ICD-Net: Inertial Covariance Displacement Network for Drone Visual-Inertial SLAM

TL;DR

ICD-Net introduces a neural network-based approach to improve drone visual-inertial SLAM by directly estimating displacements and uncertainties from raw sensor data, significantly enhancing accuracy and robustness in challenging conditions.

Contribution

The paper presents ICD-Net, a novel framework that learns to process raw inertial data and predict displacement with uncertainty, integrating these into SLAM to outperform traditional methods.

Findings

Over 38% improvement in trajectory accuracy on high-speed drone sequences

Effective uncertainty estimation enhances SLAM robustness

Maintains real-time performance despite added neural network processing

Abstract

Visual-inertial SLAM systems often exhibit suboptimal performance due to multiple confounding factors including imperfect sensor calibration, noisy measurements, rapid motion dynamics, low illumination, and the inherent limitations of traditional inertial navigation integration methods. These issues are particularly problematic in drone applications where robust and accurate state estimation is critical for safe autonomous operation. In this work, we present ICD-Net, a novel framework that enhances visual-inertial SLAM performance by learning to process raw inertial measurements and generating displacement estimates with associated uncertainty quantification. Rather than relying on analytical inertial sensor models that struggle with real-world sensor imperfections, our method directly extracts displacement maps from sensor data while simultaneously predicting measurement covariances that reflect estimation confidence. We integrate ICD-Net outputs as additional residual constraints into the VINS-Fusion optimization framework, where the predicted uncertainties appropriately weight the neural network contributions relative to traditional visual and inertial terms. The learned displacement constraints provide complementary information that compensates for various error sources in the SLAM pipeline. Our approach can be used under both normal operating conditions and in situations of camera inconsistency or visual degradation. Experimental evaluation on challenging high-speed drone sequences demonstrated that our approach significantly improved trajectory estimation accuracy compared to standard VINS-Fusion, with more than 38% improvement in mean APE and uncertainty estimates proving crucial for maintaining system robustness. Our method shows that neural network enhancement can effectively address multiple sources of SLAM degradation while maintaining real-time performance requirements.