← Search

Thierry Chateau

2 accepted papers

2018

Learning to Touch Objects Through Stage-Wise Deep Reinforcement Learning

IROS 2018poster

Learning complex behaviors through reinforcement learning is particularly challenging when reward is only available upon successful completion of the full behavior. In manipulation robotics, so-called shaping rewards are often used to overcome this problem. However, these usually require human engin…

Cited by 7SourceScholar
2017

Deep MANTA: A Coarse-To-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis From Monocular Image

CVPR 2017poster

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization, visibility characterization and 3D dimension estimation. Its archite…

Cited by 564PDFScholar