Coarse Global Visual Localization of a Mobile Robot

Localization, which is the ability of a mobile robot to estimate its position within its environment, is a key capability for autonomous operation of any mobile robot. This thesis presents a system for indoor coarse and global localization of a mobile robot based on visual information. The system is based on image matching and uses SIFT features as natural landmarks. Features extracted from training images arestored in a database for use in localization later. During localization an image of the scene is captured using the on-board camera of the robot, features are extracted from the image and the best match is searched from the database. Feature matching is done using the k-d tree algorithm. Experimental results showed that localization accuracy increases with the number of training features used in the training database, while, on the other hand, increasing number of features tended to have a negative impact on the computational time. For some parts of the environment the error rate was relatively high due to a strong correlation of features taken from those places across the environment.

Mobile robot localization using sonar ranging and wlan intensity maps

 Main goal of this thesis was to implement a localization system which uses sonars and WLAN intensity maps to localize an indoor mobile robot. A probabilistic localization method, Monte Carlo Localization is used in localization. Also the theory behind probabilistic localization is explained. Two main problems in mobile robotics, path tracking and global localization, are solved in this thesis. Implemented system can achieve acceptable performance in path tracking. Global localization using WLAN received signal strength information is shown to provide good results, which can be used to localize the robot accurately, but also some bad results, which are no use when trying to localize the robot to the correct place. Main goal of solving ambiguity in office like environment is achieved in many test cases.

Multi-sensor Simultaneous Localization and Mapping

Simultaneous localization and mapping(SLAM) is a very important problem in mobile robotics. Many solutions have been proposed by different scientists during the last two decades, nevertheless few studies have considered the use of multiple sensors simultane¬ously. The solution is on combining several data sources with the aid of an Extended Kalman Filter (EKF). Two approaches are proposed. The first one is to use the ordinary EKF SLAM algorithm for each data source separately in parallel and then at the end of each step, fuse the results into one solution. Another proposed approach is the use of multiple data sources simultaneously in a single filter. The comparison of the computational com¬plexity of the two methods is also presented. The first method is almost four times faster than the second one.

Localization, Frequency, and Functions of Filled Pauses: Five American Politicians’ Use of er and erm in the Talk Show Larry King Live

Tämän pro gradu– tutkielman tavoitteena oli testata täytettyjen taukojen (er ja erm) esiintymistiheyttä, sijaintia kieliopillisessa rakenteessa sekä funktioita Kjellmerin (2003) korpus-tutkimuksessa. Materiaalina käytin viiden yhdysvaltalaisen poliitikon puhetta keskusteluohjelmasta Larry King Live. Tutkimuksessani sovelsin Kjellmerin tutkimusmenetelmiä, joita muokkasin huomattavasti suppeampaan materiaaliini sopiviksi. Lähestymistapani oli täten induktiivinen toisin kuin testatussa tutkimuksessa. Materiaalini oli tarkoituksellisesti rajattu, sillä halusin selvittää, kuvaavatko Kjellmerin laajaan materiaaliin perustuvat tutkimustulokset myös täytettyjen taukojen käyttöä suppeammassa materiaalissa. Materiaalini (kokonaisuudessaan 101 minuuttia) transkriboin ortografisesti. Analyysissäni arvioin täytettyjen taukojen esiintymistiheyden puhujakohtaisesti ja koko ryhmälle suhteuttamalla täytettyjen taukojen lukumäärän kokonaissanamäärään. Tämän jälkeen tein perinteisen kielioppianalyysin rakenteista, joita edeltää tai joissa esiintyy täytetty tauko, ja täytettyjen taukojen sijainnin perusteella luokittelin ne sana-, lauseke-, ja lausetasolle. Lopuksi analysoin täytettyjen taukojen käyttöä soveltaen Kjellmerin ehdottamia funktioita (hesitaatio, vuorottelujäsennyksen merkitseminen, huomion herättäminen ja kontaktin luominen, korostus ja korjaus) ja niiden piirteitä omaan materiaaliini. Tutkimukseni perusteella täytetyt tauot esiintyvät tutkitun viiden poliitikon puheessa suhteellisen usein. Puhujakohtaiset eroavaisuudet olivat kuitenkin huomattavat. Kieliopillisen luokitteluni mukaan sana-, lauseke- ja lausetasot eivät täysin kuvaa täytettyjen taukojen sijoittumista, sillä täytetyt tauot edelsivät mm. määre-lauseita, jotka eivät vastaa lausetasoa englannin kielessä. Materiaalini funktioanalyysi osoitti, että täytetyt tauot yleensä vastaavat yhtä tai useampaa Kjellmerin ehdottamaa funktioita. Lisäksi tutkimukseni mukaan täytetyillä tauoilla on ainakin yksi rakenteellinen funktio. Analyysini perusteella Kjellmerin tutkimustulokset ovat siis pääosin sovellettavissa suppeampaan materiaaliin. Puutteiksi hänen tutkimuksessaan osoittautuivat funktioanalyysille tärkeän kontekstuaalisen informaation puute sekä keskittyminen täytettyihin taukoihin, jotka esiintyvät vain tietyissä kielioppirakenteissa. Yleisesti voin tutkimukseni pohjalta todeta, että täytetyt tauot ovat vielä vajaasti tunnettuja ja että kieliopillisen sijoituksen ja funktioiden lisätutkimus on tarpeellista.

Two-dimensional atom localization and Raman cooling of tripod-type atoms

Both atom localization and Raman cooling, considered in the thesis, reflect recent progress in the area of all-optical methods. We focus on twodimensional (2D) case, using a four-level tripod-type atomic scheme for atom localization within the optical half-wavelength as well as for efficient subrecoil Raman cooling. In the first part, we discuss the principles of 1D atom localization, accompanying by an example of the measurement of a spontaneously-emitted photon. Modifying this example, one archives sub-wavelength localization of a three-level -type atom, measuring the population in its upper state. We go further and obtain 2D sub-wavelength localization for a four-level tripod-type atom. The upper-state population is classified according to the spatial distribution, which in turn forms such structures as spikes, craters and waves. The second part of the thesis is devoted to Raman cooling. The cooling process is controlled by a sequence of velocity-selective transfers from one to another ground state. So far, 1D deep subrecoil cooling has been carried out with the sequence of square or Blackman pulses, applied to -type atoms. In turn, we discuss the transfer of atoms by stimulated Raman adiabatic passage (STIRAP), which provides robustness against the pulse duration if the cooling time is not in any critical role. A tripod-type atomic scheme is used for the purpose of 2D Raman cooling, allowing one to increase the efficiency and simplify the realization of the cooling.

Indoor Localization Solutions for a Marine Industry Augmented Reality Tool

In this report are described means for indoor localization in special, challenging circum-stances in marine industry. The work has been carried out in MARIN project, where a tool based on mobile augmented reality technologies for marine industry is developed. The tool can be used for various inspection and documentation tasks and it is aimed for improving the efficiency in design and construction work by offering the possibility to visualize the newest 3D-CAD model in real environment. Indoor localization is needed to support the system in initialization of the accurate camera pose calculation and auto-matically finding the right location in the 3D-CAD model. The suitability of each indoor localization method to the specific environment and circumstances is evaluated.