RGBD-information-based small soccer robot recognition, tracking and grabbing method

A football robot and robot technology, applied in the field of visual perception servo movement, can solve the problems of complex goals and high dynamics of football games, and achieve high adaptability

Active Publication Date: 2019-10-25
ZHEJIANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with general applications, football games have the characteristics of high dynamics and complex goals. It is required that the robot can quickly perform image processing and path planning, and at the same time fully grasp the situation on the field and respond to it. Research on visual perception servo movement technology presents certain challenges

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
  • RGBD-information-based small soccer robot recognition, tracking and grabbing method
  • RGBD-information-based small soccer robot recognition, tracking and grabbing method
  • RGBD-information-based small soccer robot recognition, tracking and grabbing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0050] In this embodiment, it is necessary to equip a small football robot that does not originally have an independent vision and independent computing processing system with a vision unit and a computing chip. Due to the need to obtain separate vision, this embodiment adds an Intel RealSense D435 depth camera to the robot, so that the robot can obtain a visual image in front of the robot.

[0051] The first step to realize the recognition and tracking of the ball is to recognize the position of the ball from the visual image. figure 2 As shown, it will be described in detail below.

[0052] 1. Visual recognition

[0053] 1.1 Obtaining visual information: As the hardware uses Intel RealSense D435 depth camera as the sensing element, Intel’s official RealSense SDK (Software Development Kit): librealsense can be used to obtain RGB image information, depth information, and point cloud information. The specific API interfaces include pipe.wait_for_frames() for obtaining Frameset, get_...

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, which belongs to the technical field of visual perception type servo moving, discloses an RGBD-information-based small soccer robot recognition, tracking and grabbing method. At present, all mobile and information sources of the existing small soccer robot rely on the full-area camera at a high altitude and the small soccer robot does not have independent vision and independent computing processing system and moves by performing instructions from a computer side; and when the full-area camera fails to work, the small soccer robot becomes blind completely to cause the failure. However, the small soccer robot is provided with a depth camera as a sensing element; and the robot has the independent vision by cooperating with the corresponding control algorithm. When the robot hasthe independent vision, the robot has the self-awareness ability to plays an important role. The small soccer robot is especially suitable for serving as a goalkeeper; and the soccer can be blocked based on the trajectory of the soccer.

Description

Technical field [0001] The invention belongs to the field of visual perception servo movement, and specifically relates to a method for identifying, tracking and capturing a small football robot based on RGBD information. Background technique [0002] The idea of ​​a robot football game was first proposed by Professor Alan Mackworth of the University of British Columbia in Canada in 1992 in the paper "On Seeing Robots". Its purpose is to practice and verify related theories and technologies through a standard platform, and effectively promote the field of robots and artificial intelligence. development of. In 1996, under the advocacy of Carnegie Mellon University and other scholars, the RoboCup Robot World Cup competition was officially established, and gradually developed one of the most influential robot competitions in the world. The goal is to be selected by RoboCup by 2050. The champion plays a friendly match with the human World Cup football champion. [0003] The small soc...

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
IPC IPC(8): G05D1/02
CPCG05D1/0251G05D1/0223G05D1/0221G05D1/0276
Inventor 陈泽希黄哲远王云凯方献泽熊蓉
Owner ZHEJIANG UNIV
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