We are building an artificial intelligence research center for automotive applications based in the center of Paris to conduct ambitious research projects, in particular in assisted and autonomous driving
Automated driving relies first on a diverse range of sensors, like Valeo’s cameras, LiDARs, radars and ultrasonics. Exploiting at best the outputs of each of these sensors at any instant is fundamental to understand the complex environment of the vehicle. To this end, we explore various deep learning approaches where sensors are considered both in isolation and collectively.
Deep learning and reinforcement learning are key technologies for autonomous driving. One of the challenges they face is to adapt to conditions which differ from those met during training. To improve systems’ performance in such situations, we explore so-called domain adaption techniques, as in AdvEnt, our project presented at CVPR 2019.
When the unexpected happens, when the weather badly degrades, when a sensor gets blocked, the embarked perception system should diagnose the situation and react accordingly, e.g, by calling an alternative system or the human driver. With this in mind, we investigate automatic ways to assess the uncertainty of a system and to predict its performance.
Deep Learning | Vision and Language | Visual reasoning
Supelec | Heuritech | SorbonneU
Kebab practitioner
Deep Learning | Vision and Language
Paris-Sud | ONERA | UNICAEN
Rookie bodybuilder
Machine Learning | Computer Vision | Visual Search | Autonomous systems
Politehnica | Mines | Inria | Safran
Random walker
Deep Learning | Computer Vision | Uncertainty
Centrale | ParisSaclay | Heuritech | Earthcube | CNAM
Self-supervised disc-jokey
Deep Learning | Computer Vision | Vision and Language
Enseirb | CergyU | KULeuven | Ensea | CNRS | SorbonneU | IUF
Top chef
Deep Learning | Computer Vision
AUTH | Cortexica | ENPC
Life-loving epicurean
Machine Learning | Computer Vision | Generative Networks
CTU-Prague | NII-Tokyo
Curious being
Deep Learning | Computer Vision
IIIT-H | Technicolor | Inria
Keen explorer
Joint 2D-3D Scene Understanding
TU Berlin | Centrale | Inria | UCSD
Funky drummer
Panthéon-Sorbonne | Marriott | Saint-Gobain | Faurecia
MisChief of Staff
Computer Vision | Photogrammetry | Geometry Processing
X | Inria | EdinburgU | Simulog | Inria | TrustedLogic | Inria | ENPC
Persistent eclectist
Deep Learning for compression | Neural Network Performance
Telecom | Technicolor | Teraki
Open source musician
Deep Learning | Machine Learning | Signal Processing
Panthéon-Sorbonne | Telecom | Zyl | Telecom
Creative traveller
Machine Learning | Computer Vision | Computational Imaging | Signal & Image Processing
Centrale | Inria | BrownU | Inria | Microsoft | Inria |Technicolor
Passionate reader
Deep Learning | Computer Vision
INSA | ValeoVS | ValeoCDA
Snow lover
Deep Learning | Machine Learning | Applied Mathematics | Generalization
Centrale | Prophesee | ENPC
Brownian mover
Deep Learning | Computer Vision | Domain Adaptation
X | TU-Munich | SorbonneU
Adaptive mind
Reinforcement Learning
Supelec | Mines
Reinforcement learner
Computer Vision | Machine Learning
X | Technicolor | MVA | NYU | Inria
Hard thinker
Deep Learning | Computer Vision
Telecom | Inria | NEC
Protein lover
Valeo.ai researchers present eight papers, including 4 orals at the premier annual computer vision conference in June 2019.
Himalaya Jain, researcher at valeo.ai, receives the Best Thesis Prize from Rennes 1 Foundation in April 2019.
Spyros Gidaris, researcher at Valeo.ai, receives the Best Thesis Prize from Ponts Foundation in June 2019.
Valeo is proud to be part of Prairie, the new Paris Interdisciplinary Artificial Intelligence Institute – May 2019.
