Fabien Moutarde

Professeur

Adresse e-mail: fabien.moutarde@minesparis.psl.eu
Discipline(s): Signal, image, automatique, robotique et génie industriel
Thème(s): Robotique

Mots-clés

Équipe

CAOR

Biographie

Fabien Moutarde est un chercheur dont les travaux se situent à l’intersection de l’intelligence artificielle, de la robotique et de la perception multimodale. Ses recherches couvrent des thématiques variées, allant des algorithmes de vision par ordinateur à l’intégration de données sensorielles multiples (vision, son, Wi-Fi) pour des applications en localisation et navigation autonome. Son expertise s’étend également à l’apprentissage par renforcement, où il explore des méthodes innovantes pour améliorer l’efficacité et la robustesse des agents autonomes, notamment dans des environnements complexes comme la conduite urbaine ou la manipulation robotique. Ses contributions incluent des approches hybrides combinant réseaux de neurones profonds et stratégies d’imitation, avec un accent sur la généralisation et l’adaptabilité des systèmes. Les applications pratiques de ses travaux touchent des domaines tels que la robotique collaborative, les véhicules autonomes et la compréhension des interactions humaines en milieu urbain.

Publication(s)

2026
An Efficient Multi-Estimation-Based Parameter Centroid Decision Via Linear Regression Approach DOI : 10.1109/TPAMI.2026.3653765
2025
NERAF: 3D SCENE INFUSED NEURAL RADIANCE AND ACOUSTIC FIELDS
2024
PANO-ECHO: PANOramic depth prediction enhancement with ECHO features DOI : 10.1109/CAI59869.2024.00193
2024
HiER: Highlight Experience Replay for Boosting Off-Policy Reinforcement Learning Agents DOI : 10.1109/ACCESS.2024.3427012
2024
MBAPPE: MCTS-Built-Around Prediction for Planning Explicitly DOI : 10.1109/IV55156.2024.10588457
2023
GRI: General Reinforced Imitation and Its Application to Vision-Based Autonomous Driving DOI : 10.3390/robotics12050127
2023
The Audio-Visual BatVision Dataset for Research on Sight and Sound DOI : 10.1109/IROS55552.2023.10341715
2023
Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks
2023
TSGN: Temporal Scene Graph Neural Networks with Projected Vectorized Representation for Multi-Agent Motion Prediction DOI : 10.1109/IV55152.2023.10186764
2022
Vision and Wi-Fi fusion in probabilistic appearance-based localization DOI : 10.1177/0278364920910485
2022
THOMAS: TRAJECTORY HEATMAP OUTPUT WITH LEARNED MULTI-AGENT SAMPLING
2022
GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation DOI : 10.1109/ICRA46639.2022.9812253
2022
Assessing Cross-dataset Generalization of Pedestrian Crossing Predictors DOI : 10.1109/IV51971.2022.9827083
2021
HOME: Heatmap Output for future Motion Estimation DOI : 10.1109/ITSC48978.2021.9564944
2021
TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction DOI : 10.1109/FG52635.2021.9666989
2020
Generative model for skeletal human movements based on conditional dc-gan applied to pseudo-images DOI : 10.3390/a13120319
2020
Predicting intentions of pedestrians from 2d skeletal pose sequences with a representation-focused multi-branch deep learning network DOI : 10.3390/a13120331
2020
End-to-end model-free reinforcement learning for urban driving using implicit affordances DOI : 10.1109/CVPR42600.2020.00718
2020
Vehicle Absolute Ego-Localization from Vision, Using Only Pre-existing Geo-Referenced Panoramas DOI : 10.1007/978-3-030-44610-9_1
2019
Urban localization with street views using a convolutional neural network for end-to-end camera pose regression DOI : 10.1109/IVS.2019.8813892
2019
Multi-users online recognition of technical gestures for natural human–robot collaboration in manufacturing DOI : 10.1007/s10514-018-9704-y
2019
Real-Time Gestural Control of Robot Manipulator Through Deep Learning Human-Pose Inference DOI : 10.1007/978-3-030-34995-0_51
2018
End to End Vehicle Lateral Control Using a Single Fisheye Camera DOI : 10.1109/IROS.2018.8594090
2018
Coupled Longitudinal and Lateral Control of a Vehicle using Deep Learning DOI : 10.1109/ITSC.2018.8570020
2018
A Natural User Interface for Gestural Expression and Emotional Elicitation to Access the Musical Intangible Cultural Heritage DOI : 10.1145/3127324
2018
Deep learning for hand gesture recognition on skeletal data DOI : 10.1109/FG.2018.00025
2017
Topological localization using Wi-Fi and vision merged into FABMAP framework DOI : 10.1109/IROS.2017.8206171
2016
Improving robustness of monocular urban localization using augmented street view DOI : 10.1109/ITSC.2016.7795603
2016
Motion planning for urban autonomous driving using bezier curves and MPC DOI : 10.1109/ITSC.2016.7795651
2016
Fingers gestures early-recognition with a unified framework for RGB or depth camera DOI : 10.1145/2948910.2948947
2016
Monocular urban localization using street view DOI : 10.1109/ICARCV.2016.7838744
2016
Towards the design of augmented feedforward and feedback for sensorimotor learning of motor skills DOI : 10.1145/2948910.2948959
