Development of an automatic fruit sorting robot based on object detection algorithm

In recent years, agricultural robots have becomes an increasingly popular filed, which bring huge development and innovation to the agriculture. Among these robot-related technologies, visual information is an important information for robots operating in unstructured environment. This project aims...

Full description

Saved in:
Bibliographic Details
Main Author: Wang, Ke
Other Authors: Cheah Chien Chern
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/157566
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-157566
record_format dspace
spelling sg-ntu-dr.10356-1575662022-05-12T08:50:32Z Development of an automatic fruit sorting robot based on object detection algorithm Wang, Ke Cheah Chien Chern School of Electrical and Electronic Engineering ECCCheah@ntu.edu.sg Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics In recent years, agricultural robots have becomes an increasingly popular filed, which bring huge development and innovation to the agriculture. Among these robot-related technologies, visual information is an important information for robots operating in unstructured environment. This project aims to design a banana sorting robot system base on an object detection neural network called YOLOv5(You Look Only Once) algorithm. Specifically, this project includes the preparation of the bananas dataset and use the dataset to train the YOLOv5 network. The image preprocessing is applied to acquire the binary image and find the picking point on the banana. Camera calibration and eye-hand calibration are also performed to obtain the coordinate of the picking point with respect to the robot base coordinate frame. A UR5e robot is used in this project and the RTDE(Real Time Data Exchange) package constructs the connection between the PC and the UR5e robot. Then a python code and its corresponding robot program are designed to operate the UR5e robot to complete the banana grabbing task. In the end, a practical experiment shows that the bananas can be successfully detected and picked up. Master of Science (Computer Control and Automation) 2022-05-12T08:50:32Z 2022-05-12T08:50:32Z 2022 Thesis-Master by Coursework Wang, K. (2022). Development of an automatic fruit sorting robot based on object detection algorithm. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157566 https://hdl.handle.net/10356/157566 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
spellingShingle Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
Wang, Ke
Development of an automatic fruit sorting robot based on object detection algorithm
description In recent years, agricultural robots have becomes an increasingly popular filed, which bring huge development and innovation to the agriculture. Among these robot-related technologies, visual information is an important information for robots operating in unstructured environment. This project aims to design a banana sorting robot system base on an object detection neural network called YOLOv5(You Look Only Once) algorithm. Specifically, this project includes the preparation of the bananas dataset and use the dataset to train the YOLOv5 network. The image preprocessing is applied to acquire the binary image and find the picking point on the banana. Camera calibration and eye-hand calibration are also performed to obtain the coordinate of the picking point with respect to the robot base coordinate frame. A UR5e robot is used in this project and the RTDE(Real Time Data Exchange) package constructs the connection between the PC and the UR5e robot. Then a python code and its corresponding robot program are designed to operate the UR5e robot to complete the banana grabbing task. In the end, a practical experiment shows that the bananas can be successfully detected and picked up.
author2 Cheah Chien Chern
author_facet Cheah Chien Chern
Wang, Ke
format Thesis-Master by Coursework
author Wang, Ke
author_sort Wang, Ke
title Development of an automatic fruit sorting robot based on object detection algorithm
title_short Development of an automatic fruit sorting robot based on object detection algorithm
title_full Development of an automatic fruit sorting robot based on object detection algorithm
title_fullStr Development of an automatic fruit sorting robot based on object detection algorithm
title_full_unstemmed Development of an automatic fruit sorting robot based on object detection algorithm
title_sort development of an automatic fruit sorting robot based on object detection algorithm
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/157566
_version_ 1734310237742039040