Skip to content

The robot can position it self within a three dimensional coordinate system. Locating and sorting of objects by the use of computer vision and Convolutional Neural Network. Fast and accurate, and will work in robust environments.

License

Notifications You must be signed in to change notification settings

magnusoy/Pick-And-Sort-Robot

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Pick-And-Sort-Robot

The aim for this project is to build a prototype of an autonomous industrial robot as proof ofconcept for future automated solutions in sorting systems. The robot will operate on a frame system, where the objects are localized under, and in between the frame. The main task willbe to detect, classify and sort the objects as fast and accurate as possible. Where as the core objectives for creating this robot is mentioned below:

  • Design and develop a prototype robot suited to operate in various types of system, like forexample a conveyor belt system. It needs to have high enough accuracy in both classifi-cation and movement. During development, concurrency and thread safe operations willbe taken into account.

  • Program the robot so it can position it self within a three dimensional coordinate system.

  • Develop software for locating and sorting of objects by the use of computer vision and Convolutional Neural Network.

  • Develop a system that is fast and accurate, and will work in robust environments.

  • Assemble the prototype and test it according to specified requirements.

  • Design and implement a graphical user interface that can easily be operated by instructed personnel.

Demo

Demo video

Report

Report

Built With

Authors

License

This project is licensed under the MIT License - see the LICENSE.md file for details

About

The robot can position it self within a three dimensional coordinate system. Locating and sorting of objects by the use of computer vision and Convolutional Neural Network. Fast and accurate, and will work in robust environments.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •