OdoNet: Untethered Speed Aiding for Vehicle Navigation Without Hardware Wheeled Odometer

Odometer has been proven to significantly improve the robustness and accuracy of Global Navigation Satellite System/Inertial System (GNSS/INS) integrated vehicle navigation in GNSS-denied environments. However, odometer is inaccessible many applications, especially for aftermarket devices smartphones. To apply forward speed aiding without hardware wheeled odometer, we propose OdoNet, an untethered one-dimensional Convolution Neural Network (CNN)-based pseudo-odometer model learning from a single Inertial Measurement Unit (IMU). Dedicated experiments have conducted verify generalization capability precision OdoNet. The results indicate that IMU individuality, loads, road conditions little impact on while biases mounting angles may notably ruin Hence, data-cleaning procedure adopted effectively mitigate impacts angles. Compared processing mode using only non-holonomic constraint (NHC), by employing pseudo-odometer, positioning error reduced around 68%, percentage 74% odometer. In conclusion, proposed OdoNet can be employed as navigation.