Magnus Andersson

Positioning and Navigation of a Robot Lawn Mover Using an ID-Marker

mangans84 — Fri, 11 Jun 2010 20:24:42 +0000

In this project a web camera is used to view over a lawn, by using a chessboard like reference object placed somewhere on the lawn the image can then translated into a bird’s view, i.e. a from above view, of the lawn.

The bird’s view is then imported to a user-interface, in which the user can control which parts of the lawn that are to be cut and not.
A path planning algorithm then uses the painted bird’s view image to calculate a path for the robot lawn mover.
A continuously flow of images from the web camera are then used to calculate the position and heading of the robot lawn mover.
To be able to find the position the lawn mover it is equipped with an ID-marker, which can be identified in the bird’s view image.
This results in a position with respect to the “Chessboard”, the position of the robot lawn mover can then be translated and used in the navigation system.
The robot lawn mover then follows the calculated path until the lawn is cut and returns to its original position.
In an indoor environment the accuracy of the positioning system were found to be +-5 cm up to a distance of abut 4 m. Differences in height between the ID-marker and the chessboard reference object resulted in in positioning errors above +-5 cm. A good enough path-planning algorithm were implemented and were found never to miss any parts of the cutting area. A user-interface was created, which in a user friendly way allows the user to decide where the robot lawn mover should cut and not. It is also possible to simulate the whole system in the user interface.
A prototype testing robot was successfully implemented, which made it possible to test the system in a real environment.
Project Report

Eye Tracking

mangans84 — Fri, 11 Jun 2010 19:45:13 +0000

The purpose of this project is to locate the eyes of humans in photos. If this is possible then the algorithm is also evaluated in real-time using a standard web camera. The algorithm is evaluated on different persons and in four different environments to determine its performance.

It works by using several image processing methods such as color discrimination, thresholding, different transformations, ﬁltering methods and a neural network. All methods were implemented to achieve as short execution times as possible. The algorithm was ﬁnally able to identify eyes, in good conditions, with a probability of 78.75 %. If dark pictures with difficult backgrounds were used, the probability of identifying the eyes were decreased substantially. The algorithm was found to work best with an artiﬁcial feed forward neural network, even though in some environments the network had negative effects on the result. If bright enough photos were used the algorithm was fast enough to be used in (soft) real-time with approximately 20 frames per second.

Project Report

Interaction Design

mangans84 — Fri, 11 Jun 2010 19:13:02 +0000

The aim of this course was to understand how the interaction between man and machine affects the work results, i.e. mental and physical effects.

Project, the task was to investigate how Gothenburgs treatment plant could be improved.

Gryaab Interaction Design Project Report – (In Swedish)

Home Assignments

Assignment 1 – (In Swedish)

Assignment 2 – (In Swedish)

Particle Swarm Optimization

mangans84 — Mon, 21 Dec 2009 12:44:06 +0000

Uses a swarm of particles to find a minimum of a function. The particles velocities and positions are updated every iteration. In the end of the optimization the particles are more and more attracted to the best particle.

Particle swarm optimization

Matlab Code – Particle Swarm Optimization Change extension to .zip to open!

FeedForward Neural Network learned by a GA

mangans84 — Mon, 21 Dec 2009 12:15:23 +0000

Uses a Genetic Algorithm to learna a FeedForward Neural Network how to solve a 3-parity XOR function i.e. if the amount of ones is odd, the function should return 1. The FFNN has three inputs and uses three hidden neurons and one output neuron to return the output.

FeedForward Neural Network

Matlab Code – FFNN Change extension to .zip to open!

X₁	X₂	X₃	FFNN Output
0	0	0	4.5263e-05
0	0	1	1.0000
0	1	0	1.0000
0	1	1	4.6127e-05
1	0	0	1.0000
1	0	1	4.4731e-05
1	1	0	1.3068e-07
1	1	1	1.0000

The Travelling Salesman Problem

mangans84 — Mon, 21 Dec 2009 12:06:11 +0000

Uses a Genetic Algorithm to find the shortest path, if you are to visit every city once and only once. The GA uses Swap Mutation, Ordered Crossover and Tournament Selection.

