Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Mobile robot predictive navigation method based on multi-target tracking

A multi-target tracking and mobile robot technology, applied in the field of mobile robot navigation and multi-target tracking, can solve the problems of frequent changes in navigation lines, achieve good interactivity, robustness, and simple environmental conditions

Pending Publication Date: 2021-11-19
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method improves the cognitive prediction ability of the robot, and then solves the problem of frequent changes in the navigation line of the mobile robot during the navigation process, which has good research significance and application value

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
  • Mobile robot predictive navigation method based on multi-target tracking
  • Mobile robot predictive navigation method based on multi-target tracking
  • Mobile robot predictive navigation method based on multi-target tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below in conjunction with specific embodiments.

[0066] like figure 1 and figure 2 As shown, the predictive navigation method for a mobile robot based on multi-target tracking provided in this embodiment uses a server training platform, mobile robots, ASUS A456U notebook computers, Logit C270 CMOS cameras and other auxiliary equipment, which includes the following steps:

[0067] 1) Input the camera real-time video stream, and preprocess the image frame.

[0068] 1.1) Use the cv2.VideoCapture function in the opencv-python library to start the camera driver and obtain the CMOS camera video stream;

[0069] 1.2) Obtain the image frame in the video stream data, and preprocess the image frame: use the letterbox function in opencv-python to rescale the image on the premise of maintaining the aspect ratio of the image, and use the gray value for the remaining blank area. Fill it with 0 pixels. According to the resolution pa...

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 discloses a mobile robot predictive navigation method based on multi-target tracking, which comprises the following steps: 1) inputting a real-time video stream of a camera, and preprocessing an image frame; 2) collecting historical track points through an online multi-target tracking model; 3) checking the compliance stability of the trajectory data; 4) through the historical track points, predicting and obtaining future track points; 5) creating a local cost map through the ROS server node; and 6) influencing navigation planning in advance through the move_base navigation node. The invention provides a predictive navigation method for the condition of frequent change of a navigation line in the navigation process of a mobile robot in a dynamic environment by adopting an idea of predicting the pedestrian trajectory by combining online multi-target tracking with a time sequence prediction model, and creates a local cost map by utilizing the predicted future pedestrian trajectory, and updating and adding the local cost map to the move_base navigation node so as to influence the navigation path planning of the robot in advance.

Description

technical field [0001] The invention relates to the technical field of mobile robot navigation and multi-target tracking, in particular to a mobile robot predictive navigation method based on multi-target tracking. Background technique [0002] In recent years, with the rise of artificial intelligence technology, the research on intelligent robots has gradually deepened, and there are higher requirements for the intelligent navigation of robots in dynamic environments. [0003] According to the traditional robot navigation method, the mobile robot will immediately change the navigation plan according to the information sensed by the current sensor, such as sensing an obstacle ahead. In a dynamic environment, such as a pedestrian walking in front of the robot, the traditional method needs to continuously change the navigation trajectory according to the current pedestrian position information. However, the new path after the change may still be impassable, resulting in frequ...

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): G06K9/00G06K9/62G06T7/70G06Q10/04B25J9/16
CPCG06T7/70G06Q10/047B25J9/1666B25J9/1697G06F18/214Y02T10/40
Inventor 毕盛洪瀚思董敏
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com