Physics-Regularized Machine Learning for Proprioceptive Vehicle Localization Using Onboard Sensors

2026-07-06

AI Summary

This work addresses the significant degradation in localization accuracy of vehicle-mounted sensors under impaired perception conditions, such as GNSS signal outages. To tackle this challenge, the authors propose the PRML2 framework, which enables end-to-end training through a differentiable Kalman filter to fuse IMU and onboard sensor data. A physics-informed regularization mechanism is introduced to embed motion model priors directly into the learning process, thereby enhancing the consistency, accuracy, and cross-scenario generalization of pose estimation. Evaluated on public benchmarks, the method outperforms existing approaches and demonstrates robustness and real-time performance on a newly curated dataset featuring low-adhesion road conditions.

Abstract

Accurate and robust localization is essential for autonomous mobility systems in real-world environments. While fusing Inertial Measurement Unit (IMU) data with satellite-based correction signals provides precise vehicle pose estimates, performance degrades substantially during outages. Recent studies indicate that Machine Learning (ML) can improve IMU-based proprioceptive localization, highlighting untapped potential for onboard sensors readily available in production vehicles. This paper introduces Physics-Regularized Machine Learning for Localization (PRML2), a hybrid framework that combines the complementary strengths of Kalman filtering and data-driven learning to estimate vehicle pose directly from onboard sensors. A key aspect of PRML2 is its physics-regularized learning, enabled by end-to-end training of an ML model through a differentiable Kalman filter. This improves consistency with vehicle motion models, thereby enhancing both localization accuracy and generalization across driving conditions. We evaluate the performance limits of ML-enhanced onboard odometry on a publicly available dataset and show that PRML2 achieves superior localization accuracy and demonstrates real-time capability. This work also introduces a novel dataset to support vehicle localization research under low-friction conditions. The proposed framework provides a robust and cost-effective solution for vehicle localization under degraded sensing conditions by integrating learning with physics-based priors.

Problem

• vehicle localization
• proprioceptive sensing
• IMU
• degraded sensing conditions
• onboard sensors

Innovation

• physics-regularized learning
• differentiable Kalman filter
• proprioceptive localization
• onboard sensor fusion
• ML-enhanced odometry