Autonomous, self-navigating agents have been rising in popularity due to a push for a more technologically aided future. From cars to vacuum cleaners, the applications of self-navigating agents are vast and span many different fields and aspects of life. As the demand for these autonomous robotic agents has been increasing, so has the demand for innovative features, robust behavior, and lower cost hardware. One particular area with a constant demand for improvement is localization, or an agent's ability to determine where it is located within its environment. Whether the agent's environment is primarily indoor or outdoor, dense or sparse, static or dynamic, an agent must be able to have knowledge of its location. Many different techniques exist today for localization, each having its strengths and weaknesses. Despite the abundance of different techniques, there is still room for improvement. This research presents a novel indoor localization algorithm that fuses data from multiple sensors for a relatively low cost. Inspired by recent innovations in deep learning and particle filters, a fast, robust, and accurate autonomous localization system has been created. Results demonstrate that the proposed system is both real-time and robust against changing conditions within the environment.
Computer Engineering (MS)
Department, Program, or Center
Computer Engineering (KGCOE)
Lauzon, Jacob F., "Sensor Fusion and Deep Learning for Indoor Agent Localization" (2017). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus