Extraterrestrial star catalogue trafficability analysis method and system based on deep learning

Abstract

The invention discloses an extraterrestrial star catalogue trafficability analysis method and system based on deep learning, and the method comprises the steps: firstly generating multi-dimensional data of a virtual simulation site of an extraterrestrial star catalogue through a process type data generation method, and building the virtual simulation site through the geometric information in the multi-dimensional data; constructing a patrolling device, enabling the patrolling device to run in the virtual simulation site, obtaining a trafficability experiment result with traffic direction limitation, and converting the trafficability experiment result into a trafficability experiment result without direction limitation; and intercepting a local map of the position of the patroller in the map by using a sliding window, inputting the local map and the corresponding trafficability experiment result without direction limitation into a trafficability prediction network, training the network to obtain an optimized network, and outputting the trafficability experiment result without direction limitation through the network. According to the method, the environmental geometry and material attributes are comprehensively considered, the obtained map can more reasonably reflect the passing degree of the terrain, and the possibility of encountering risks in out-of-satellite detection is reduced.

Description

technical field [0001] The invention belongs to the fields of deep learning and aerospace, and mainly relates to a method and system for analyzing the transitivity of extraterrestrial surfaces based on deep learning. Background technique [0002] Trafficability is an index to measure the difficulty of an entity to cross an area. The trafficability analysis is to design relevant algorithms to describe and quantify the trafficability of the environment based on the environmental information obtained by intelligent sensing devices such as sensors. [0003] In recent years, my country's exploration of extraterrestrial planets has made milestone progress. From the exploration of the moon by "Chang'e" to the exploration of Mars by "Tianwen", this series of subjects has put forward new requirements and requirements for my country's extraterrestrial exploration new challenge. In extraterrestrial exploration, due to the unstructured and complex unknowns of the extraterrestrial surfac...

AI Technical Summary

Problems solved by technology

[0006] Traditional trafficability methods based on geometric information are based on empirical formulas or thresholds, so they cannot handle complex ground information perfectly, and dangerous situations may occur in extraterrestrial exploration

The results based on deep learning methods rely on the definition and labeling methods of popularity tags, and it is difficult to obtain data sets

Images