Visual Aids for the blind people is an important subject. Apparently visually impaired individuals get impeded by certain hurdles in everyday life. This work proposes an indoor navigation system for visually impaired people. In particular, the goal of this study is to develop a robust, independent and portable aid to assist a user to navigate familiar as well as unfamiliar areas. The algorithm uses the data from Microsoft Xbox Kinect 360 which makes a 3D map of the indoor areas and detects the depth and estimates the relative distance and angle to an obstacle/human. To ensure the accuracy, Kinect tool is enabled with a colour camera to capture real-time details of surroundings which are then processed accordingly. Besides, the developed aid makes the user aware of environmental changes through a Bluetooth enabled headphones used as audio output device. The trials were conducted on six blindfolded volunteers who successfully navigated across various locations in the university campus such as classrooms, hallways, and stairs. Moreover, the user could also track a particular person through output generated from processed images. Hence, the work suggests a significant improvement for existing visual aids which may be very helpful in customisation as well as the adaptability of these devices.

No description available.

Nach einer Betrachtung der bestehenden Ansätze zur automatischen Graphgenerierung wurde eine Möglichkeit entwickelt, auf der Grundlage von OpenStreetMap-Innenraumkarten mit Hilfe einer bereits existierenden Implementierung des Straight Skeleton in Python automatisch Wege zu berechnen und diese wieder ins OpenStreetMap-Format zu überführen.:1. Einleitung 2. Überblick zur aktuellen Forschung 3. Anwendung des Straight Skeleton auf OpenStreetMap-Daten 3.1. Polyskel 3.2. Einlesen der Daten und Extrahieren der Türen und Räume 3.3. Kombination von Türen und Räumen 3.4. Generierung von Wegen mit Hilfe von polyskel 3.5. Kurze Wege zu längeren zusammenfassen 3.6. Wege vereinfachen 3.7. Wege im OpenStreetMap-Format speichern 4. Fazit und Ausblick Literaturverzeichnis Anhang

Pastarųjų metų technologinė puslaidininkinių trimačių mikro struktūrų gamybos procese pažanga leidžia sukurti vis tikslesnius ir patikimesnius tokio tipo elektromechaninius jutiklius. Gerėjanti tokio tipo jutiklių kokybė atveria naujas jų panaudojimo galimybes. Vena jų – vidaus navigacinė sistema. Tokio tipo sistema reikalauja tikslių pagreičio, kampinio greičio ir kitokio tipo duomenų judėjimo trajektorijai nustatyti. Šiame darbe yra apžvelgtos pagrindinės problemos su kuriomis susiduriama kuriant inercines vidaus navigacines sistemas. Apžvelgti, patikrinti ir pasiūlyti alternatyvūs šių problemų sprendimo metodai. Mechaninių jutiklių taikymo navigacijai patalpų viduje tyrimas. Magistro baigiamasis darbas elektronikos inžinerijos magistro laipsniui. Vilniaus Gedimino technikos universitetas. 2014 m. / Recent technological improvements in micromachining process allows to produce smaller, cheaper and more accurate MEMS sensors. Better accuracy/size ratio increases MEMS sensors application field. One of most precise sensors looking for field is MEMS based indoor navigation system, which requires precise accelerometer/gyros, to ensure error free estimated position. Current gyros and accelerometers are much less precise than standard laser based gyros and bulk accelerometers. This work describes the main problems of using MEMS for inertial navigation and possible solutions, to minimize estimated position error. Research of MEMS application for indoor navigation. Master thesis for electronics engineer master degree. Vilnius Gediminas Technical University. Vilnius 2014 m.

This project examines the level of accuracy that can be achieved in precision positioning by using built-in sensors in an Android smartphone. The project is focused in estimating the position of the phone inside a building where the GPS signal is bad or unavailable. The approach is sensor-fusion: by using data from the device’s different sensors, such as accelerometer, gyroscope and wireless adapter, the position is determined. The results show that the technique is promising for future handheld indoor navigation systems that can be used in malls, museums, large office buildings, hospitals, etc.

