Attention on the road!

Abstract

Autonomous driving and advanced driver-assistance systems require the perception of the surrounding environment. A subtask in perception is the detection and classification of objects in the environment, commonly referred to as object detection. To aid in this task an autonomous system is outfitted with a sensor suite which commonly include camera, LiDAR and radar sensor modalities. The contribution of this work is the construction of a novel object detection pipline using a sensor suite of five radar sensors which are capable of detecting objects in a complete field of view. The model constructed is an end-to-end deep learning model which utilizes graph convolutions over radar points to generate a contextualized representation of the sensor data. It is shown that the model presented is able detect the most commonly occurring classes in the dataset and performs particularly well on objects in motion. It is explored why the model performs poorly on the uncommon classes which stems from limitations in the non-maximum suppression algorithm as well as the low efficacy of the object classifier.