no code implementations • 10 Jul 2020 • Adithya Ranga, Filippo Giruzzi, Jagdish Bhanushali, Emilie Wirbel, Patrick Pérez, Tuan-Hung Vu, Xavier Perrotton
In this paper we propose a multi-task learning model to predict pedestrian actions, crossing intent and forecast their future path from video sequences.
no code implementations • 9 Mar 2020 • Thibault Buhet, Emilie Wirbel, Andrei Bursuc, Xavier Perrotton
Our model processes ego vehicle front-facing camera images and bird-eye view grid, computed from Lidar point clouds, with detections of past and present objects, in order to generate multiple trajectories for both ego vehicle and its neighbors.
1 code implementation • CVPR 2020 • Marin Toromanoff, Emilie Wirbel, Fabien Moutarde
To our knowledge we are the first to present a successful RL agent handling such a complex task especially regarding the traffic light detection.
Ranked #13 on Autonomous Driving on CARLA Leaderboard
no code implementations • 2 Sep 2019 • Thibault Buhet, Emilie Wirbel, Xavier Perrotton
Mid-to-mid (environment abstraction to mid-level trajectory representation) or direct perception (raw signal to performance) approaches strive to handle more complex, real life environment and tasks (e. g. complex intersection).
1 code implementation • 13 Aug 2019 • Marin Toromanoff, Emilie Wirbel, Fabien Moutarde
In the Arcade Learning Environment (ALE), small changes in environment parameters such as stochasticity or the maximum allowed play time can lead to very different performance.
no code implementations • 14 Dec 2018 • Laurent George, Thibault Buhet, Emilie Wirbel, Gaetan Le-Gall, Xavier Perrotton
In this paper we present a complete study of an end-to-end imitation learning system for speed control of a real car, based on a neural network with a Long Short Term Memory (LSTM).
no code implementations • 20 Aug 2018 • Marin Toromanoff, Emilie Wirbel, Frédéric Wilhelm, Camilo Vejarano, Xavier Perrotton, Fabien Moutarde
Experiments are conducted on a custom dataset corresponding to more than 10000 km and 200 hours of open road driving.
no code implementations • 2 Aug 2018 • Maximilian Jaritz, Raoul de Charette, Emilie Wirbel, Xavier Perrotton, Fawzi Nashashibi
Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.).
Ranked #9 on Depth Completion on KITTI Depth Completion