2021
DOI: 10.3390/su132112044
|View full text |Cite
|
Sign up to set email alerts
|

Status Recognition Using Pre-Trained YOLOv5 for Sustainable Human-Robot Collaboration (HRC) System in Mold Assembly

Abstract: Molds are still assembled manually because of frequent demand changes and the requirement for comprehensive knowledge related to their high flexibility and adaptability in operation. We propose the application of human-robot collaboration (HRC) systems to improve manual mold assembly. In the existing HRC systems, humans control the execution of robot tasks, and this causes delays in the operation. Therefore, we propose a status recognition system to enable the early execution of robot tasks without human contr… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 39 publications
0
5
0
Order By: Relevance
“…Based on other research [17][18][19] and our pilot studies, the results have shown that augmentation has a positive impact on detection accuracy. Furthermore, experiments have shown that by freezing backbones, the accuracy increases about 1.5 times.…”
Section: Experiments Methodologymentioning
confidence: 58%
“…Based on other research [17][18][19] and our pilot studies, the results have shown that augmentation has a positive impact on detection accuracy. Furthermore, experiments have shown that by freezing backbones, the accuracy increases about 1.5 times.…”
Section: Experiments Methodologymentioning
confidence: 58%
“…Te YOLO family of models, including YOLOv2, YOLOv3, YOLOv4, YOLOv5, YOLOv6, and the recent YOLOv7, are widely employed for recognition tasks. Te variations in size among the diferent models of the YOLOv5 family, such as YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x, are determined by the width and depth of the BottleneckCSP module [36]. Te primary function of the BottleneckCSP module is to extract features from the feature map, enabling the extraction of valuable information from the input image.…”
Section: Yolov5mentioning
confidence: 99%
“…Next, by applying machine learning algorithms, collisions in shared workspaces can be detected before they occur. In [10] the framework for task and status recognition for HRC in Mold Assembly using YOLOv5 was developed. The results indicated the performance had a mean average precision value of 84.8%.…”
Section: Introductionmentioning
confidence: 99%
“…Currently it is difficult to compare the effectiveness of the results obtained, due to the specific and strictly defined common workplace of humans and cobots with specific behavioural scenarios. According to the notes in the introduction, the results in works [9,10] achieved an accuracy of 90% in recognising an object and 96.4% in predicting collisions, which can be said to be satisfactory. In [23] the scenario covers the HRC space, where an operator exchanges components with one cobot.…”
mentioning
confidence: 95%