Spiking Neural-Invariant Kalman Fusion for Accurate Localization Using Low-Cost IMUs

TL;DR

This paper introduces a brain-inspired state estimation framework combining spiking neural networks with an invariant Kalman filter to improve localization accuracy using low-cost IMUs, demonstrating robustness and superior performance.

Contribution

It presents a novel integration of SNNs with InEKF for adaptive, noise-resilient localization, which is a new approach in low-cost IMU-based robot navigation.

Findings

Outperforms existing methods in localization accuracy.

Demonstrates robustness to sensor noise.

Validated on KITTI dataset and real-world robot data.

Abstract

Low-cost inertial measurement units (IMUs) are widely utilized in mobile robot localization due to their affordability and ease of integration. However, their complex, nonlinear, and time-varying noise characteristics often lead to significant degradation in localization accuracy when applied directly for dead reckoning. To overcome this limitation, we propose a novel brain-inspired state estimation framework that combines a spiking neural network (SNN) with an invariant extended Kalman filter (InEKF). The SNN is designed to extract motion-related features from long sequences of IMU data affected by substantial random noise and is trained via a surrogate gradient descent algorithm to enable dynamic adaptation of the covariance noise parameter within the InEKF. By fusing the SNN output with raw IMU measurements, the proposed method enhances the robustness and accuracy of pose estimation. Extensive experiments conducted on the KITTI dataset and real-world data collected using a mobile robot equipped with a low-cost IMU demonstrate that the proposed approach outperforms state-of-the-art methods in localization accuracy and exhibits strong robustness to sensor noise, highlighting its potential for real-world mobile robot applications.