论文标题
基于自适应的神经网络的无气体卡尔曼滤波器，用于非合作飞船的稳健姿势跟踪
Adaptive Neural Network-based Unscented Kalman Filter for Robust Pose Tracking of Noncooperative Spacecraft
论文作者
论文摘要
本文提出了一个基于神经网络的无气体卡尔曼滤波器（UKF），以估算并跟踪已知的，非合作的，翻滚的目标航天飞机的姿势（即位置和方向），以近距离呈现场景。 UKF根据目标的多任务卷积神经网络（CNN）提供的姿势信息估算了目标轨道和态度相对于服务商的轨道和态度。为了启用可靠的跟踪，使用自适应状态噪声补偿来在线调整UKF的过程噪声协方差矩阵，该噪声补偿利用了新开发的封闭形式的过程噪声模型用于相对态度动力学。本文还介绍了卫星硬件在环境轨迹轨迹（衬衫）数据集，以实现对拟议管道的性能和鲁棒性的全面分析。衬衫包括使用图形渲染器和机器人测试床创建的低地球轨道中的两个代表性会合轨迹的标记图像。具体而言，CNN仅根据合成数据进行培训，而完整导航管道的功能和性能是在机器人测试台上的真实图像上评估的。拟议的UKF在衬衫上进行了评估，并显示在稳态下具有次点级别的位置和程度级别的方向误差。
This paper presents a neural network-based Unscented Kalman Filter (UKF) to estimate and track the pose (i.e., position and orientation) of a known, noncooperative, tumbling target spacecraft in a close-proximity rendezvous scenario. The UKF estimates the target's orbit and attitude relative to the servicer based on the pose information provided by a multi-task Convolutional Neural Network (CNN) from incoming monocular images of the target. In order to enable reliable tracking, the process noise covariance matrix of the UKF is tuned online using adaptive state noise compensation which leverages a newly developed closed-form process noise model for relative attitude dynamics. This paper also introduces the Satellite Hardware-In-the-loop Rendezvous Trajectories (SHIRT) dataset to enable comprehensive analyses of the performance and robustness of the proposed pipeline. SHIRT comprises the labeled images of two representative rendezvous trajectories in low Earth orbit created using both a graphics renderer and a robotic testbed. Specifically, the CNN is solely trained on synthetic data, whereas functionality and performance of the complete navigation pipeline are evaluated on real images from the robotic testbed. The proposed UKF is evaluated on SHIRT and is shown to have sub-decimeter-level position and degree-level orientation errors at steady-state.
