Till denna undersökning har en artefakt i form av en spelprototyp skapats där olika labyrinter används i samband med panorerade röstkommandon för att undersöka auditiv navigation. Det som mäts är tid och antal misstag som görs under labyrinterna som sedan jämförs mellan tre grupper som navigeras med antingen mono, korrekt panorering eller inkorrekt panorering på röstkommandona.Då navigation främst använder visuell information bidrar denna undersökning med forskning kring hur röst och panorering kan användas till auditiv navigation. På grund av att röst är ett vanligt och effektivt kommunikationssätt är det ett enkelt verktyg att bruka i vardagen. Resultaten tyder på att korrekt panorering ledde till färre misstag jämfört med de andra panoreringarna. Däremot uppstod ingen större skillnad tidsmässigt mellan panoreringarna.Denna spelprototyp skulle kunna utvecklas till spel i form av “Audio Games” eller “Serious Games” genom att implementera ytterligare funktioner som kan höja underhållningsfaktorn eller utmaningen i lärandet.

<p>Most people are familiar with the BRIO labyrinth game and the challenge of guiding the ball through the maze. The goal of this project was to use this game to create a platform for evaluation of control algorithms. The platform was used to evaluate a few different controlling algorithms, both traditional automatic control algorithms as well as algorithms based on online incremental learning.</p><p>The game was fitted with servo actuators for tilting the maze. A camera together with computer vision algorithms were used to estimate the state of the game. The evaluated controlling algorithm had the task of calculating a proper control signal, given the estimated state of the game.</p><p>The evaluated learning systems used traditional control algorithms to provide initial training data. After initial training, the systems learned from their own actions and after a while they outperformed the controller used to provide initial training.</p>

Most people are familiar with the BRIO labyrinth game and the challenge of guiding the ball through the maze. The goal of this project was to use this game to create a platform for evaluation of control algorithms. The platform was used to evaluate a few different controlling algorithms, both traditional automatic control algorithms as well as algorithms based on online incremental learning. The game was fitted with servo actuators for tilting the maze. A camera together with computer vision algorithms were used to estimate the state of the game. The evaluated controlling algorithm had the task of calculating a proper control signal, given the estimated state of the game. The evaluated learning systems used traditional control algorithms to provide initial training data. After initial training, the systems learned from their own actions and after a while they outperformed the controller used to provide initial training.