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

Fabian Schenk, Friedrich Fraundorfer

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

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.
Originalspracheenglisch
TitelProceedings of the International Conference on Robotics and Automation 2019
Seitenumfang8
PublikationsstatusVeröffentlicht - 20 Mai 2019
VeranstaltungIEEE International Conference on Robotics and Automation 2019 - Palais des congrès de Montréal, Montreal, Kanada
Dauer: 20 Mai 201924 Mai 2019
https://www.icra2019.org/

Konferenz

KonferenzIEEE International Conference on Robotics and Automation 2019
KurztitelICRA
LandKanada
OrtMontreal
Zeitraum20/05/1924/05/19
Internetadresse

Fingerprint

Cameras
Sensors
Program processors
Robotics
Pipelines
Lighting

Schlagwörter

    Dies zitieren

    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.

    Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem KonferenzbandForschungBegutachtung

    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., Montreal, Kanada, 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 -