A Novel Approach to Visual Navigation based on Feature Line Correspondences for Precision Landing

Abstract

To satisfy the needs of precise pin-point landing missions in deep space exploration, this paper proposes a method based on feature line extraction and matching to estimate the attitude and position of a lander during the descent phase. Linear equations for a lander's motion parameters are given by using at least three feature lines on the planetary surface and their two-dimensional projections. Then, by taking advantage of Singular Value Decomposition (SVD), candidate solutions are obtained. Lastly, the unique lander's attitude and position relative to the landing site are selected from the candidate solutions. Simulation results show that the proposed algorithm is able to estimate a lander's attitude and position robustly and quickly. Without an extended Kalman filter, the average errors of attitude are less than 1°and the average errors of position are less than 10 m at an altitude of 2,000 m. With an extended Kalman filter, attitude errors are within 0·5°and position errors are within 1 m at an altitude of 247·9 m.

A robust optical navigation method for pin-point landing of asteroid based on 3D navigation features

“…However, these algorithms are less adaptable to changes in light source spectra or light source directions, and are hardly applicable to the needs of feature-based navigation in complex lighting environments of asteroids. In addition to extracting point features of images, some scholars extract line segment features of images [14,15], including straight lines, curves, and edges of features, are more robust to illumination than point features. However, line features are more difficult to describe and extract, especially for debris-pile type asteroids.…”

Improved random sampling consensus algorithm for vision navigation of intelligent harvester robot

“…Recently, navigation line visual detection algorithms for agricultural machinery operations have been proposed (Liang et al, 2016;Cheng et al, 2017;Shao et al, 2018;Yu et al, 2019). The improved Hough transformation to detect the navigation path (Xia et al, 2013) could improve the robustness of the recognition algorithm, but could not meet the real-time requirements.…”