Vinsamlegast notið þetta auðkenni þegar þið vitnið til verksins eða tengið í það: http://hdl.handle.net/1946/35738
Indoor positioning systems (IPS) are very commonly used in robotics and are essential for many autonomous operations as GPS can be unreliable indoors and is therefore infeasible for such applications. In this paper we lay the groundwork for a pedestrian positioning system, which can map indoor spaces and track pedestrian migrations inside buildings using mobile phones. The IPS revolves around using known methods in robotics, such as simultaneous localization and mapping(SLAM), to see if they can be adapted to work using only the sensors available in mobile phones. Research into phones sensors and mainly the accelerometer will be done to figure out if the sensor values returned by a modern mobile phone are up to the task of mapping of pedestrian movements accurately. This will be done by both plotting the movements the accelerometer calculates to see how accurate they are and creating a machine learning algorithm to classify movement patters such as walking and running. The results from testing the sensors did not match what would be expected, likely due to the algorithms used by the mobile phone. Using the raw sensor data and creating an algorithm might prove to give different results. Classifying movements worked with around 92-95% accuracy but due to COVID19 gathering of data became very hard so there might be over-fitting in the results. This research mainly shows what does notwork when trying to create a indoor positioning system using mobile phones rather then what does. This research shows that using a mobile phone positioning system to create a IPS has it’s limits. This report eliminates many options and does not find the ultimate solution. But is hopefully a step towards a pedestrian SLAM. We will contrast this problem with its counterpart in robotics and discuss the added complexities and propose our possible solutions to mitigate them.