The popularity of wireless sensor networks is constantly increasing, both for use instatic machine to machine environments as well as dynamic environments wherethe sensor nodes are carried by humans. Higher demands are put on real-timetracking algorithms of the sensor nodes, both in terms of accuracy and speed. This thesis addresses the issue of tracking persons wearing small sensor nodeswithin a radio network. Focus lies on fusing sensor data in an efficient way withconsideration to the computationally constrained sensor nodes. Different sensorsare stochastically modelled, evaluated, and fused to form an estimate of the person’sposition. The central approach to solve the problem is to use a dead reckoning methodby detecting steps taken by the wearer combined with an Inertial MeasurementUnit to calculate the heading of the person wearing the sensor node. To decreasethe unavoidable drift which is associated with a dead reckoning algorithm, a mapis successfully fused with the dead reckoning algorithm. The information from themap can to a large extent remove drift. The developed system can successfully track a person wearing a sensor nodein an office environment across multiple floors. This is done with only minorknowledge about the initial conditions for the user. The system can recover fromdivergence situations which increases the long term reliability. / Intresset för trådlösa sensornätverk ökar konstant, såväl för statiska maskintill-maskintillämpningar som för dynamiska miljöer där sensornoderna är burnaav människor. Allt högre krav ställs på positioneringsalgoritmer för sensornätverken,där både hög precision och låg beräkningstid ofta är krav. Denna rapport behandlar problemet med att bestämma positionen av personburnasensornoder. Rapportens fokus är att effektivt kombinera sensordatamed hänsyn till sensornodernas begränsade beräkningskapacitet. Olika sensorermodelleras stokastiskt, utvärderas och kombineras för att forma en skattning avsensornodens position. Den huvudsakliga metoden för att lösa problemet är att dödräkna sensornodbärarenssteg kombinerat med kompass och tröghetssensorer för att skattastegets riktning. En karta över byggnaden används för att reducera den annarsoundvikliga drift som härrör från dödräkning. Informationen från kartan visarsig i stor utsträckning kunna reducera den här driften. Det utvecklade systemet kan följa en person genom en kontorsmiljö somsträcker sig över flera våningsplan. Detta med enbart lite information om personensinitiala position. Systemet kan även återhämta sig från situationer däralgoritmen divergerar vilket ökar systemets pålitlighet på lång sikt.

With an increasing need for greater traffic safety, there is an increasing demand for means by which solutions to the traffic safety problem can be studied. The purpose of this thesis is to investigate the feasibility of using an autonomous indoor navigation system as a component in a demonstration system for studying cooperative vehicular scenarios. Our method involves developing and evaluating such a navigation system. Our navigation system uses a pre-existing localization system based on passive RFID, odometry and a particle filter. The localization system is used to estimate the robot pose, which is used to calculate a trajectory to the goal. A control system with a feedback loop is used to control the robot actuators and to drive the robot to the goal.   The results of our evaluation tests show that the system generally fulfills the performance requirements stated for the tests. There is however some uncertainty about the consistency of its performance. Results did not indicate that this was caused by the choice of localization techniques. The conclusion is that an autonomous navigation system using the aforementioned localization techniques is plausible for use in a demonstration system. However, we suggest that the system is further tested and evaluated before it is used with applications where accuracy is prioritized.

No description available.

No description available.

Because of the limitation of GPS indoors there is a demand for alternative methods to accurately determine both position and orientation. Previous attempts at positional tracking has required an infrastructure of hardware and sensors to provide the path of an object or person. This is not a mobile solution to a mobile problem. This project aims to answer the question if it is possible to use an Inertial measurement unit sensor for this application. It will also create a prototype device that will demonstrate the capabilities of the proposed method. The goal of the project is to reach an accuracy of ±20 cm for position and ±5 degrees for rotation. A Kalman filter will be used to filter the output from the sensor in order to get more stable and accurate readings. The results show that it is possible to determine position of ±20 cm up to 100 cm with the proposed method. An inertial measurement unit is capable of measuring rotation accuracy of ±5 degrees and a prototype has been designed and manufactured to demonstrate the method.