Mapping
Our AI-based methods automate and assist human-in-the-loop HD map production processes through machine learning and computer vision applied to offline map generation pipelines.
Recent ATG R&D publications
DAGMapper: Learning to Map by Discovering Lane Topology
Namdar Homayounfar, Wei-Chiu Ma*, Justin Liang*, Xinyu Wu, Jack Fan, Raquel Urtasun (ICCV 2019)
Exploiting Sparse Semantic HD Maps for Self-Driving Vehicle Localization
Wei-Chiu Ma*, Ignacio Tartavull*, Ioan Andrei Barsan*, Shenlong Wang*, Min Bai, Gellert Mattyus, Namdar Homayounfar, Shrinidhi Kowshika Lakshmikanth, Andrei Pokrovsky, Raquel Urtasun (IROS 2019)
Convolutional Recurrent Network for Road Boundary Extraction
Justin Liang*, Namdar Homayounfar*, Wei-Chiu Ma, Shenlong Wang, Raquel Urtasun (CVPR 2019)
Learning to Localize Through Compressed Binary Maps
Xinkai Wei*, Ioan Andrei Bârsan*, Shenlong Wang*, Julieta Martinez, Raquel Urtasun (CVPR 2019)
Deep Multi-Sensor Lane Detection
Min Bai*, Gellért Máttyus*, Namdar Homayounfar, Shenlong Wang, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun (IROS 2018, oral)
Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds
Chris Zhang, Wenjie Luo, Raquel Urtasun (3DV 2018, spotlight)
End-to-End Deep Structured Models for Drawing Crosswalks
Justin Liang, Raquel Urtasun (ECCV 2018)
Hierarchical Recurrent Attention Networks for Structured Online Maps
Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun (CVPR 2018)
DeepRoadMapper: Extracting Road Topology From Aerial Images
Gellért Máttyus, Wenjie Luo, Raquel Urtasun (ICCV 2017)