中国空间科学技术

中国空间科学技术 ›› 2026, Vol. 46 ›› Issue (5): 38-47.doi: 10.16708/j.cnki.1000-758X.2026.0075

• 深空与月球导航技术专题 • 上一篇    下一篇

RoMa-TRN：面向深空任务的无地图自主地形相对导航视觉测量技术

田启航1，杨巍1,*，林大泳2，徐云飞2   

  1. 1.北京控制工程研究所空间智能控制技术全国重点实验室，北京100094
    2.北京控制工程研究所空间光电测量与智能感知实验室，北京100094
  • 收稿日期:2025-09-08 修回日期:2025-10-23 录用日期:2025-10-30 发布日期:2026-09-23 出版日期:2026-09-30

RoMa-TRN:employing vision measurements to enable autonomous terrain relative navigation without maps for deep space missions

TIAN Qihang1，YANG Wei1,*，LIN Dayong2，XU Yunfei2   

  1. 1.National Key Laboratory of Space Intelligent Control，Beijing Institute of Control Engineering, Beijing 100094, China
    2.Space Optoelectronic Measurement and Perception Lab，Beijing Institute of Control Engineering, Beijing 100094, 
    China
  • Received:2025-09-08 Revision received:2025-10-23 Accepted:2025-10-30 Online:2026-09-23 Published:2026-09-30

PDF (PC)

47

摘要： 自主地形相对导航是未来行星探测任务中的一项关键技术。传统的地形相对导航方法通常依赖陆标检测与图像配准，即通过导航图像与星载地图间的数据关联实现飞行器的相对位姿测量。测量值与地图的匹配问题是一项复杂且资源密集型的任务，且对于星上先验状态精度要求较高。特征匹配是计算机视觉领域中的一项关键任务，其目的是通过鲁棒的视觉模型，实现真实变化场景下稳定及准确的图像配准。本文针对未来深空地外天体探测任务中的自主光学导航问题进行了研究，首次提出了RoMa-TRN，即一种基于RoMa特征匹配的无地图自主地形相对导航方法。针对单目相机的连续影像，该方法使用视觉预训练模型进行前端特征匹配，并构建视觉里程计，求解最小二乘问题实现帧间飞行器的运动方向估计。该测量值可作为星上导航滤波器的输入，用于更新飞行器状态。实验结果表明，相比于其他特征匹配方法，本文所述方法在不同光照及视角变化条件下均能实现准确及鲁棒的图像配准。在太阳高度角为1°及89°的极端工况下，本文所述方法未见显著性能退化。在10km轨道高度上，本文所述方法可达到约0.03°的运动方向估计精度，可为导航滤波器提供高精度的运动方向观测。

关键词: 地形相对导航, 特征匹配, 视觉里程计, 深度学习, 制导、导航与控制

Abstract: Autonomous terrain relative navigation (TRN) is expected to play a crucial role of upcoming planetary missions. Conventional TRN methods typically rely on landmark detection and image registration, which achieve relative pose estimation of the spacecraft by establishing data association between navigation images and onboard maps. The association problem between measurements and maps is a complex and computationally intensive task, and requires high accuracy in the prior knowledge onboard. Feature matching is a critical task in computer vision, aiming to achieve stable and accurate image registration under real-world varying conditions through robust visual models. This paper addresses the challenge of autonomous optical navigation for future deep space missions and for the first time, RoMa-TRN, an autonomous TRN method based on RoMa feature matching without maps is proposed. For sequential images captured by a monocular camera, the method employs the pre-trained visual model for front-end feature matching and constructs visual odometry. By solving a least-squares problem, it estimates the inter-frame direction of motion of the spacecraft. This measurement can be incorporated into an onboard navigation filter to update the state of spacecraft. Experimental results demonstrate that, compared with other feature matching methods, the proposed approach achieves accurate and robust image registration under varying illumination and viewpoint conditions. Under extreme scenarios with solar elevation angles of 1° and 89°, no significant performance degradation is observed. At an orbital altitude of 10 km, the method achieves a motion direction estimation accuracy of approximately 0.03°, enabling precise direction-of-motion for navigation filter.

Key words: terrain relative navigation, feature matching, visual odometry, deep learning, guidance, navigation and control