Lightweight Inertial Guidance and Mapping Algorithm

Accurate indoor positioning remains a significant challenge due to poor permeability of Global Navigation Satellite System (GNSS) signals within buildings, rendering traditional methods ineffective. Alternatives often suffer from limitations, hindering their practicality in constrained platforms. We propose a lightweight and robust deep learning method for pedestrian dead reckoning, termed LiDRNet.We used the Neutral Ordinary Differential Equation (NeuralODE) technique, operated on a Heading Agnostic Coordinate Frame and apply back-propagation on velocity loss to improve the effectiveness of our model. We then predict motion trajectories from raw IMU data. Benchmarking LiDRNet against other State-Of-The-Art shows a reduction of parameter count by 7 times while achieving an average trajectory error of 4 meters.LiDRNet is well-suited for deployment on resource-constrained edge devices for accurate real-time dead reckoning. Enabling on-edge accurate indoor positioning allows our approach to significantly enhance navigation, which can improve navigation assistance, asset tracking, and emergency response in indoor settings.