prikaz prve stranice dokumenta Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems
  Download
PDF 14.6 MB
doctoral thesis
Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:186549
Peršić, Juraj
University of Zagreb
Faculty of Electrical Engineering and Computing
Department of Control and Computer Engineering

Institutional repository: FER Repository

Cite this document

Peršić, J. (2021). Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems (Doctoral thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:186549

Peršić, Juraj. "Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:186549

Peršić, Juraj. "Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:186549

Peršić, J. (2021). 'Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems', Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 17 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:186549

Peršić J. Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems [Doctoral thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 November 17] Available at: https://urn.nsk.hr/urn:nbn:hr:168:186549

J. Peršić, "Extrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems", Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:186549

Metadata
TitleExtrinsic and temporal calibration of heterogeneous mobile robot exteroceptive sensor systems
Title (croatian)Ekstrinzično i vremensko umjeravanje heterogenih eksterocepcijskih senzorskih sustava mobilnih robota
AuthorJuraj Peršić
MentorIvan Petrović (mentor)
Committee memberIvan Petrović (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
(Department of Control and Computer Engineering)
Zagreb
Defense date and country2021, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Universal decimal classification
(UDC)		004 - Computer science and technology. Computing. Data processing
Abstract
Robust environment perception of a mobile robot strongly relies on fusion of multiple heterogeneous sensors. However, proper sensor calibration is essential for fusion. Extrinsic calibration tries to find transform between coordinate frames of two or more sensors. This thesis proposes a novel calibration target suitable for accurate 6 degrees of freedom calibration of radar-camera-lidar systems. Furthermore, measurements of the target enable two-step optimization which leads to accurate extrinsic calibration. While the first step is rather standard reprojection error optimization, a novel second step based on radar cross section (RCS) is proposed. It exploits newly discovered effect of radar’s RCS estimation error related to the elevation angle. Temporal calibration tries to align timestamps of multiple sensors based on comparison of their measurements. This thesis proposes a method for temporal calibration based on moving target tracking thus enabling temporal calibration of radars with other sensors such as cameras and lidars. The backbone of the proposed approach are Gaussian Processes used for continuous-time trajectory representation. Furthermore, a novel joint spatiotemporal calibration is proposed that owes its efficiency to the Exactly Sparse Gaussian Process Regression and on- manifold optimization. Online calibration uses information from the environment to generate correspondences between the sensors. This thesis proposes a novel method for online calibration based on moving object tracking applied to radar-camera-lidar systems. It introduces a calibration-agnostic track-to-track association scheme that works well under miscalibration. Furthermore, lightweight online decalibration detection scheme is proposed based on analytical pairwise calibration solution. Lastly, complete recalibration of the system is achieved through graph-based multisensor calibration. Combination of the proposed target-based and targetless methods enables a complete solution to calibration of radar-camera-lidar sensor systems.
Abstract (croatian)
Robusna percepcija okoline mobilnog robota značajno ovisi o fuziji više heterogenih senzora. Međutim, ispravno umjeravanje senzora je neophodno za fuziju. Ekstrinzično umjeravanje nastoji pronaći transformaciju između koordinatnih sustava dva ili više senzora. Disertacija predstavlja novu metu prikladnu za umjeravanje sustava radar-lidar-kamera u svih šest stupnjeva slobode. Nadalje, mjerenja mete omogućuju dvo-koračnu optimizaciju koja dovodi do preciznih parametara ekstrinzičnog umjeravanja. Prvi korak koristi uobičajenu optimizaciju reprojekcijske pogreške, dok je drugi korak zasnovan na radarskom presjeku (RCS). Koristeći novo otkriveni efekt radarove pogreške u estimaciji RCS-a, povezanim s kutem elevacije, metoda poboljšava rezultate umjeravanja. Vremensko umjeravanje nastoji preklopiti vremena očitanja više senzora koristeći usporedbu njihovih mjerenja. Disertacija predlaže metodu za vremensko umjeravanje zasnovanu na praćenju gibajuće mete čime je omogućeno vremensko umjeravanje radara s drugim senzorima poput kamera i lidara. Okosnica predložene metode je reprezentacija kontinuiranih trajektorija koristeći regresiju Gaussovim procesima. Nadalje, predložena je nova metoda za istodobnu optimizaciju vremenskih i ekstrinzičnih parametara umjeravanja koja duguje svoju efikasnost točno rijetkoj regresiji Gaussovim procesima te optimizaciji na višestrukosti. Umjeravanje tijekom rada koristi informacije iz okoline kako bi uparilo mjerenja između senzora. Disertacija predlaže novu metodu za umjeravanje tijekom rada zasnovanu na praćenju gibajućih objekata primijenjenu na senzorski sustav radar-lidar-kamera. Predloženo je uparivanje praćenih traka koristeći metodu neosjetljivu na pogreške u umjeravanju. Uz to, uvedena je računski jednostavna metoda za otkrivanje pogreške umjeravanja. Po otkrivanju pogreške, metoda pokreće cjelovito umjeravanje sustava zasnovano na optimizaciji na grafovima. Kombinacijom predloženih metoda zasnovanih na meti i bez nje, omogućeno je cjelovito rješenje za umjeravanje senzorskog sustava radar-lidar-kamera.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:168:186549
Study programmeTitle: Computer Science
Study programme type: university
Study level: postgraduate
Academic / professional title: Doktor znanosti (Doktor znanosti)
Catalog URLhttp://lib.fer.hr/cgi-bin/koha/opac-detail.pl?biblionumber=52383
Type of resourceText
Extentxvi, 121 str.
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-03-15 07:59:13