Bayesian Simultaneous Localization and Multi-Lane Tracking Using Onboard Sensors and a SD Map

TL;DR

This paper introduces a cost-effective Bayesian method combining GNSS, visual odometry, and lane detection to create detailed lane-level maps for autonomous driving, using only onboard sensors and a standard map as prior.

Contribution

It develops a Bayesian simultaneous localization and multi-object tracking framework employing a TPMBM filter with B-spline trajectories for traffic line estimation.

Findings

Traffic line estimates generally align with lane markings

Method works with only onboard sensors and a standard map

Preliminary results show promising lane-level accuracy

Abstract

High-definition map with accurate lane-level information is crucial for autonomous driving, but the creation of these maps is a resource-intensive process. To this end, we present a cost-effective solution to create lane-level roadmaps using only the global navigation satellite system (GNSS) and a camera on customer vehicles. Our proposed solution utilizes a prior standard-definition (SD) map, GNSS measurements, visual odometry, and lane marking edge detection points, to simultaneously estimate the vehicle's 6D pose, its position within a SD map, and also the 3D geometry of traffic lines. This is achieved using a Bayesian simultaneous localization and multi-object tracking filter, where the estimation of traffic lines is formulated as a multiple extended object tracking problem, solved using a trajectory Poisson multi-Bernoulli mixture (TPMBM) filter. In TPMBM filtering, traffic lines are modeled using B-spline trajectories, and each trajectory is parameterized by a sequence of control points. The proposed solution has been evaluated using experimental data collected by a test vehicle driving on highway. Preliminary results show that the traffic line estimates, overlaid on the satellite image, generally align with the lane markings up to some lateral offsets.