End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances

Marin Toromanoff (1, 2, 3) , Emilie Wirbel (1) , Fabien Moutarde (2)

1 Valeo Driving Assistance Domain
2 CAOR - Centre de Robotique
3 Valeo.ai

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 affor-dances, 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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Automatique / Robotique

Marin Toromanoff, Emilie Wirbel, Fabien Moutarde. End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances. IEEE conference on Computer Vision and Pattern Recognition (CVPR'2020), Jun 2020, Seattle, United States. ⟨hal-02513566⟩