A Method of Lunar Autonomous Driving Perception Planning Based on Hybrid A *

Tao “Eric” Hu, Tao Cao, Bo Zheng, Zhouyuan Qian, Fei Han, Liang He · 2024

As humans continue to deepen their exploration of space, lunar autonomous driving technology has gradually become a research hotspot. This article conducts a comprehensive and in-depth study of lunar autonomous driving technology, aiming to provide technical support for future lunar exploration missions. First, the background and significance of lunar autonomous driving technology are introduced, and the characteristics of the lunar environment and the importance of autonomous driving in lunar exploration are explained. This paper proposes a lunar surface autonomous driving method based on hybrid A*. This method detects obstacles and 3D targets through pre-fusion of radar and images, thereby constructing a passable grid map, and then uses the hybrid A* algorithm as a During the global planning period, the path is planned in real time, control instructions are output, and automatic detection and avoidance of obstacles are realized. At the same time, combined with the Lidar vision inertial fusion odometer algorithm, autonomous navigation of lunar vehicles is achieved. Finally, the feasibility and effectiveness of the proposed method were verified through experiments. The research results of this article will provide important technical support for future lunar exploration missions and help promote the further development of lunar surface autonomous driving technology.

Read the paper · More papers on PaperTik