发表机构
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对空中惯性里程计的速度估计问题，提出VeloBins将速度回归转为分箱分类，无需单独不确定性解码器，在四类空中数据集上降低了多种误差，实现了最优性能。
AI 中文摘要
惯性里程计（IO）对空中机器人至关重要，而剧烈机动和光照不足会降低视觉传感器的性能。近期基于学习的IO方法通过从IMU及平台特定传感器学习运动先验，再将预测结果融合进扩展卡尔曼滤波中，改进了传统的基于积分的方法。然而，通过回归学习速度存在困难，而用单独解码器和负对数似然（NLL）损失联合估计不确定性会进一步复杂化训练，还可能导致估计结果过于自信。本文提出VeloBins，将速度回归重新表述为离散速度分箱上的分类问题，通过分箱分布的期望解码速度，通过其方差解码不确定性，无需单独的不确定性解码器。我们进一步使用以真实速度为中心、标准差设为速度误差的误差条件高斯标签显式监督不确定性。我们在四个空中数据集上评估VeloBins，涵盖自由形式剧烈飞行、27克纳米四旋翼，以及速度超过21米/秒的无人机竞速场景。VeloBins在所有四个数据集上实现了最低的平均误差，与最强基线相比，速度、相对轨迹和绝对轨迹误差分别降低了3%-27%、8%-40%和6%-53%。值得注意的是，所提出的监督方式从未优化NLL损失，却实现了最低的NLL和最佳的滤波器一致性。代码将在论文接收后提供。
英文摘要
Inertial odometry (IO) is critical for aerial robots, where aggressive maneuvers and poor lighting degrade visual sensors. Recent learning-based IO methods improve traditional integration-based approaches by learning motion priors from IMU and platform-specific sensors, then fusing the predictions within an extended Kalman filter. However, learning velocity through regression is difficult, while jointly estimating uncertainty with a separate decoder and negative log-likelihood (NLL) loss further complicates training and can lead to over-confident estimates. We introduce VeloBins, which reformulates velocity regression as classification over discretized velocity bins. We decode both the velocity from the bin distribution's expectation and the uncertainty from its variance, removing the need for a separate uncertainty decoder. We further supervise the uncertainty explicitly using an error-conditioned Gaussian label centered at the ground-truth velocity, with a standard deviation set to the velocity error. We evaluate VeloBins on four aerial datasets, ranging from free-form aggressive flights and a 27 g nano-quadrotor to drone racing at over 21~m/s. VeloBins achieves the lowest average errors on all four datasets, reducing velocity, relative trajectory, and absolute trajectory errors by 3-27%, 8-40%, and 6-53%, respectively, compared with the strongest baseline. Notably, the proposed supervision achieves the lowest NLL and best filter consistency despite never optimizing an NLL loss. The code will be available upon acceptance.
Comments8 pages, 6 figures, 4 tables. Supplementary video: https://youtu.be/QkZY0So3myw
