Method, device, equipment and system for map building

Abstract

The invention discloses a method, device, equipment and system for map building. The method is applied to movable equipment and comprises the steps that sample data of a current motion environment in which the movable equipment is moving acquired by an environment sensor is received, wherein the sample data comprises position data and image data; absolute pose information of the movable equipment is determined at least according to the position data; a semantic entity in the current motion environment is detected according to the image data, wherein the semantic entity is an entity which may affect motion; according to the absolute pose information of the movable equipment and the image data, attribute information of the semantic entity is determined, wherein the attribute information indicates physical features of the semantic entity; and a real-time semantic map of the current motion environment is built according to the semantic entity and the attribute information. Hence, a high-precision semantic map can be generated.

Description

technical field [0001] The present application relates to the technical field of map construction, and more specifically, to a map construction method, device, device and system. Background technique [0002] Before a mobile device (for example, an autonomous driving robot) can perform a task, it must first have prior knowledge of the mobile environment (for example, the scene road network), that is, a high-precision map. On the one hand, high-precision maps can alleviate the difficulty of real-time perception. On the other hand, global information can also be added to obtain better decisions. Therefore, high-precision maps are an essential infrastructure for current autonomous driving. [0003] Existing digital maps cannot be directly used for autonomous driving due to insufficient accuracy and details. At present, high-precision maps in autonomous driving are mainly obtained through data acquired by special acquisition equipment (for example, acquisition vehicles) equippe...

AI Technical Summary

Problems solved by technology

[0004] The map information drawn by the above-mentioned special acquisition equipment is very accurate, but there are also the following problems: 1) The cost of data acquisition is high: the equipment cost and the acquisition cost are relatively high; 2) The update frequency is low: due to the need for special acquisition equipment and algorithm processing, Therefore, the update frequency is difficult to guarantee, and only the update cycle in units of years can be obtained; 3) The storage process is complex: generally, it is necessary to store a comprehensive high-precision measurement map, and manual editing is required to obtain a high-precision map

Images