Learned Inertial Odometry for Cycling Based on Mixture of Experts Algorithm

2025-10-20

AI Summary

To address critical challenges in high-precision bicycle localization—including severe GNSS multipath interference, poor robustness of conventional inertial navigation, and excessive computational overhead of existing learning-based inertial odometry (e.g., TLIO) hindering edge deployment—this paper proposes MoE-LLIO, a lightweight Mixture-of-Experts learning-based inertial odometry framework. Methodologically, we design an improved sparse-gated MoE architecture that enables efficient tight coupling between raw IMU measurements and displacement predictions. Compared to the state-of-the-art LLIO, MoE-LLIO reduces model parameters by 64.7% and inference computational cost by 81.8%, while maintaining comparable localization accuracy. This work significantly enhances the feasibility of real-time deployment of learning-based inertial odometry on resource-constrained mobile devices, establishing a new paradigm for vehicular edge localization.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Learning to Search
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

With the rapid growth of bike sharing and the increasing diversity of cycling applications, accurate bicycle localization has become essential. traditional GNSS-based methods suffer from multipath effects, while existing inertial navigation approaches rely on precise modeling and show limited robustness. Tight Learned Inertial Odometry (TLIO) achieves low position drift by combining raw IMU data with predicted displacements by neural networks, but its high computational cost restricts deployment on mobile devices. To overcome this, we extend TLIO to bicycle localization and introduce an improved Mixture-of Experts (MoE) model that reduces both training and inference costs. Experiments show that, compared to the state-of-the-art LLIO framework, our method achieves comparable accuracy while reducing parameters by 64.7% and computational cost by 81.8%.

Problem

• Improving bicycle localization accuracy under GNSS limitations
• Reducing computational cost of learned inertial odometry for cycling
• Enhancing mobile deployment efficiency with Mixture-of-Experts algorithm

Innovation

• Mixture-of-Experts model reduces computational costs
• Combines raw IMU data with neural network predictions
• Achieves comparable accuracy with fewer parameters