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.
Abstract (translated)
视觉惯性SLAM系统由于多种干扰因素(如不完美的传感器校准、噪声测量、快速运动动态、低光照条件以及传统惯性导航集成方法的内在局限)往往表现出次优性能。这些问题在无人机应用中尤为严重,因为这些应用场景需要稳健且准确的状态估计以确保安全的自主操作。在此研究工作中,我们提出了ICD-Net(Inertial-Centric Displacement Network),这是一个新颖的框架,通过学习处理原始惯性测量数据并生成具有不确定性量化的位移估计来增强视觉惯性SLAM性能。 我们的方法直接从传感器数据中提取位移图,同时预测反映估算信心的测量协方差,而非依赖于难以应对真实世界传感器缺陷的分析式惯性传感器模型。我们将ICD-Net输出作为额外残差约束集成到VINS-Fusion优化框架中,在此框架下,预测的不确定性恰当地对神经网络贡献与传统视觉和惯性项进行了加权。所学得的位移约束提供了互补信息,有助于补偿SLAM管道中的各种误差来源。 我们的方法既适用于常规操作条件,也适用于相机不一致或视觉退化的情况。在具有挑战性的高速无人机序列上的实验评估表明,相较于标准VINS-Fusion,本方法显著提高了轨迹估计精度,平均APE(绝对位姿误差)提升了超过38%,并且不确定性估计对于保持系统的鲁棒性至关重要。 我们的研究表明,神经网络增强能够有效解决SLAM退化问题的多个来源,并且能够在满足实时性能要求的同时实现这一目标。
URL
https://arxiv.org/abs/2512.00037