2016
A tabletop instrument for manipulation of sound morphologies with hands, fingertips and upper-body DOI : 10.1145/2948910.2948946
2016
A hierarchical Model Predictive Control framework for on-road formation control of autonomous vehicles DOI : 10.1109/IVS.2016.7535413
2016
A user-adaptive gesture recognition system applied to human-robot collaboration in factories DOI : 10.1145/2948910.2948933
2016
Analysis of Large-Scale Traffic Dynamics in an Urban Transportation Network Using Non-Negative Tensor Factorization DOI : 10.1007/s13177-014-0099-7
2016
A distributed MPC framework for road-following formation control of car-like vehicles DOI : 10.1109/ICARCV.2016.7838837
2015
Novel 3D game-like applications driven by body interactions for learning specific forms of intangible cultural heritage DOI : 10.5220/0005456606510660
2015
Towards the Design of a Natural User Interface for Performing and Learning Musical Gestures DOI : 10.1016/j.promfg.2015.07.952
2015
Music Gestural Skills Development Engaging Teachers, Learners and Expert Performers DOI : 10.1016/j.promfg.2015.07.428
2015
Gesture Recognition Using a Depth Camera for Human Robot Collaboration on Assembly Line DOI : 10.1016/j.promfg.2015.07.216
2015
Decentralized model predictive control for smooth coordination of automated vehicles at intersection DOI : 10.1109/ECC.2015.7331068
2014
Priority-based coordination of autonomous and legacy vehicles at intersection DOI : 10.1109/ITSC.2014.6957845
2014
Capture, modeling, and recognition of expert technical gestures in wheel-throwing art of pottery DOI : 10.1145/2627729
2014
Humanoid robot navigation: Getting localization information from vision DOI : 10.1515/jisys-2013-0079
2013
Statistical traffic state analysis in large-scale transportation networks using locality-preserving non-negative matrix factorisation DOI : 10.1049/iet-its.2011.0157
2013
Recognition of supplementary signs for correct interpretation of traffic signs DOI : 10.1109/IVWorkshops.2013.6615228
2013
Fast 3D keypoints detector and descriptor for view-based 3D objects recognition DOI : 10.1007/978-3-642-40303-3_12
2013
Recognition of supplementary signs for correct interpretation of traffic signs DOI : 10.1109/IVS.2013.6629450
2013
Information, modeling and traffic reconstruction DOI : 10.1002/9781118743751.ch3
2012
3D keypoints detection for objects recognition
2012
Subsign detection with region-growing from contrasted seeds DOI : 10.1109/ITSC.2012.6338826
2012
Analysis of large-scale traffic dynamics using non-negative tensor factorization
2011
3D keypoint detectors and descriptors for 3D objects recognition with TOF camera DOI : 10.1117/12.872483
2011
Analysis of network-level traffic states using locality preservative non-negative matrix factorization DOI : 10.1109/ITSC.2011.6083060
2010
Joint interpretation of on-board vision and static GPS cartography for determination of correct speed limit
2010
Spatial and temporal analysis of traffic states on large scale networks DOI : 10.1109/ITSC.2010.5625175
2009
Visual object categorization with new keypoint-based adaBoost features DOI : 10.1109/IVS.2009.5164310
2009
PhD forum: Keypoints-based background model and foreground pedestrians extraction for future smart cameras DOI : 10.1109/ICDSC.2009.5289390
2009
Adaboost with "Keypoint Presence Features" for real-time vehicle visual detection
2008
Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences DOI : 10.1109/ICDSC.2008.4635689
2008
Improving pan-European speed-limit signs recognition with a new "global number segmentation" before digit recognition DOI : 10.1109/IVS.2008.4621168
2008
A robot behavior-learning experiment using particle swarm optimization for training a neural-based animat DOI : 10.1109/ICARCV.2008.4795790
2008
Detection and recognition of end-of-speed-limit and supplementary signs for improved european speed limit support
2007
Modular traffic signs recognition applied to on-vehicle real-time visual detection of American and European speed limit signs
2007
Robust on-vehicle real-time visual detection of American and European speed limit signs, with a modular Traffic Signs Recognition system DOI : 10.1109/ivs.2007.4290268
2006
Combining adaBoost with a hill-climbing evolutionary feature search for efficient training of performant visual object detectors DOI : 10.1142/9789812774118_0104
2005
U*F clustering: A new performant "cluster- mining" method based on segmentation of self-organizing maps
1998
Adaptive compression of still images: Automating the choice of algorithm and parameters DOI : 10.1117/12.324116
1995
Scale invariance and self-similar behavior of dark matter halos DOI : 10.1086/175331
1991
Precollapse scale invariance in gravitational instability DOI : 10.1086/170728
1990
Collisionless formation of filaments in an expanding universe DOI : 10.1086/168662

