Using gyroscopic sensors data with artificial neural networks for junction detection

Gyroscopic sensors are frequently used in automotive navigation systems in order to improve location estimation by using the angle information to supplement other sensors such as GPS location data. Gyroscopic sensors can become a major sensor for location estimation for automobiles or autonomous robots for situations where GPS data are inaccurate or cannot be received. In this paper, we assume a situation where GPS data cannot be received, e.g. in a building or tunnel, and gyroscopic sensors and speedometer are the only available sensors for location estimation. We propose applying artificial neural networks to gyroscopic sensor data in order to estimate the current location of the automotive device. We conducted an experiment using an electric model railroad to verify the accuracy of the proposed method.