Robot control method based on natural language understanding

A technology of natural language understanding and control methods, which is applied in the field of robot control based on natural language understanding, and can solve problems such as the gap between intelligent voice control and other problems

Inactive Publication Date: 2018-08-24
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, most robot control systems based on voice recognition can only simply recognize some basic commands such as "forward", "turn left", "stop", etc., even if there are a small number of robot control systems that can realize continuous voice recognition , and can only recognize robot control commands in a fixed pattern, which is far from the expected intelligent voice control of robots

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Robot control method based on natural language understanding
  • Robot control method based on natural language understanding
  • Robot control method based on natural language understanding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0067] A robot control method based on natural language understanding of this example, as attached figure 1 shown, including the following steps:

[0068] S1. Acquiring and analyzing voice signals;

[0069] S2. Understanding user intent;

[0070] S3, controlling the movement of the robot.

[0071] Said step S1 comprises the following steps:

[0072] The operator issues a series of continuous voice commands through the microphone, the microphone acquires the voice signal and turns it into a voice stream, and the computer receives the voice stream and converts it into a digital signal that the computer can process. After the voice signal is digitized, it can be reflected as a waveform diagram to intuitively represent its digital characteristics. First, the voice signal is preprocessed through steps such as pre-filtering, sampling, A / D conversion, framing, data windowing, and high-frequency boosting. Since the obtained speech signal and the reference template have different l...

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

No PUM Login to view more

Abstract

The invention provides a robot control method based on natural language understanding, and the method comprises the steps: (1) acquiring a speech signal and converting the speech signal into a corresponding digital signal, and then converting the digital signal into corresponding text information through a dynamic time warping algorithm; (2) establishing a model, and carrying out the matching of the key information and redundant information contained in the text information, obtaining a segmentation result of the text information, and then classifying the text information through a classifierestablished through a maximum entropy model, and then converting a control instruction to be converted further in the classification result; (3) carrying out the reverse solving of the obtained spatial coordinates of a tail executor of a mechanical arm into a joint variable of a rotating joint through a robot control command, and controlling the robot to move.

Description

technical field [0001] The invention belongs to the field of robot motion, in particular to a robot control method based on natural language understanding. Background technique [0002] With the increasing intelligence and flexibility of robots, traditional robot control methods have gradually been unable to meet the needs of intelligent robots. Therefore, finding a suitable intelligent control method for robots has become a current research direction. Through the intelligent control method, the robot only needs to understand human intentions, and complete the rest of the control work through its own intelligence. [0003] Nowadays, with the development of computer technology and speech recognition technology, speech has been gradually accepted by people as one of the ways of communicating with computers. As a common way of communication between people, voice is more convenient than mouse and keyboard. Therefore, voice has become one of the intelligent control methods of ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/22G10L15/26G06F17/30
CPCG10L15/22G10L15/26G06F16/35G06F16/374
Inventor 张平杜广龙徐灿金培根何子平陈明轩李方
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap