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.