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

This thesis has been done within Nokia Bell Labs France and the Maracas team of the CITI laboratory.

The defense willtake place on Friday, January 28 at 2:00 pm, in the showcase room of the Telecommunications Department (first floor), INSA Lyon, Villeurbanne.

The presentation will be available on Zoom at the following link: https://insa-lyon-fr.zoom.us/j/96199554997

Title

Applications of Deep Learning to the Design of Enhanced Wireless Communication Systems

Abstract

Innovation in the physical layer of communication systems has traditionally been achieved

by breaking down the transceivers into sets of processing blocks, each optimized independently based on mathematical models. This approach is now challenged by the ever-growing demand for wireless connectivity and the increasingly diverse set of devices and use-cases. Conversely, deep learning (DL)-based systems are able to handle increasingly complex tasks for which no tractable models are available. By learning from the data, these systems could be trained to embrace the undesired effects of practical hardware and channels instead of trying to cancel them. This thesis aims at comparing different approaches to unlock the full potential of DL in the physical layer.

First, we describe a neural network (NN)-based block strategy, where an NN is optimized to replace one or multiple block(s) in a communication system. We apply this strategy to introduce a multi-user multiple-input multiple-output (MU-MIMO) detector that builds on top of an existing DL-based architecture. The key motivation is to replace the need for retraining on each new channel realization by a hypernetwork that generates optimized sets of parameters for the underlying DL detector. Second, we detail an end-to-end strategy, in which the transmitter and receiver are modeled as NNs that are jointly trained to maximize an achievable information rate. This approach allows for deeper optimizations, as illustrated with the design of waveforms that achieve high throughputs while satisfying peak-to-average power ratio (PAPR) and adjacent channel leakage ratio (ACLR) constraints. Lastly, we propose a hybrid strategy, where multiple DL components are inserted into a traditional architecture but trained to optimize the end-to-end performance. To demonstrate its benefits, we propose a DL-enhanced MU-MIMO receiver that both enable lower bit error rates (BERs) compared to a conventional receiver and remains scalable to any number of users.

Each approach has its own strengths and shortcomings. While the first one is the easiest to implement, its individual block optimization does not ensure the overall system optimality. On the other hand, systems designed with the second approach are computationally complex and do not comply with current standards, but allow the emergence of new opportunities such as high-dimensional constellations and pilotless transmissions. Finally, even if the block-based architecture of the third approach prevents deeper optimizations, the combined flexibility and end-to-end performance gains motivate its use for short-term practical implementations.

Jury

• • Reviewer: Didier LE RUYET, Professor, CNAM, Paris, France
  • Reviewer: Charlotte LANGLAIS, Permanent Research Staff, IMT Atlantique, Brest, France
  • Examiner: Inbar FIJALKOW, Professor, ENSEA, Cergy, France
  • Examiner: Stephan TEN BRINK, Professor, University of Stuttgart, Stuttgart, Allemagne
  • Thesis supervisor: Jean-Marie GORCE, Professor, INSA Lyon, Villeurbanne, France
  • Thesis co-supervisor: Jakob HOYDIS, Principal Research Scientist, Nvidia, France*
  • Thesis co-supervisor Fayçal AIT AOUDIA, Senior Research Scientist, Nvidia, France*

* Previously at Nokia Bell Labs France