A method and system for analyzing the accessibility of extraterrestrial planets based on deep learning

Abstract

The present invention discloses a method and system for analyzing the accessibility of extraterrestrial planets based on deep learning. The method first generates multi-dimensional data of a virtual simulation site for extraterrestrial planets through a procedural data generation method, and uses the geometric information therein to build Virtual simulation site; then build a patroller, and let the patroller run in the virtual simulation site, obtain the trafficability experiment results with traffic direction restrictions, and then convert them into trafficability experiment results without direction restrictions; use sliding window interception The local map of the location of the inspector in the map, and input the local map and the corresponding unrestricted trafficability experiment results into the trafficability prediction network, train the network, obtain the optimized network, and output the unrestricted traffic through the network sex test results. The invention comprehensively considers the environment geometry and material attributes, and the obtained map can more reasonably reflect the passability of the terrain and reduce the possibility of encountering risks in extraterrestrial detection.

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 accessibility of extraterrestrial planetary tables based on deep learning. Background technique [0002] Accessibility is an index that measures the difficulty of an entity traversing an area. Accessibility analysis is to design relevant algorithms to describe and quantify the accessibility 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 "Chang'e"'s exploration of the moon to "Tianwen"'s exploration of Mars, these series of topics have put forward new requirements and requirements for my country's extraterrestrial exploration level. new challenge. In extraterrestrial exploration, due to the unstructured and complex unknown topography of the extraterr...

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