Deep learning has revolutionized the ability to learn "end-to-end" autonomous vehicle control directly from raw sensory data. While there have been recent advances on extensions to handle forms of navigation instruction, these works are unable to capture the full distribution of possible actions that could be taken and to reason about localization of the robot within the environment. In this paper, we extend end-to-end driving networks with the ability to understand maps. We define a novel variational network capable of learning from raw camera data of the environment as well as higher level roadmaps to predict (1) a full probability distribution over the possible control commands; and (2) a deterministic control command capable of navigating on the route specified within the map. Additionally, we formulate how our model can be used to localize the robot according to correspondences between the map and the observed visual road topology, inspired by the rough localization that human drivers can perform. We evaluate our algorithms on real-world driving data, and reason about the robustness of the inferred steering commands under various types of rich driving scenarios. In addition, we evaluate our localization algorithm over a new set of roads and intersections which the model has never driven through and demonstrate rough localization in situations without any GPS prior.

Technical Paper: http://arxiv.org/abs/1811.10119

Authors: Alexander Amini, Guy Rosman, Sertac Karaman, and Daniela Rus

Acknowledgments:
Support for this work was given by the National Science Foundation (NSF) and Toyota Research Institute (TRI). However, note that this article solely reflects the opinions and conclusions of its authors and not TRI or any other Toyota entity. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the V100 GPU and Drive PX2 used for this research.