DMCA
Visual SLAM for autonomous ground vehicles
| Venue: | in IEEE International Conference on Robotics and Automation |
| Citations: | 6 - 4 self |
BibTeX
@INPROCEEDINGS{Lategahn_visualslam,
author = {Henning Lategahn and Andreas Geiger and Bernd Kitt},
title = {Visual SLAM for autonomous ground vehicles},
booktitle = {in IEEE International Conference on Robotics and Automation},
year = {},
pages = {150--156}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
and Visual SLAM (V-SLAM) in particular have been an active area of research lately. In V-SLAM the main focus is most often laid on the localization part of the problem allowing for a drift free motion estimate. To this end, a sparse set of landmarks is tracked and their position is estimated. However, this set of landmarks (rendering the map) is often too sparse for tasks in autonomous driving such as navigation, path planning, obstacle avoidance etc. Some methods keep the raw measurements for past robot poses to address the sparsity problem often resulting in a pose only SLAM akin to laser scanner SLAM. For the stereo case, this is however impractical due to the high noise of stereo reconstructed point clouds. In this paper we propose a dense stereo V-SLAM algorithm that estimates a dense 3D map representation which is more accurate than raw stereo measurements. Thereto, we run a sparse V-SLAM system, take the resulting pose estimates to compute a locally dense representation from dense stereo correspondences. This dense representation is expressed in local coordinate systems which are tracked as part of the SLAM estimate. This allows the dense part to be continuously updated. Our system is driven by visual odometry priors to achieve high robustness when tracking landmarks. Moreover, the sparse part of the SLAM system uses recently published sub mapping techniques to achieve constant runtime complexity most of the time. The improved accuracy over raw stereo measurements is shown in a Monte Carlo simulation. Finally, we demonstrate the feasibility of our method by presenting outdoor experiments of a car like robot. I.
Keyphrases
visual slam autonomous ground vehicle raw stereo measurement dense representation high noise improved accuracy dense stereo correspondence sparse v-slam system drift free motion estimate scanner slam main focus localization part visual odometry prior slam system dense stereo v-slam algorithm local coordinate system high robustness slam estimate constant runtime complexity outdoor experiment sparse set path planning pose estimate stereo case sparse part monte carlo simulation past robot pose raw measurement dense part map representation sparsity problem active area obstacle avoidance etc point cloud
