LOKALIZACIJA V NOTRANJEM OKOLJU Z UPORABO PAMETNEGA TELEFONA

Tomažič, Simon (avtor), Škrjanc, Igor (mentor)

V doktorski disertaciji obravnavamo lokalizacijo v notranjem okolju z uporabo pametnega telefona. Ta je postal skoraj nepogrešljiv pripomoček sodobnega človeka, tudi zaradi vse večje vloge na področju osebnih navigacijskih sistemov. Lokalizacija v notranjem okolju je trenutno predmet številnih raziskav in projektov, saj se še nobeden izmed obstoječih lokalizacijskih sistemov ni uveljavil v taki meri, kot so se globalni navigacijski satelitski sistemi pri lokalizaciji in navigaciji v zunanjem okolju. Razlogi za to se skrivajo v visoki ceni preciznih lokalizacijskih sistemov oz. v slabi natančnosti cenovno dostopnih sistemov. Da bi nek nov lokalizacijski sistem prišel v širšo uporabo, pa mora biti z njim dosežen kompromis, ki predvideva zadovoljivo natančnost lokalizacije za relativno nizko ceno. Sodobni pametni telefoni imajo vgrajene številne senzorje (to so inercialni senzorji, kamera, barometer) in komunikacijske module (WiFi, Bluetooth, NFC), ki omogočajo implementacijo različnih lokalizacijskih algoritmov. Da bi v čim večji meri izkoristili potencial sodobnih mobilnih naprav, smo razvili tri različne lokalizacijske sisteme, in sicer vizualno lokalizacijo, inercialni navigacijski sistem in pa radijsko lokalizacijo. V sklopu vizualne lokalizacije smo na pametnem telefonu implementirali algoritem vizualne odometrije, ki se izvaja v realnem času na dveh ločenih nitih. Pri inercialnem navigacijskem sistemu smo za namen uporabe navigacije na slepo implementirali števec korakov (pedometer) in digitalni kompas, ki temeljita na uporabi pospeškometra, žiroskopa in magnetometra. Ker sta tako vizualna odometrija kot tudi inercialni navigacijski sistem občutljiva na zunanje motnje, smo oba lokalizacijska sistema združili z uporabo razširjenega Kalmanovega filtra. Na ta način smo dobili natančen in robusten relativni lokalizacijski sistem, ki omogoča določanje položaja v prostoru glede na poznano začetno točko. Da bi lahko določali tudi globalne položaje v prostoru, smo se lotili razvoja radijske lokalizacije, v sklopu katere smo preizkusili več različnih metod, in sicer trilateracijo, metodo prstnih odtisov in optimizacijo z rojem delcev, ki omogočajo določanje položaja v prostoru glede na meritve jakosti Bluetooth signalov. Za potrebe delovanja omenjenih metod smo zgradili nelinearne ter tudi mehke modele, ki opisujejo spreminjanje jakosti signalov v odvisnosti od razdalje do oddajnikov. Pri zajemu meritev, na podlagi katerih so bili zgrajeni modeli, je imel ključno vlogo razviti relativni lokalizacijski sistem, saj smo z njegovo uporabo na enostaven način zbrali meritve jakosti signalov v odvisnosti od razdalje do oddajnikov. Najboljši rezultati lokalizacije so bili dobljeni z uporabo mehkih modelov in metode prstnih odtisov. V tem primeru smo za 53 % ocenjenih položajev dobili napako manjšo od 0,5 m oz. za 99 % ocenjenih položajev manjšo od 1 m. Z namenom, da bi rezultate globalne lokalizacije še nekoliko izboljšali, smo implementirali fuzijo Bluetooth lokalizacijskega sistema, ki temelji na metodi prstnih odtisov in relativnega lokalizacijskega sistema, ki ga sestavljata vizualna odometrija in inercialni navigacijski sistem. Z združitvijo obeh sistemov so se napake globalnih položajev zmanjšale, saj je bila v tem primeru napaka manjša od 0,5 m pri več kot 80 % ocenjenih položajev. Z izvrstnimi rezultati se razvitemu lokalizacijskemu sistemu odpirajo številna vrata, saj se lahko uporablja pri vodenju avtonomnih mobilnih sistemov ali ljudi znotraj zgradb.

• Jezik: Slovenski jezik
• Ključne besede: Lokalizacija, fuzija, odometrija, kamera, inercialni senzorji, Kalmanov filter, pedometer, digitalni kompas, Bluetooth, prstni odtisi, pametni telefon, mehki modeli, pešec
• Vrsta gradiva: Doktorsko delo/naloga
• Organizacija: FE - Fakulteta za elektrotehniko
• Leto izida: 2016
• PID: 20.500.12556/RUL-87057
• COBISS.SI-ID: 11648340
• Datum objave v RUL: 17.11.2016

Sekundarni jezik

• Jezik: Angleški jezik
• Naslov: INDOOR LOCALIZATION WITH SMARTPHONE

Izvleček

The doctoral thesis deals with localization in indoor environment by using a smartphone. The latter has in a way become an indispensable tool of modern man, due to, among other things, the ever-increasing role in the field of personal navigation systems. Indoor localization is currently the subject of numerous studies and projects since none of the existing positioning systems have been established in such a way as the global navigation satellite systems for localization and navigation in the outdoor environment. The reasons for this lie in the high cost of precision positioning systems and in the poor performance of affordable systems. A new indoor positioning system may come into wider use if a compromise is reached, i.e. when sufficient accuracy and precision of localization are provided for a relatively low price. Modern smartphones are equipped with numerous sensors (inertial sensors, camera, barometer) and communications modules (WiFi, Bluetooth, NFC), which enable the implementation of various localization algorithms. To exploit the potential of modern mobile devices as much as possible, we have developed three different localization systems, namely visual localization, inertial navigation system and radio localization. Within the visual localization a visual odometry algorithm was implemented on a smartphone, where it can run in real time in two separate threads. On inertial navigation system a step counter (pedometer) and a digital compass, which are based on the use of accelerometer, gyroscope and magnetometer, were implemented for the purpose of dead reckoning. Since visual odometry as well as the inertial navigation system are sensitive to external disturbances, both localization systems were combined with the extended Kalman filter. In this way, an accurate and robust relative localization system which enables determining the position relative to a known starting point was obtained. In order to determine global positions in indoor environment, we undertook the development of radio localization, under which we tested several different methods, namely trilateration, fingerprint-based method and particle swarm optimization, which can operate with analysis of measurement of Bluetooth signals’ strengths. For the needs of the operation of aforementioned methods, we built a non-linear, as well as fuzzy models, which describe the change in signals’ strengths as a function of the distance to the transmitters. The developed relative localization system played a key role at measurement acquisition on which the models were built, since signals’ strengths as a function of the distance to the transmitters can simply be obtained by its use. The best localization results were obtained by using the fuzzy models and the fingerprint-based method. In this case 53 % of the position errors were smaller than 0.5 m and 99 % of the position errors were smaller than 1 m. In order to get even better results of the global localization, a fusion of the global positioning system based on Bluetooth fingerprints and relative localization system, which consists of visual odometry and inertial navigation system, was implemented. By combining these two systems, the errors of the global positions were reduced, since in this case more than 80 % of the errors were smaller than 0.5 m. With excellent results many doors open for the developed localization system, as it can be used in guiding autonomous mobile systems or people inside buildings.

• Ključne besede: Localization, fusion, odometry, camera, inertial sensors, Kalman filter, pedometer, digital compass, Bluetooth, fingerprints, smartphone, fuzzy models, pedestrian