MoRPI-PINN: A Physics-Informed Framework for Mobile Robot Pure Inertial Navigation

2025-07-24

AI Summary

To address severe drift in pure inertial navigation under GNSS- and vision-denied conditions, this paper proposes a physics-informed neural network (PINN)-driven lightweight inertial navigation framework. Methodologically: (i) a serpentine sliding maneuver is designed to enhance the signal-to-noise ratio of inertial measurements; (ii) rigid-body kinematic and dynamic equations are incorporated as hard physical constraints into network training; and (iii) a compact neural architecture enables efficient edge deployment. Experiments across multiple mobile robot platforms demonstrate over 85% improvement in localization accuracy, significantly reduced drift rate, high real-time performance, and strong cross-platform generalizability. The core contribution lies in the first joint modeling of executable motion excitation and embedded physical constraints—enabling robust, fully autonomous pure inertial navigation without external references.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Low Level & Physics-based Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

A fundamental requirement for full autonomy in mobile robots is accurate navigation even in situations where satellite navigation or cameras are unavailable. In such practical situations, relying only on inertial sensors will result in navigation solution drift due to the sensors' inherent noise and error terms. One of the emerging solutions to mitigate drift is to maneuver the robot in a snake-like slithering motion to increase the inertial signal-to-noise ratio, allowing the regression of the mobile robot position. In this work, we propose MoRPI-PINN as a physics-informed neural network framework for accurate inertial-based mobile robot navigation. By embedding physical laws and constraints into the training process, MoRPI-PINN is capable of providing an accurate and robust navigation solution. Using real-world experiments, we show accuracy improvements of over 85% compared to other approaches. MoRPI-PINN is a lightweight approach that can be implemented even on edge devices and used in any typical mobile robot application.

Problem

• Improving mobile robot navigation without satellite or cameras
• Reducing inertial sensor drift via physics-informed neural networks
• Enhancing accuracy in pure inertial navigation systems

Innovation

• Physics-informed neural network for robot navigation
• Slithering motion to enhance inertial signals
• Lightweight framework suitable for edge devices