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.

翻译：本文提出了一种基于神经网络的无迹卡尔曼滤波（UKF），用于在近距离交会场景中估计和跟踪已知非合作翻滚目标航天器的位姿（即位置和姿态）。该UKF利用多任务卷积神经网络（CNN）从目标单目图像中提供的位姿信息，估计目标相对于服务航天器的轨道和姿态。为实现可靠跟踪，UKF的过程噪声协方差矩阵通过自适应状态噪声补偿进行在线调整，该方法利用了新开发的相对姿态动力学闭环过程噪声模型。本文还引入了卫星硬件在环交会轨迹（SHIRT）数据集，以全面分析所提管道的性能和鲁棒性。SHIRT包含两个代表性低地球轨道交会轨迹的标注图像，这些图像分别通过图形渲染器和机器人测试平台生成。具体而言，CNN仅使用合成数据进行训练，而整个导航管道的功能和性能则在机器人测试平台的真实图像上进行评估。所提出的UKF在SHIRT数据集上进行了评估，结果表明其在稳态下可实现亚分米级位置误差和度级姿态误差。