A mobile platform navigation method and device based on deep learning
A mobile platform and deep learning technology, applied in the field of navigation, can solve the problems of high equipment cost, large amount of calculation, limited application scenarios, etc., and achieve the effect of low equipment cost, low equipment precision requirements, and simple operation.
Active Publication Date: 2020-11-10
BEIJING RES INST OF PRECISE MECHATRONICS CONTROLS
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technology of the present invention solves the problem: overcomes the deficiencies of the existing technology, and provides a mobile platform navigation method and device based on deep learning to solve the problems of high equipment cost, large amount of calculation and limited application scenarios in the existing SLAM algorithm
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0052] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will further describe the public implementation manners of the present invention in detail with reference to the accompanying drawings.
[0053] The invention discloses a mobile platform navigation scheme based on deep learning. The scheme utilizes the advantages of deep learning algorithms to recurse the captured images through a deep neural network, and use the recursively obtained classification results as motions for adjusting the motion of the mobile platform. Instructions, let the mobile platform "remember" the environment captured by the camera during the training process, so that the mobile platform can quickly reach the destination according to the "memory" during the training during navigation.
[0054] refer to figure 1 , shows a flow chart of steps of a method for navigating a mobile platform based on deep learning in an embodiment of the present i...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a deep learning-based mobile platform navigation method and device. The method comprises the following steps of: controlling a mobile platform to move from a start point to a target point according to a received first movement instruction; shooting a surrounding scene of the mobile platform in real time through a shooting device on the mobile platform so as to obtain a real-time scene image; carrying out feature matching on the real-time scene image with sample scene images in a sample scene image library obtained on basis of deep learning so as to obtain a matched sample scene image; determining a second movement instruction matched with the matched sample scene image; and adjusting the movement process of the mobile platform in real time according to the second movement instruction until the mobile platform moves to the target point. Through the method and device, the problem that existing SLAM algorithms are high in equipment cost, large in calculated amountand limited in application scenes is solved.
Description
technical field [0001] The invention belongs to the technical field of navigation, and in particular relates to a mobile platform navigation method and device based on deep learning. Background technique [0002] Among the currently commonly used mobile platform (robot) visual navigation algorithms, SLAM (Simultaneous Localization And Mapping, simultaneous map modeling and positioning) algorithm is widely used as the mainstream algorithm. [0003] In the current SLAM algorithm, first use the camera or other sensors (lidar) to map the complex environment around the mobile platform movement, and at the same time, the mobile platform performs self-positioning; then, combine the established map model and self-positioning results , to realize the navigation of the mobile platform. [0004] However, there are many problems in the actual application of the current SLAM algorithm: 1. The accuracy of the established map model depends on the shooting accuracy of the camera or other s...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T19/00G06K9/00G06K9/66
Inventor 廖瑜梁斌焱王燕波张科王妍邓涛
Owner BEIJING RES INST OF PRECISE MECHATRONICS CONTROLS