ReNiL: Relative Neural Inertial Locator with Any-Scale Bayesian Inference

2025-08-08

AI Summary

Pedestrian inertial localization faces challenges including variable motion scales, unstable step frequencies, and inconsistent uncertainty modeling; existing learning-based methods suffer from limited generalizability and reliability due to reliance on fixed-length sliding windows. This paper proposes an uncertainty-aware end-to-end neural inertial localization framework. First, we introduce the Inertial Positioning Demand Point (IPDP) mechanism for context-driven sparse state estimation. Second, we design an Arbitrary-Scale Laplacian Estimator (ASLE), which integrates Bayesian regression with Laplacian displacement modeling to ensure cross-scale uncertainty consistency in Euclidean space. Third, we unify motion-aware pose filtering, block-wise self-supervised learning, and a dual-task network architecture. Evaluated on RoNIN-ds and our newly constructed WUDataset, our method achieves state-of-the-art performance in both localization accuracy and uncertainty calibration—outperforming TLIO, CTIN, and others—while reducing computational overhead, thereby demonstrating practicality and robustness for mobile and IoT applications.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Pedestrian inertial localization is key for mobile and IoT services because it provides infrastructure-free positioning. Yet most learning-based methods depend on fixed sliding-window integration, struggle to adapt to diverse motion scales and cadences, and yield inconsistent uncertainty, limiting real-world use. We present ReNiL, a Bayesian deep-learning framework for accurate, efficient, and uncertainty-aware pedestrian localization. ReNiL introduces Inertial Positioning Demand Points (IPDPs) to estimate motion at contextually meaningful waypoints instead of dense tracking, and supports inference on IMU sequences at any scale so cadence can match application needs. It couples a motion-aware orientation filter with an Any-Scale Laplace Estimator (ASLE), a dual-task network that blends patch-based self-supervision with Bayesian regression. By modeling displacements with a Laplace distribution, ReNiL provides homogeneous Euclidean uncertainty that integrates cleanly with other sensors. A Bayesian inference chain links successive IPDPs into consistent trajectories. On RoNIN-ds and a new WUDataset covering indoor and outdoor motion from 28 participants, ReNiL achieves state-of-the-art displacement accuracy and uncertainty consistency, outperforming TLIO, CTIN, iMoT, and RoNIN variants while reducing computation. Application studies further show robustness and practicality for mobile and IoT localization, making ReNiL a scalable, uncertainty-aware foundation for next-generation positioning.

Problem

• Pedestrian inertial localization lacks adaptability to diverse motion scales and cadences
• Existing methods struggle with inconsistent uncertainty estimation in real-world use
• Current approaches depend on fixed sliding-window integration limiting flexibility

Innovation

• Bayesian deep-learning framework for localization
• Any-Scale Laplace Estimator for flexible inference
• Inertial Positioning Demand Points for motion estimation