| Issue |
ITM Web Conf.
Volume 47, 2022
2022 2nd International Conference on Computer, Communication, Control, Automation and Robotics (CCCAR2022)
|
|
|---|---|---|
| Article Number | 01031 | |
| Number of page(s) | 7 | |
| Section | Computer Science and System Design, Application | |
| DOI | https://doi.org/10.1051/itmconf/20224701031 | |
| Published online | 23 June 2022 | |
Research on items sorting robot based on SSD target detection
Southwest Petroleum University, School of Information, 637001, Nanchong, China
* Corresponding author: 201931772110@stu.swpu.edu.cn
To achieve the automatic classification of items and improve the sorting efficiency of the sorting robot. A design method of a robot based on color classification is proposed. The system uses an all-around Mcnamu wheeled mobile platform equipped with a Raspberry Pi 4B, an STM32 MCU, a USB monocular camera, and a 6-DOF robotic arm. The SSD target detection model is used to identify sorted items, and color navigation is used to locate the sorting area and complete operations such as finding, identifying, grabbing, and putting back items. The actual test results show that the robot has an average item recognition rate of 99% and a classification rate of 97.25%, which verifies the feasibility of the robot and provides a reference for research on intelligent collaboration, item classification, fast logistics, and machine vision.
Key words: SSD target detection / Items sorting / Color navigation / Mechanical control
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.