Lyft 3D object detection for autonomous vehicles

Abstract Self-driving technology is going to change the infrastructure of transportation systems worldwide in the near future. It is an opportunity to improve the quality of the social life style. While infrastructure strains under rapid urban growth, avoidable collisions, vehicle emissions, and single-occupant commutators are choking cities. In this severe condition, autonomous vehicles are expected to redefine the transportation system by unlocking environmental, social, and economic benefits. There are various challenges that the autonomous ground vehicle (AGV) needs to take care of to drive safely from the source to the desired destination. One such challenge is to avoid sense and detect the peripheral objects and respond accordingly. This chapter focuses on detecting 3D objects with 3D bounding boxes which come within the range of AGV LiDAR or camera. The objective of this chapter is to use deep learning models to train the LiDAR and camera images and to evaluate the confidence score for each model.

[1]  Dragomir Anguelov,et al.  VectorNet: Encoding HD Maps and Agent Dynamics From Vectorized Representation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Simon Lucey,et al.  Argoverse: 3D Tracking and Forecasting With Rich Maps , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yin Zhou,et al.  VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  Qiang Xu,et al.  nuScenes: A Multimodal Dataset for Autonomous Driving , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[6]  Leonidas J. Guibas,et al.  Frustum PointNets for 3D Object Detection from RGB-D Data , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Bin Yang,et al.  Multi-Task Multi-Sensor Fusion for 3D Object Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Dragomir Anguelov,et al.  Scalability in Perception for Autonomous Driving: Waymo Open Dataset , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jiong Yang,et al.  PointPillars: Fast Encoders for Object Detection From Point Clouds , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Henggang Cui,et al.  Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Driving , 2018, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[11]  Ruigang Yang,et al.  The ApolloScape Open Dataset for Autonomous Driving and Its Application , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.