
L’équipe Emeraude du citi est co-organisateur de la conférence Sound and Music Computing 2022 qui aura lieu à Saint-Étienne du 4 au 12 Juin. Voilà le programme : https://smc22.grame.fr/program.html
L’équipe Emeraude du citi est co-organisateur de la conférence Sound and Music Computing 2022 qui aura lieu à Saint-Étienne du 4 au 12 Juin. Voilà le programme : https://smc22.grame.fr/program.html
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
Large-scale Automatic Learning of Autonomous Agent Behavior with Structured Deep Reinforcement Learning
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.
FAST Project is an ANR project involving Insa-Lyon (CITI), Grame-CNCM, Central Lyon.
This project aims to:
Here’s a short demo video of what Citizens from the Emeraude team have done in the project: https://youtu.be/_Cwk7LwjXGk
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
Applications of Deep Learning to the Design of Enhanced Wireless Communication Systems
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.
* Previously at Nokia Bell Labs France
Title: Projet Samildanach – Communication Scientifique dans une Culture Digitale
Date and Place: January 27th 14h, Amphi Chappe
Lien visio : https://insa-lyon-fr.zoom.us/j/97446195543
Speaker: Dr. Frédéric Prost (UGA)
Abstract:
L’objectif de ce séminaire est de présenter un projet relatif à la communication scientifique. L’idée est d’utiliser plusieurs technologies récentes comme la blockchain, les tables de hachage décentralisées ainsi que les calculs de réputation issus des réseaux sociaux pour les appliquer au domaine de la publication scientifique. La blockchain est utilisée pour certifier,présenter une résistance à la censure, assurer la non répudiation et une structure d’incitations pour le développement du réseau (rémunération des acteurs qui aident le réseau). Ce projet est intrinsèquement multi-disciplinaire et au croisement de nombreuses technologies et domaines de l’informatique.
Biographie:
The defense will be held in the Amphitheater, Claude Chappe, and will be streamed live here.
On the Performance of Spatial Modulation and Full Duplex Radio Architectures
Index modulation techniques have exhibited great potential in the scenarios foreseen in next-generation wireless networks. Applying in the spatial domain, spatial modulation (SM) as a single radio-frequency (RF) multiple-input–multiple-output (MIMO) solution has attracted wide attention. The SM system has only one transmitting antenna activated for each time slot which results in low system complexity and cost. It exploits the index of the transmitting antennas to convey additional information bits.
To analyze the SM performance, a simulated framework over the time-varying Rician fading channel is built with ADS and Matlab software and a channel state information (CSI) detector is highlighted. The simulation results are verified by the experimental implementation based on the National Instruments (NI) PXI chassis hardware and LabVIEW programming environment. In the practical analysis, two models of the propagation environments are considered, where a channel sounding method is employed in order to extract the channel coefficients.
Despite issues on system complexity and cost, a shortage of spectrum resources can also restrict the development of mobile communications technology. Full duplex (FD) communications have been developed to double the radio link data rate and spectral efficiency through simultaneous and bidirectional communication. The main challenge of FD systems is self-interference (SI), which is caused by the coupling of the transmitting antenna with the receiving one. The combination of FD and SM will not only maintain spectral efficiency but also decrease the complexity of the self-interference cancellation (SIC) because of the single RF chain.
Based on these, a full duplex spatial modulation (FDSM) system is proposed as well as the SIC method. Moreover, the impact of SIC accuracy on the system performance is studied. We focus on the FDSM system imperfections including IQ imbalance, phase noise, power amplifier (PA) nonlinearities and RF switch nonidealities. The bit error rate (BER) performance under different scenarios with these imperfections is analyzed, along with the estimation and cancellation method.
