RESLAM: A real-time robust edge-based SLAM system

Fabian Schenk, Friedrich Fraundorfer

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Abstract

Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Robotics and Automation 2019
Number of pages8
Publication statusPublished - 20 May 2019
EventIEEE International Conference on Robotics and Automation 2019 - Palais des congrès de Montréal, Montreal, Canada
Duration: 20 May 201924 May 2019
https://www.icra2019.org/

Conference

ConferenceIEEE International Conference on Robotics and Automation 2019
Abbreviated titleICRA
CountryCanada
CityMontreal
Period20/05/1924/05/19
Internet address

Fingerprint

Cameras
Sensors
Program processors
Robotics
Pipelines
Lighting

Keywords

  • SLAM
  • Edge-based
  • direct methods
  • RGBD sensors

Cite this

Schenk, F., & Fraundorfer, F. (2019). RESLAM: A real-time robust edge-based SLAM system. In Proceedings of the International Conference on Robotics and Automation 2019

RESLAM: A real-time robust edge-based SLAM system. / Schenk, Fabian; Fraundorfer, Friedrich.

Proceedings of the International Conference on Robotics and Automation 2019. 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Schenk, F & Fraundorfer, F 2019, RESLAM: A real-time robust edge-based SLAM system. in Proceedings of the International Conference on Robotics and Automation 2019. IEEE International Conference on Robotics and Automation 2019, Montreal, Canada, 20/05/19.
Schenk F, Fraundorfer F. RESLAM: A real-time robust edge-based SLAM system. In Proceedings of the International Conference on Robotics and Automation 2019. 2019
Schenk, Fabian ; Fraundorfer, Friedrich. / RESLAM: A real-time robust edge-based SLAM system. Proceedings of the International Conference on Robotics and Automation 2019. 2019.
@inproceedings{5083066b35164f59b9bbb9375b3618e3,
title = "RESLAM: A real-time robust edge-based SLAM system",
abstract = "Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software.",
keywords = "SLAM, Edge-based, direct methods, RGBD sensors",
author = "Fabian Schenk and Friedrich Fraundorfer",
year = "2019",
month = "5",
day = "20",
language = "English",
booktitle = "Proceedings of the International Conference on Robotics and Automation 2019",

}

TY - GEN

T1 - RESLAM: A real-time robust edge-based SLAM system

AU - Schenk, Fabian

AU - Fraundorfer, Friedrich

PY - 2019/5/20

Y1 - 2019/5/20

N2 - Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software.

AB - Simultaneous Localization and Mapping is a key requirement for many practical applications in robotics. In this work, we present RESLAM, a novel edge-based SLAM system for RGBD sensors. Due to their sparse representation, larger convergence basin and stability under illumination changes, edges are a promising alternative to feature-based or other direct approaches. We build a complete SLAM pipeline with camera pose estimation, sliding window optimization, loop closure and relocalisation capabilities that utilizes edges throughout all steps. In our system, we additionally refine the initial depth from the sensor, the camera poses and the camera intrinsics in a sliding window to increase accuracy. Further, we introduce an edge-based verification for loop closures that can also be applied for relocalisation. We evaluate RESLAM on wide variety of benchmark datasets that include difficult scenes and camera motions and also present qualitative results. We show that this novel edge-based SLAM system performs comparable to state-of-the-art methods, while running in real-time on a CPU. RESLAM is available as open-source software.

KW - SLAM

KW - Edge-based

KW - direct methods

KW - RGBD sensors

M3 - Conference contribution

BT - Proceedings of the International Conference on Robotics and Automation 2019

ER -