MoE-Gyro: Self-Supervised Over-Range Reconstruction and Denoising for MEMS Gyroscopes

2025-05-27

arXiv.org

AI Summary

MEMS gyroscopes suffer from a fundamental trade-off between measurement range and noise performance, with existing approaches failing to simultaneously satisfy hardware feasibility and practical deployment requirements. This paper introduces the first self-supervised framework tailored for saturated IMU signals, featuring a novel dual-expert dynamic routing architecture (ORE+DE) that integrates Gaussian-decay attention, FFT-guided signal enhancement, and a dual-branch complementary masking mechanism. We further establish the first open-source IMU signal enhancement benchmark—ISEBench—and release the GyroPeak-100 dataset. Experimental results demonstrate a substantial expansion of the measurable angular rate range from 450°/s to 1500°/s, a 98.4% reduction in bias instability, and state-of-the-art performance on ISEBench, thereby decisively breaking the conventional range–noise trade-off barrier.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Machine Learning: Mixture of Experts (MoE)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

MEMS gyroscopes play a critical role in inertial navigation and motion control applications but typically suffer from a fundamental trade-off between measurement range and noise performance. Existing hardware-based solutions aimed at mitigating this issue introduce additional complexity, cost, and scalability challenges. Deep-learning methods primarily focus on noise reduction and typically require precisely aligned ground-truth signals, making them difficult to deploy in practical scenarios and leaving the fundamental trade-off unresolved. To address these challenges, we introduce Mixture of Experts for MEMS Gyroscopes (MoE-Gyro), a novel self-supervised framework specifically designed for simultaneous over-range signal reconstruction and noise suppression. MoE-Gyro employs two experts: an Over-Range Reconstruction Expert (ORE), featuring a Gaussian-Decay Attention mechanism for reconstructing saturated segments; and a Denoise Expert (DE), utilizing dual-branch complementary masking combined with FFT-guided augmentation for robust noise reduction. A lightweight gating module dynamically routes input segments to the appropriate expert. Furthermore, existing evaluation lack a comprehensive standard for assessing multi-dimensional signal enhancement. To bridge this gap, we introduce IMU Signal Enhancement Benchmark (ISEBench), an open-source benchmarking platform comprising the GyroPeak-100 dataset and a unified evaluation of IMU signal enhancement methods. We evaluate MoE-Gyro using our proposed ISEBench, demonstrating that our framework significantly extends the measurable range from 450 deg/s to 1500 deg/s, reduces Bias Instability by 98.4%, and achieves state-of-the-art performance, effectively addressing the long-standing trade-off in inertial sensing.

Problem

• Addresses MEMS gyroscope range-noise trade-off limitations
• Develops self-supervised framework for simultaneous reconstruction and denoising
• Introduces benchmark for comprehensive IMU signal enhancement evaluation

Innovation

• Self-supervised framework for gyroscope signal reconstruction
• Gaussian-Decay Attention reconstructs saturated signal segments
• Dual-branch masking with FFT augmentation reduces noise