Enseignements

Introduction au Machine-Learning

Responsable

Théorie de l’apprentissage statistique ; typologie des applications ; réseaux neuronaux (MLP, convNets …) ; méthodes à noyaux et Support Vector Machines (SVM) ; méthodes ensemblistes : dopage (boosting) et forêts aléatoires ; clustering (k-means, DBSCAN, …) ; attention & transformers ; réseaux récurrent (RNN)

Large-Scale Machine-Learning

Responsable

From cancer research to finance, natural language processing, marketing or self-driving cars, many fields are nowadays impacted by recent progress in machine learning algorithms that benefit from the ability to collect huge amounts of data and "learn" from them. The goal of this intensive 5-days ADVANCED course is to present the theoretical foundations and practical algorithms to implement and solve modern machine learning problems, and to expose the students to current applications and challenges of Machine Learning in science and industry.

Direction(s) de thèse(s)

2025 Perception sémantique par analyse spatio-spectrale de la scène. IVANOVA Ivanina
2024 Apprentissage par Renforcement pour la prédiction et la planification dans la conduite automatisée DOULAZMI Waël
2024 Prédiction de mouvement impliquant intéractions agent à agent et modélisation multimodale AZEVEDO TONÉ Caio
2024 Multi-Modal Foundation Model for 4D Scene Understanding and Synthesis WANG Fusang
2023 perception active pour la compréhension de scène nocturne via l’éclairage du véhicule DE MOREAU Simon
2022 Raisonnement multimodal pour la reconstruction géométrique et acoustique de scènes BRUNETTO Amandine
2021 Intégrer des connaissances expertes dans des méthodes d'apprentissage par renforcement profond pour la conduite autonome CHEKROUN Raphaël
2020 Prédiction intelligente des trajectoires de véhicules, dans différents scenarii de conduite autonome GILLES Thomas
2019 Analyse des mouvements et gestes des piétons via caméra embarquée pour la prédiction de leurs intentions GESNOUIN Joseph
2019 Apprentissage profond par Renforcement et Démonstrations, pour le comportement de robots manipulateurs BUJALANCE MARTIN Jesús
2018 Apprentissage par renforcement du contrôle d’un véhicule autonome à partir de la vision TOROMANOFF Marin
2016 Localisation d'un robot humanoïde en milieu intérieur non-contraint NOWAKOWSKI Mathieu
2016 Apprentissage profond pour les séries temporelles multivarieées : contrôle de véhicule autonome, reconnaissance de gestes et génération de mouvement DEVINEAU Guillaume