measuring the signal strength received by the user equipment from each of the base stations. The association must now deal with the diversification of user application needs and the growing heterogeneity of cellular networks.

In this thesis, we show experimentally that the current association process has reached its limits, that it is agnostic of the configurations of the base stations and that it does not allow to control the throughput that the user equipment will obtain following the association. We set up for the realization of our measurements an experimental platform based on the software suite of cellular networks srsRAN and software radios USRP NI-2091.

We propose in this thesis a new metric to be used during the association process. This metric, broadcasted by the base station, is a load information which in our case will be represented by the number of user equipment connected to the base station. We also discuss other metrics that can be used as load information. We show, once again experimentally, by modifying the source code of the srsRAN software suite ourselves, that if the user equipment takes this load information into account in the association process, the association decision is improved in 22% of cases.

Jury

• Tara ALI YAHIA, Associate Professor HDR, Université Paris Saclay (Reviewer)
• Vania CONAN, HDR, Thales (Reviewer)
• Véronique VEQUE, Professor, Université Paris Saclay (Examiner)
• Frédéric LAUNAY, Associate Professor, IUT de Poitiers (Examiner)
• Stéphane FRENOT, Professor, INSA-Lyon (Examiner)
• André-Luc BEYLOT, Professor, ENSEEIHT (Examiner)
• Fabrice VALOIS, Professor, INSA-Lyon (Thesis supervisor)
• Razvan STANICA, Associate Professor HDR, INSA-Lyon (Thesis co-supervisor)

The defense will take place on Thursday, July 7 at 2 pm, in the amphitheatre of the Telecommunications Department (Claude Chappe building), INSA Lyon, Villeurbanne.

The presentation will be available online: https://youtu.be/hX3t9pKPcoc

Title

Activity Models and Bayesian Estimation Algorithms for Wireless Grant-Free Random Access

Abstract

The new 5G’s wireless networks have recently started to be deployed all around the world. With them, a large spectrum of services are about to emerge, resulting in new stringent requirements so that 5G targets performance exceed that of 4G by a factor of 10. The services are centered around the use cases of enhanced mobile broadband (eMBB), ultra reliable and low-latency communication (uRLLC) and massive machine-type communication (mMTC) where each of which has required the ongoing development of key new technologies. Many of these technologies will also play an important role in the emergence of 6G.

In this thesis, the focus is on grant-free RA (GFRA) as an enabler of uRLLC and mMTC. GFRA is a new protocol introduced in 5G new radio (5G-NR) for reducing the data overhead of the random access (RA) procedure. This results in a significant reduction in the latencies of the user equipments (UEs) access to a connected medium via an access point (AP). Achieving efficient GFRA is of key importance for many 5G applications, e.g. for large scale internet of things (IoT) wireless networks. The study of new non-orthogonal multiple access (NOMA) signal processing techniques is then considered. Using tools from the theory of compressed sensing (CS), and particularly from Bayesian CS, new algorithms within the family of approximate message passing (AMP) are developed to address the joint active user detection and channel estimation (AUDaCE) problem. The active user detection is crucial to properly identify transmitting UEs within the context of large-scale dense network; the channel estimation is equally important so that an AP can reliably transmit back data to the detected UEs.

In this thesis, in contrast to existing work on this topic, the AUDaCE is studied for wireless networks where the activity of the UEs is assumed to be correlated, as is typical for many large-scale dense networks. To this end, two new activity models are introduced. The first one assumes that the activity of the UEs in the network can be modeled via group-homogeneous activity (GHomA) where devices in the same group have common pairwise correlations and marginal activity probabilities. The second model accounts for more general dependence structure via group-heterogeneous activity (GHetA). Novel approximate message passing algorithms within the hybrid GAMP (HGAMP) framework are developed for each of the models. With the aid of latent variables associated to each group for modeling the activity probabilities of the UEs, the GHomA-HGAMP algorithm can perform AUDaCE for GFRA leveraging such a group homogeneity. When the activity is heterogenous, i.e. each UE is associated with a latent variable modeling its activity probability correlated with the other variables, it is possible to develop GHetA-HGAMP using the copula theory.

