UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds

TL;DR

UMLoc is an innovative framework that combines uncertainty modeling and map constraints to improve inertial localization accuracy in GPS-denied environments, providing reliable drift estimates and feasible trajectory generation.

Contribution

It introduces a novel end-to-end approach integrating LSTM-based uncertainty estimation with a CGAN for map-constrained inertial localization, enhancing drift resilience.

Findings

Achieves a mean drift ratio of 5.9% over 70 meters

Attains an average Absolute Trajectory Error of 1.36 meters

Maintains well-calibrated prediction bounds

Abstract

Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define 68%, 90%, and 95% prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-hour indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of 5.9% over a 70 m travel distance and an average Absolute Trajectory Error (ATE) of 1.36 m, while maintaining calibrated prediction bounds.