外观
论文arXiv 2608.106232 个月前
当你的状态估计器偏离正轨时：通过频谱分析检测估计器故障
原文链接：When Your State Estimator Has Lost The Plot: Detecting Estimator Failures Via Spectral Analysis（arXiv 2608.10623 · 发布日期：2026-08-11）
When Your State Estimator Has Lost The Plot: Detecting Estimator Failures Via Spectral Analysis
提出传感器无关的频域内省方法，分析近期速度估计功率分布，并在空中机器人户外飞行里程计数据上验证。
核心要点
- 未建模扰动会使机载状态估计退化或失效，现有质量评估方法存在理想假设或分布依赖。
- 方法分析近期速度估计的频域功率分布，考察信号功率、谱带宽和熵等指标。
- 在视觉-惯性、LiDAR-惯性和雷达-惯性里程计上，检测51%-58%标注故障，精确率60%-84%。
- 结果表明，简单频域输出分析可作为轻量内省工具，补充现有鲁棒性技术。
验证范围与局限：验证限于一台空中机器人的户外飞行数据，涵盖三类惯性里程计框架。
英文摘要 (Abstract)
Reliable onboard state estimation is essential for safe robotic operation, yet unmodeled disturbances, such as sensor aliasing or out-of-distribution noise, still cause estimators to degrade or fail completely. While many methods aim to improve estimator robustness, only a few provide introspective mechanisms to assess estimate quality. Existing uncertainty measures, such as covariances, rely on idealized assumptions and tend to be overconfident, and more recent data-driven approaches are typically tied to their training data distributions. We propose a sensor-agnostic introspective method that assesses estimator health by analyzing the frequency-domain power distribution of recent velocity estimates. The method is evaluated using outdoor flight data from an aerial robot running visual-inertial, LiDAR-inertial, and radar-inertial odometry. The dataset includes multiple estimator failures, enabling analysis of several frequency-domain indicators, such as signal power, spectral bandwidth, and entropy. We observe consistent spectral power differences between healthy and degraded estimates, allowing detection of 51%-58% of labeled failures with 60%-84% precision across three fundamentally different state estimation frameworks. Our results show that even a simple frequency-domain analysis of a state estimator's output can serve as a lightweight introspective tool to complement existing robustness techniques in real-world robotic deployments, and opens promising avenues for future investigation.
作者：Christian Lanegger, Helen Oleynikova, Roland Siegwart, Michael Pantic
来源
本页事实对应的公开页面，以原文为准。