PiDR: Physics-Informed Inertial Dead Reckoning for Autonomous Platforms

TL;DR

PiDR introduces a physics-informed neural network for inertial dead reckoning in GNSS-denied environments by embedding strapdown INS dynamics as residuals in training. The method jointly optimizes data fidelity and physics consistency, enabling accurate navigation from IMU data with limited ground-truth supervision. Across mobile robots and autonomous underwater vehicles, PiDR yields substantial improvements in trajectory accuracy and drift mitigation compared to purely model-based and prior PINN approaches, including ~29% and ~94% gains in key metrics. The approach is lightweight, generalizes across platforms, and is suitable for real-time deployment on resource-constrained systems.

Abstract

A fundamental requirement for full autonomy is the ability to sustain accurate navigation in the absence of external data, such as GNSS signals or visual information. In these challenging environments, the platform must rely exclusively on inertial sensors, leading to pure inertial navigation. However, the inherent noise and other error terms of the inertial sensors in such real-world scenarios will cause the navigation solution to drift over time. Although conventional deep-learning models have emerged as a possible approach to inertial navigation, they are inherently black-box in nature. Furthermore, they struggle to learn effectively with limited supervised sensor data and often fail to preserve physical principles. To address these limitations, we propose PiDR, a physics-informed inertial dead-reckoning framework for autonomous platforms in situations of pure inertial navigation. PiDR offers transparency by explicitly integrating inertial navigation principles into the network training process through the physics-informed residual component. PiDR plays a crucial role in mitigating abrupt trajectory deviations even under limited or sparse supervision. We evaluated PiDR on real-world datasets collected by a mobile robot and an autonomous underwater vehicle. We obtained more than 29% positioning improvement in both datasets, demonstrating the ability of PiDR to generalize different platforms operating in various environments and dynamics. Thus, PiDR offers a robust, lightweight, yet effective architecture and can be deployed on resource-constrained platforms, enabling real-time pure inertial navigation in adverse scenarios.

Figures (7)

• Figure 1: Training pipeline of our proposed PiDR framework.
• Figure 2: ROSbot XL mounted with DOT IMUs and MRU-P.
• Figure 3: ROSbot XL trajectories used for training of PiDR (Trajectories R1 and R4).
• Figure 4: Snapir AUV during the mission in the Mediterranean Sea, Haifa, Israel.
• Figure 5: AUV trajectories in the NED frame. Trajectories T1, T2, T3, T5, T6, T7, and T8 belong to the training set, and T10, T11, and T13 are part of the testing set.