An End-to-End System for Crowdsourced 3d Maps for Autonomous Vehicles: The Mapping Component
This addresses the need for affordable high-definition mapping in autonomous driving, though it appears incremental as an end-to-end pipeline using existing techniques.
The paper tackles the problem of creating precise 3D maps for autonomous vehicles using cost-effective sensors, achieving mean absolute accuracy of less than 20 cm at sign corners from 25 journeys.
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.