Title: L’observabilité du spectre radio et ses opportunités
Date and Place: December 2nd 14h20, salle Vitrine (CITI Lab, INSA-Lyon, Batiment Claude Chappe), 6 avenue des arts, 69621 Villeurbanne
Speaker: Dr.Raul De Lacerda (CentraleSupélec)
Abstract:
Title: Présentation de travaux passés sur les boucles de routage et la couche MAC LoRaWAN, et de projets sur LoRa
Date and Place: November 22th 10h30, Amphi Chappe (CITI Lab, INSA-Lyon, Batiment Claude Chappe), 6 avenue des arts, 69621 Villeurbanne
Speaker: Dr. Alexandre Guitton (Université Clermont Auvergne)
Abstract:
Biography:
Alexandre Guitton est professeur en informatique à l’Isima (école interne de Clermont Auvergne INP, établissement composante de l’Université Clermont Auvergne). Il effectue sa recherche au LIMOS (UMR CNRS). Il est spécialisé dans le domaine des réseaux sans fil et de l’intérêt des objets, et travaille plus précisément sur la conception de protocoles d’accès au médium pour la surveillance (généralement environnementale) par des réseaux de capteurs sans fil. Récemment, il s’est concentré sur la technologie LoRa et cherche à trouver des algorithmes efficaces permettant de récupérer des messages qui entrent en collision.
Title: Software Defined Approaches for Non-Conventional Wireless Communication Paradigms
Date and Place: November 25th 14h00, room TBA (CITI Lab, INSA-Lyon, Batiment Claude Chappe), 6 avenue des arts, 69621 Villeurbanne
Speaker: Dr. Valeria Loscri (Inria)
Abstract:
The increasing demand of high data rate, bandwidth, low latency in wireless communication systems, imposes the urgence to investigate on new communication paradigms.
New communication technologies should be integrated in communication systems to make them as much flexible as possible and capable to dynamically reacting to external conditions based on the status of each node. Based on these considerations, in this talk two main concepts will be discussed: 1) wireless systems based on Software Defined (SD) approaches and 2) non-conventional communication paradigms. The synergic combination of these two concepts seems to have a great potential for responding to the demand of new communication services. The non-conventional wireless communication paradigms as Visible Light Communication (VLC) and the integration of Reconfigurable Intelligent (Meta)Surface in the wireless systems, allow to extend the range of wireless systems and to meet the urgence of Sustainable ICT. The SD approach may provide a sufficient degree of flexibility and adaptivity for making the coexistence of non-conventional wireless solutions with the traditional wireless approaches very smooth.
Biography:
Valeria Loscri is a permanent research scientist at Inria Lille – Nord Europe since October 2013. From December 2006 to September 2013, she was research fellow in the TITAN Lab at the University of Calabria, Italy. She received her M.Sc. and Ph.D degrees in computer science in 2003 and 2007, respectively, from the University of Calabria and her HDR (Habilitation à diriger des recherches) in 2018 from the Université de Lille (France). Her prominent research interests focus on emerging technologies for new communication paradigms such as Visible Light Communication (VLC), reconfigurable Intelligent (Meta)Surfaces (RIM) based systems and cyber security in wireless communication systems. She has been involved in several European Projects (H2020 CyberSANE, FP7 EU VITAL) and national projects. She is on the editorial board of IEEE COMST, Elsevier ComNet, ComCom, JNCA, IEEE Transaction on NanoBioscience. Since 2019, she is Scientific International Delegate for Inria Lille – Nord Europe.
Title: Recent Approaches of Speaker Anonymization Techniques
Date and Place: November 17th 14h00, Citi (room TBD) + visio
Speaker: Dr. Mohamed Maouche (Postdoc Inria)
Abstract:
An increasing number of smart devices embed speech-commands. The usage of speech offers simplicity, accessibility and it also opens new human-computer interactions. However, the gathering and exploitation of this type of data raise many privacy threats as speech data is sensitive in nature. Personal information about the speaker can be inferred (e.g., gender, emotion…). In addition, speech is a biometric characteristic, it can be used to identify speakers. To address this issue anonymization techniques have been proposed. In this talk, we are going to present the recent approaches for speech anonymization techniques with a focus on x-vector based anonymization.
Biography:
Starting October 2021, I’m a post-doc in Privatics (Inria) at Lyon working on privacy in Federated Learning in the Chaire DSVD supported by Renault and Labex IMU. Previously, I was a post-doc with Magnet (Inria) at Lille for two years, working on speech privacy. Before, I have received my Ph.D. in 2019 from Insa Lyon which I did under the supervision of Sara Bouchenak and Sonia Ben Mokhtar in Liris Lab working on Location Privacy. My main interest throughout my research is the re-identification and anonymization problem, especially while facing peculiar data.