Robust optimal sensor planning for occlusion handling in dynamic robotic environments

Rishi Mohan (Corresponding author), Bram de Jager

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Uittreksel

Optimal sensor planning for workspace detectionin robotic environments is hindered due to sensor occlusions.These occlusions are often dynamic. Probabilistic optimizationframeworks, which generally deal with the uncertain nature ofthese occlusions suffer from unreliability and/or unavailability ofprobability distribution functions. This paper proposes and analyses a robust optimization approach (minimax) which generatessensor configurations based on occlusion scenarios that causemaximum obstruction of the robotic workspace. The optimalsolution is independent of probability distribution functions andprovides a guaranteed level of workspace visibility regardlessof occluder positions, thus accounting for random occlusions.The method also allows the user to determine the impact of theworst-case occlusion scenarios leading to a broader perspective onsensor planning. Evaluation of the approach for a mobile medicalX-ray robotic system in a simulation healthcare environmentshows the effectiveness of the proposed method
TaalEngels
Artikelnummer8643386
Pagina's4259-4270
Aantal pagina's12
TijdschriftIEEE Sensors Journal
Volume19
Nummer van het tijdschrift11
DOI's
StatusGepubliceerd - 1 jun 2019

Vingerafdruk

occlusion
robotics
planning
Robotics
Planning
Distribution functions
sensors
Sensors
Visibility
Probability distributions
probability distribution functions
visibility
rays
distribution functions
optimization
evaluation
configurations
simulation

Trefwoorden

    Citeer dit

    @article{4c9b8355612947ed83589653d098a844,
    title = "Robust optimal sensor planning for occlusion handling in dynamic robotic environments",
    abstract = "Optimal sensor planning for workspace detectionin robotic environments is hindered due to sensor occlusions.These occlusions are often dynamic. Probabilistic optimizationframeworks, which generally deal with the uncertain nature ofthese occlusions suffer from unreliability and/or unavailability ofprobability distribution functions. This paper proposes and analyses a robust optimization approach (minimax) which generatessensor configurations based on occlusion scenarios that causemaximum obstruction of the robotic workspace. The optimalsolution is independent of probability distribution functions andprovides a guaranteed level of workspace visibility regardlessof occluder positions, thus accounting for random occlusions.The method also allows the user to determine the impact of theworst-case occlusion scenarios leading to a broader perspective onsensor planning. Evaluation of the approach for a mobile medicalX-ray robotic system in a simulation healthcare environmentshows the effectiveness of the proposed method",
    keywords = "dynamic occlusions, minimax optimization, Optimal sensor placement, workspace detection",
    author = "Rishi Mohan and {de Jager}, Bram",
    year = "2019",
    month = "6",
    day = "1",
    doi = "10.1109/JSEN.2019.2899929",
    language = "English",
    volume = "19",
    pages = "4259--4270",
    journal = "IEEE Sensors Journal",
    issn = "1530-437X",
    publisher = "Institute of Electrical and Electronics Engineers",
    number = "11",

    }

    Robust optimal sensor planning for occlusion handling in dynamic robotic environments. / Mohan, Rishi (Corresponding author); de Jager, Bram.

    In: IEEE Sensors Journal, Vol. 19, Nr. 11, 8643386, 01.06.2019, blz. 4259-4270.

    Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

    TY - JOUR

    T1 - Robust optimal sensor planning for occlusion handling in dynamic robotic environments

    AU - Mohan,Rishi

    AU - de Jager,Bram

    PY - 2019/6/1

    Y1 - 2019/6/1

    N2 - Optimal sensor planning for workspace detectionin robotic environments is hindered due to sensor occlusions.These occlusions are often dynamic. Probabilistic optimizationframeworks, which generally deal with the uncertain nature ofthese occlusions suffer from unreliability and/or unavailability ofprobability distribution functions. This paper proposes and analyses a robust optimization approach (minimax) which generatessensor configurations based on occlusion scenarios that causemaximum obstruction of the robotic workspace. The optimalsolution is independent of probability distribution functions andprovides a guaranteed level of workspace visibility regardlessof occluder positions, thus accounting for random occlusions.The method also allows the user to determine the impact of theworst-case occlusion scenarios leading to a broader perspective onsensor planning. Evaluation of the approach for a mobile medicalX-ray robotic system in a simulation healthcare environmentshows the effectiveness of the proposed method

    AB - Optimal sensor planning for workspace detectionin robotic environments is hindered due to sensor occlusions.These occlusions are often dynamic. Probabilistic optimizationframeworks, which generally deal with the uncertain nature ofthese occlusions suffer from unreliability and/or unavailability ofprobability distribution functions. This paper proposes and analyses a robust optimization approach (minimax) which generatessensor configurations based on occlusion scenarios that causemaximum obstruction of the robotic workspace. The optimalsolution is independent of probability distribution functions andprovides a guaranteed level of workspace visibility regardlessof occluder positions, thus accounting for random occlusions.The method also allows the user to determine the impact of theworst-case occlusion scenarios leading to a broader perspective onsensor planning. Evaluation of the approach for a mobile medicalX-ray robotic system in a simulation healthcare environmentshows the effectiveness of the proposed method

    KW - dynamic occlusions

    KW - minimax optimization

    KW - Optimal sensor placement

    KW - workspace detection

    UR - http://www.scopus.com/inward/record.url?scp=85065433445&partnerID=8YFLogxK

    U2 - 10.1109/JSEN.2019.2899929

    DO - 10.1109/JSEN.2019.2899929

    M3 - Article

    VL - 19

    SP - 4259

    EP - 4270

    JO - IEEE Sensors Journal

    T2 - IEEE Sensors Journal

    JF - IEEE Sensors Journal

    SN - 1530-437X

    IS - 11

    M1 - 8643386

    ER -