LBDU-VIO：面向视觉不可靠场景的基于学习偏置动力学与不确定性的视觉惯性里程计
LBDU-VIO: Learned Bias Dynamics and Uncertainty for Visual-Inertial Odometry with Unreliable Vision
- Beijing Institute of Technology（北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对视觉不可靠时传统MSCKF鲁棒性不足的问题，提出LBDU-VIO，用神经ODE建模偏置动力学并预测IMU不确定性，在EuRoC和TUM-VI上降低误差，视觉中断时相对S-MSCKF误差降低25.1%。
AI中文摘要：
空中机器人的视觉惯性里程计（VIO）依赖高频率惯性测量单元（IMU）在视觉更新之间进行传播。然而，传统的多状态约束卡尔曼滤波器（MSCKF）采用随机游走偏置假设和固定噪声参数，当视觉信息不可靠时，这会限制其鲁棒性。为解决此问题，我们提出LBDU-VIO，一种学习增强的MSCKF，具有学习得到的连续时间偏置动力学和IMU不确定性模型。一个神经常微分方程（ODE）对连续时间偏置动力学进行建模，以传播滤波器的偏置状态，取代其随机游走模型。IMU不确定性模型预测运动自适应测量噪声协方差，用于协方差传播。两个模型均在无直接标签的情况下通过位姿监督进行训练。在真实世界EuRoC和TUM-VI基准上的实验表明，相比代表性的视觉惯性基线，误差更低，包括在EuRoC序列上10秒视觉中断时，平均相对位置误差相比S-MSCKF降低25.1%。
英文摘要：
Visual-inertial odometry (VIO) for aerial robots relies on high rate inertial measurement unit (IMU) propagation between visual updates. However, conventional multi state constraint Kalman filters (MSCKFs) use random walk bias assumptions and fixed noise parameters, which can limit robustness when visual information is unreliable. To address this problem, we propose LBDU-VIO, a learning-augmented MSCKF with learned continuous time bias dynamics and an IMU uncertainty model. A neural ordinary differential equation (ODE) models continuous time bias dynamics to propagate the filter's bias states, replacing their random walk model. The IMU uncertainty model predicts motion adaptive measurement noise covariances for covariance propagation. Both models are trained with pose supervision without direct labels. Experiments on real world EuRoC and TUM-VI benchmarks show lower errors than representative visual-inertial baselines, including a 25.1% reduction in mean relative position error compared with S-MSCKF on EuRoC sequences with 10s visual outage.
