Search

Radar has been a key enabler of advanced driver assistance systems in automotive for over two decades. Being an inexpensive, all-weather and long-range sensor that simultaneously provides velocity measurements, radar is expected to be indispensable to the future of autonomous driving. Traditional radar signal processing techniques often cannot distinguish reflections from objects of interest from clutter and are generally limited to detecting peaks in the received signal. These peak detection methods effectively collapse the image-like radar signal into a sparse point cloud. In this paper, we demonstrate a deep-learning-based vehicle detection solution which operates on the image-like tensor instead of the point cloud resulted by peak detection.To the best of our knowledge, we are the first to implement such a system.

Autonomous vehicles rely on precise high definition (HD) 3D maps for navigation. This paper presents the mapping component of an end-to-end system for crowdsourcing precise 3D maps with semantically meaningful landmarks such as traffic signs (6 dof pose, shape and size) and traffic lanes (3D splines). The system uses consumer grade parts, and in particular, relies on a single front facing camera and a consumer grade GPS. Using real-time sign and lane triangulation on-device in the vehicle, with offline sign/lane clustering across multiple journeys and offline Bundle Adjustment across multiple journeys in the backend, we construct maps with mean absolute accuracy at sign corners of less than 20 cm from 25 journeys. To the best of our knowledge, this is the first end-to-end HD mapping pipeline in global coordinates in the automotive context using cost effective sensors.