Hierarchical Recurrent Attention Networks for Structured Online Maps

    Abstract

    In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on vertices, as there exists many ways to draw equivalent polylines. We demonstrate the effectiveness of our method on a 90 km stretch of highway, and show that we can recover the right topology 92% of the time.

    Authors

    Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun

    Conference

    CVPR 2018

    Full Paper

    ‘Hierarchical Recurrent Attention Networks for Structured Online Maps’ (PDF)

    Uber ATG

    Comments
    Previous articlePIXOR: Real-time 3D Object Detection from Point Clouds
    Next articleAutomatically identifying, counting, and describing wild animals in camera-trap images with deep learning
    Namdar Homayounfar
    I'm a research scientist at Uber ATG Toronto and a PhD student at Univeristy of Toronto under the supervision of Prof. Raquel Urtasun. I have broad research interests in deep learning and computer vision. My current focus is in development of deep structured models for the creation of HD maps required for the safe navigation of autonomous vehicles. Previously, I obtained my MSc degree in Statistics at University of Toronto and prior to that my BSc in Probalblity and Statistics from McGill University.
    Wei-Chiu Ma
    Wei-Chiu Ma is a PhD student at MIT advised by Prof. Antonio Torralba. His research interests lie in the intersection of computer vision and machine learning, in particular low-level vision and 3D vision. He also works part-time at Uber ATG Toronto with Prof. Raquel Urtasun to apply his research to self-driving vehicles.
    Raquel Urtasun
    Raquel Urtasun is the Chief Scientist for Uber ATG and the Head of Uber ATG Toronto. She is also a Professor at the University of Toronto, a Canada Research Chair in Machine Learning and Computer Vision and a co-founder of the Vector Institute for AI. She is a recipient of an NSERC EWR Steacie Award, an NVIDIA Pioneers of AI Award, a Ministry of Education and Innovation Early Researcher Award, three Google Faculty Research Awards, an Amazon Faculty Research Award, a Connaught New Researcher Award, a Fallona Family Research Award and two Best Paper Runner up Prize awarded CVPR in 2013 and 2017. She was also named Chatelaine 2018 Woman of the year, and 2018 Toronto’s top influencers by Adweek magazine