The traveling salesman problem

Matlab Code – Travelling Salesman Problem – Change extension to .zip to open!

Basic Genetic Algorithm

mangans84 — Mon, 21 Dec 2009 12:04:10 +0000

Uses a Basic Genetic Algorithm to minimize a function. The GA uses Single Point Crossover, Mutation and Tournament Selection.

Basic GA Program

Matlab Code – Basic Genetic Algorithm -Change extension to .zip to open!

Sustainable Painting

mangans84 — Sun, 13 Dec 2009 17:53:41 +0000

Sustainable Painting – our contribution to saving the environment

The Sustainable Painting is a dynamic painting which changes its picture depending on the household´s energy consumption. It will help the user to reflect upon how much energy they use in their household. The basic idea is that electricity, water and trash consumption are used as input to calculate the energy consumption of a household. The painting reacts to the different levels of consumption and displays different pictures depending on the usage of energy.

The objective of this ubiquitous computing project is to directly increase people’s awareness of their energy consumption in the household by making visible what is normally hidden. By increasing people’s awareness of their energy usage we hope to help encourage less consumption and ultimately achieve a more sustainable society. The project will introduce a new way to visualize energy consumption in households.

Sustainable Painting – vårt bidrag till att rädda världen (In Swedish)

Sustainable Painting är en dynamisk målning som ändrar delar av motivet beroende på ett hushålls energiförbrukning. Det kommer att hjälpa användaren att reflektera över hur mycket energi de använder i hushållet, och vilka saker i hemmet som drar mest energi. Grundtanken är att el-, vatten- och skräpkonsumtion används som underlag för att beräkna energiförbrukningen i ett hushåll. Målningen reagerar på olika förbrukning och visar olika bilder beroende på användningen av energi.

Målet med detta ubiquitous computing projektet är att öka människors medvetenhet om sin energiförbrukning i hushållet genom att synliggöra detta. Genom att öka människors medvetenhet om sin energianvändning hoppas vi kunna bidra till att uppmuntra mindre konsumtion och i slutändan uppnå ett mer hållbart samhälle. Sustainable Painting bidrar med ett nytt sättatt visualisera energikonsumtion.

You can find more information, videos, pictures etc on this link:

Sustainable Painting Homepage

Compose:Me

mangans84 — Sun, 15 Nov 2009 16:45:15 +0000

Compose:Me is designed as a toy to help kids learn music, recognize notes and compose some simple music.

The device was designed to look like a piece of sheet music (although we did not end up drawing the lines of the staff in our prototype) where you can place magnets that function as notes. The notes are then automatically played in a loop and can be changed in realtime.

There are eight different columns where you can place notes (magnets) and you can place either one or two notes per column. We are working on increasing this number so that chords can be played. Currently the odd rows correspond to the notes EGBDF and the even rows correspond to FACE. The LEDs at the top of the columns indicate which column of notes are being played. At the bottom of each column is a switch that can change the length of the note between short or long. The overall tempo can be changed with the rightmost slider and the cycle speed of the LEDs changes to match the tempo. The device has internal speakers but can also play the music on earphones or external speakers. The volume is controlled by the leftmost slider.

After presenting this project in our Physical computing course we went to the Valand School of Fine Arts to present it at an experimental music exhibition on October 16, 2009.

We received some very positive feedback and it has encouraged us to keep on working on the device. Our first goal in improving Compose:Me is to upgrade it so it can handle more than two tones at a time. Other ideas we have are to create similar devices that can interact with each other and make Compose:Me communicate with a computer to be able to play more complex sound with it.

David and Eric presenting Compose:Me at the Valand School of Fine Arts with our biggest fan Alex.

Mobil Navigation with Artificial Potential Fields

mangans84 — Mon, 11 May 2009 16:52:32 +0000

The purpose of this project was to create a path-planning algorithm, a navigation method and to avoid any obstacles by using sonars. As path-planning/navigation method Artificial Potential Fields were used. No optimal local minima solution could be found, due to this sub-goals had to be used.

Mobile Robot Project – Download, change extension to .zip and unzip (Matlab).