Extensive numerical studies are performed, which highlight significant performance improvements of GHomA-HGAMP and GHetA-HGAMP over existing algorithms (modified generalized AMP (GAMP) and group-sparse HGAMP (GS-HGAMP)), which do not properly account for correlation in activity. In particular, the channel estimation and active user detection capability are enhanced in many scenarios with up to a 4dB improvement with twice less user errors.

As a whole, this thesis provides a systematic approach to AUDaCE for wireless networks with correlated activities using tools from Bayesian CS. We then conclude by showing how it could be used for multi-carrier orthogonal frequency division multiplexing (OFDM) scenarios with possible extensions for grant-free (GF) data transmission leveraging joint data recovery, active user detection and channel estimation (DrAUDaCE).

Jury

• Catherine DOUILLARD, Professor @ IMT Atlantique, Reviewer
• Dejan VUKOBRATOVIC, Professor @ Univ. Novi Sad, Reviewer
• Aline ROUMI, Senior Research Scientist @ INRIA Rennes, Examiner
• Philippe CIBLAT, Professor @ Telecom Paris, Examiner
• Cedomir STEFANOVIC, Professor @ Univ. Aalborg, Examiner
• Jean-Marie GORCE, Professor @ INSA Lyon, Director
• Malcolm EGAN, Research Scientist @ INRIA Lyon, Supervisore

The defense willtake place on Tuesday, May 3 at 10:00 am, in the amphitheatre of the Telecommunications Department (Claude Chappe building), INSA Lyon, Villeurbanne.

The presentation will be available on Youtube at the following link: https://youtu.be/k7dh-thqbSk

Title

Large-scale Automatic Learning of Autonomous Agent Behavior with Structured Deep Reinforcement Learning

Abstract

Autonomous robotic agents have begun to impact many aspects of our society,with application in automated logistics, autonomous hospital porters, manufacturing and household assistants. The objective of this thesis is to explore Deep Reinforcement Learning approaches to planning and navigation in large and unknown 3D environments. In particular, we focus on tasks that require exploration and memory in simulated environments. An additional requirement is that learned policies should generalize to unseen map instances. Our long-term objective is the transfer of a learned policy to a real-world robotic system. Reinforcement learning algorithms learn by interaction. By acting with the objective of accumulating a task-based reward, an Embodied AI agent must learn to discover relevant semantic cues such as object recognition and obstacle avoidance, if these skills are pertinent to the task at hand. This thesis introduces the field of Structured Deep Reinforcement Learning and then describes 5 contributions that were published during the PhD.

We start by creating a set of challenging memory-based tasks whose performance is benchmarked with an unstructured memory-based agent. We then demonstrate how the incorporation of structure in the form of a learned metric map, differentiable inverse projective geometry and self-attention mechanisms; augments the unstructured agent, improving its performance and allowing us to interpret the agent’s reasoning process.

We then move from complex tasks in visually simple environments, to more challenging environments with photo-realistic observations, extracted from scans of real-world buildings. In this work we demonstrate that augmenting such an agent with a topological map can improve its navigation performance. We achieve this by learning a neural approximation of a classical path planning algorithm, which can be utilized on graphs with uncertain connectivity.

From work undertaken over the course of a 4-month internship at the research and development department of Ubisoft, we demonstrate that structured methods can also be used for navigation and planning in challenging video game environments. Where we couple a lower level neural policy with a classical planning algorithm to improve long-distance planning and navigation performance in vast environments of 1km×1km. We release an open-source version of the environment as a benchmark for navigation in large-scale environments.

Finally, we develop an open-source Deep Reinforcement Learning interface for the Godot Game Engine. Allowing for the construction of complex virtual worlds and the learning of agent behaviors with a suite of state-of-the-art algorithms. We release the tool with a permissive open-source (MIT) license, to aid researchers in their pursuit of complex embodied AI agents.

Jury

• • Mme. Elisa Fromont – Université de Rennes 1 – Rapporteur
  • M. David Filliat – ENSTA Paris – Rapporteur
  • M. Cédric Démonceaux – Université de Bourgogne – Examinateur
  • M. Karteek Alahari – INRIA Grenoble – Examinateur
  • Mme. Christine Solnon – INSA-Lyon – Examinateur
  • M. Olivier Simonin – INSA-Lyon – Directeur de thèse
  • M. Jilles Dibangoye – INSA-Lyon – Co-encadrant de thèse
  • M. Christian Wolf – Naver Labs Europe – Co-directeur de thèse