Deep Neural Network for Real-Time Autonomous Indoor Navigation
This addresses the problem of lightweight, GPS-free navigation for MAVs in indoor environments, but it is incremental as it applies existing deep learning methods to a specific domain.
The paper tackles autonomous indoor navigation for Micro Aerial Vehicles (MAVs) by using a deep learning model with a single camera to mimic an expert pilot, achieving real-time performance in diverse indoor locations.
Autonomous indoor navigation of Micro Aerial Vehicles (MAVs) possesses many challenges. One main reason is that GPS has limited precision in indoor environments. The additional fact that MAVs are not able to carry heavy weight or power consuming sensors, such as range finders, makes indoor autonomous navigation a challenging task. In this paper, we propose a practical system in which a quadcopter autonomously navigates indoors and finds a specific target, i.e., a book bag, by using a single camera. A deep learning model, Convolutional Neural Network (ConvNet), is used to learn a controller strategy that mimics an expert pilot's choice of action. We show our system's performance through real-time experiments in diverse indoor locations. To understand more about our trained network, we use several visualization techniques.