Ground-air cooperative visual navigation method and device based on improved graph optimization SLAM

Abstract

The invention discloses a ground-air cooperative visual navigation method and a ground-air cooperative visual navigation device based on improved graph optimization SLAM, which belong to the technical field of navigation. The ground-air cooperative visual navigation device combines sensors with power structures to form intelligent agents in the air and on the ground respectively, wherein each intelligent agent carries the ground-air cooperative visual navigation method based on improved graph optimization SLAM designed in the invention. The ground-air cooperative visual navigation method adopts four modules, wherein a signal acquisition module is used for acquiring position signals and visual signals in a positional environment; a front-end processing module is used for processing the acquired information and converting the various signals into a matrix; a back-end processing module uses the matrix provided by the front-end processing module to perform position estimation and state update; and an improved graph optimization algorithm module is used for speeding up a computation speed of the back-end processing module and reducing the computation pressure of the back-end processing module. By applying the ground-air cooperative visual navigation method, a multi-agent system placed in an unknown environment is subjected to optimization of a positioning navigation system, the positioning precision of the positioning navigation system is improved, the positioning speed is accelerated, and the computation complexity is reduced. The ground-air cooperative visual navigation method and the ground-air cooperative visual navigation device solve the problems of low positioning precision, slow positioning, large error, heavy computation load and the like facing the unknown environment in the prior art.

Description

technical field [0001] The invention belongs to the technical field of navigation, and in particular relates to a ground-air collaborative visual navigation method and device based on improved graph optimization SLAM. Background technique [0002] Visual navigation system has become a popular research field in navigation research in recent years. Since the introduction of Instant Localization and Mapping (SLAM) in 1986, it has developed rapidly. And this technology is more used in intelligent unmanned devices such as drones and unmanned vehicles. When a mobile robot enters an unfamiliar environment, it needs to construct an environmental map through its own sensors, and at the same time determine its own position in the map. Because the camera has excellent characteristics such as small size, light weight, and low price, and the camera can obtain two-dimensional information in the scene, and obtain pose information and motion state information through corresponding algorit...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a ground-air collaborative visual navigation method and device based on improved graph optimization SLAM. By introducing the probability calculation theory of graph optimization, graph optimization can greatly reduce the need for EKF prediction in the process of EKF prediction without abandoning the basic calculation framework. Calculating the dimension of the matrix makes the matrix sparse, which solves the problem of algorithm complexity caused by the dimension of the matrix, and solves the problem of low navigation efficiency and unstable system operation in the face of multi-agent placement scenarios in the prior art And other issues

Images