Semantic map construction method based on cloud robot mixed cloud architecture

Abstract

The invention discloses a semantic map construction method based on cloud robot mixed cloud architecture, and aims to achieve a proper balance for improving object identification accuracy and shortening identification time. The technical scheme of the method is that mixed cloud consisting of a robot, a private cloud node and a public cloud node is constructed, wherein the private cloud node obtains an environment picture shot by the robot and milemeter and position data on the basis of an ROS (Read-Only-Storage) message mechanism, and SLAM (Simultaneous Location and Mapping) is used for drawing an environmental geometric map in real time on the basis of the milemeter and position data. The private cloud node carries out object identification on the basis of an environment picture, and an object which may be wrongly identified is uploaded to the public cloud node to be identified. The private cloud node maps an object category identification tag returned from the public cloud node and an SLAM map, and the corresponding position of the object category identification tag on a map finishes the construction of a semantic map. When the method is adopted, the local calculation load of the robot can be lightened, request response time is minimized, and object identification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of robot distributed computing, in particular to a method for building a cloud-based robot semantic map by using cloud computing as backup support and building a hybrid cloud architecture. Background technique [0002] The perception data sources of robots may include multiple dimensions such as vision, force, touch, infrared, ultrasound, and lidar. Robot semantic map construction means that robots recognize and understand the environment based on these perception data, and the core focus is on how to perceive The data is extracted from the rough and the essence, the false and the true are removed, and then analyzed and synthesized to extract high-level semantic information (such as object names and locations) that can be used by the robot for autonomous decision-making. The specific performance is to add labels of objects in the environment on the geometric map. The acquisition of semantic information can b...

AI Technical Summary

Problems solved by technology

[0006] To sum up, the solution based on private cloud performs better in request response time, and can recognize familiar objects, but requires pre-training, and has knowledge limitations, and cannot recognize unfamiliar objects in an open environment; the solution based on public cloud utilizes Internet big data knowledge has broader intelligence for object recognition in the environment, and can recognize unfamiliar objects without pre-training, but the recognition delay is large and the request response time is long

Images