Multi-layer global perception map construction method and system universal for structural and non-structural environments

Abstract

The invention relates to a multi-layer global perception map construction method and system universal for structural and non-structural environments, and belongs to the technical field of map construction. According to the universal multilayer global sensing map construction method for the structural and non-structural environments, after a global topological map is constructed according to multi-source sensing information or an initial map, single-frame sensing maps are respectively established based on different sensing information in the multi-source sensing information, then, based on the global topological map, the single-frame sensing maps are fused to obtain multilayer sensing sub-maps, and the multilayer sensing sub-maps are constructed according to the obtained multilayer sensing sub-maps. And finally, the multi-layer perception sub-map and the global topological map are associated and stored to obtain an accurate global map, so that the complexity of local environment information in the map can be improved, and the problem that enough environment information cannot be provided for local planning of the unmanned vehicle in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of global map construction, in particular to a method and system for constructing a multi-layer global perceptual map that is common to structured and unstructured environments. Background technique [0002] In recent years, the safe driving of unmanned vehicles depends on accurate positioning and detailed environmental information, so some high-precision map technologies have been produced. In high-precision maps, roads are usually represented by vector information, and additional layers represent some road settings such as traffic lights, providing long-distance navigation for unmanned vehicles. However, high-precision maps, which only rely on vector information to represent the road environment, are difficult to describe the complex characteristics of the environment, especially unstructured environments with changing road boundaries, such as off-road environments, etc., and the positioning accura...

AI Technical Summary

Problems solved by technology

However, high-precision maps, which only rely on vector information to represent the road environment, are difficult to describe the complex characteristics of the environment, especially unstructured environments such as off-road environments where road boundaries change, and the positioning accuracy is usually limited to satellite navigation services, road conditions, etc. Information is also limited to the information richness of the initial map

This kind of map often has many false detections, backward information, and simple local environmental information, which cannot provide sufficient environmental information for the local planning of unmanned vehicles, and it is difficult to provide accurate information due to the lack of lane lines and other information in low-level road infrastructure or even off-road environments. The navigation information is not suitable for the construction of a large-scale global map of the entire road segment

Images