End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances
Machine Learning
2020-03-17 v2 Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
Machine Learning
Abstract
Reinforcement Learning (RL) aims at learning an optimal behavior policy from its own experiments and not rule-based control methods. However, there is no RL algorithm yet capable of handling a task as difficult as urban driving. We present a novel technique, coined implicit affordances, to effectively leverage RL for urban driving thus including lane keeping, pedestrians and vehicles avoidance, and traffic light detection. To our knowledge we are the first to present a successful RL agent handling such a complex task especially regarding the traffic light detection. Furthermore, we have demonstrated the effectiveness of our method by winning the Camera Only track of the CARLA challenge.
Cite
@article{arxiv.1911.10868,
title = {End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances},
author = {Marin Toromanoff and Emilie Wirbel and Fabien Moutarde},
journal= {arXiv preprint arXiv:1911.10868},
year = {2020}
}
Comments
Accepted at main conference of CVPR 2020