Intelligent Seven-DoF Robot With Dynamic Obstacle Avoidance and 3-D Object Recognition for Industrial Cyber–Physical Systems in Manufacturing Automation

Luo, Ren C.; Kuo, C.‐C. Jay

doi:10.1109/jproc.2015.2508598

Cited by 47 publications

(19 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(5) Label the area that conforms to the color of the target object. (6) Clipping and outputting the area in the label through the coordinates of the label. (7) A Gaussian filter is used to smooth the output labels, and then the first derivative finite difference, nonmaximum suppression and double threshold algorithm are used to detect the labels.…”

Section: ) Image Recognitionmentioning

confidence: 99%

“…For this reason, a system structure of the robot arm system is proposed. The realization of this system includes object recognition based on 3d modeling, a grasping database of objects and online non-contact obstacle avoidance based on human-computer interaction security [6]. Over the years, object recognition technology for real world applications has developed rapidly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Study of Mechanical Arm and Intelligent Robot

Lee

2020

IEEE Access

View full text Add to dashboard Cite

As an important part of the automation industrial system, the mechanical arm robot plays an important role in service, exploration, automation engineering and other fields, and has broad application prospects. The traditional mechanical arm and Sobel edge detection methods have some shortcomings: 1. The PID method is separated from the ontology model and only carries out simple and multiple calculations according to the code of the steering engine, which is not stable enough and will take more time; 2. In some complex environments, while Sobel edge detection detects the shape of objects, the separation between the subject and background is not clear, making it impossible to obtain accurate object information. Therefore, this paper proposes a new PID method and Canny edge detection algorithm: 1. The PID method combined with three-dimensional coordinate system modeling, achieves a more stable, faster and more robust calculation formula, to complete the mechanical arm grasping function; 2. Use of Canny edge detection and the three-dimensional coordinate system to analyze the object image to obtain accurate information about the target object.

show abstract

Section: ) Image Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Study of Mechanical Arm and Intelligent Robot

Lee

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The architecture of the robot subsystem in a cyber-physical system manufacturing process and its implementation are provided by Luo and Kuo. 24 Hernández-Barragán et al 25 put forward an approach to solve dual-arm cooperative manipulation tasks using the differential evolution algorithm. Š uligoj et al 26 present a working multi-agent robot application using a stereo vision in a laboratory environment.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Selective Compliance Articulated Robot Arm robot with object recognition in a multi-agent manufacturing system

Zakhama

Charrabi

Jelassi

2019

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Nowadays, industry tends to adopt the smart factory concept in their production. Technology intelligence is applied to use all the resources efficiently. Robots and vision system are masters in this kind of industry. However, information transfer between the robot controller and the vision system poses a great challenge. Data exchange between these two systems shall be secure, and the transfer must be with a very high level of accuracy. In this article, a multi-platform software application using a vision system is performed to control a Selective Compliance Articulated Robot Arm robot. The software solution includes the detection of defaults in a product by calculating a compliance rate using an efficient algorithm. An analysis of four different algorithms related to histogram-based similarity functions is set. Then, the most efficient algorithm is integrated into the application that provides a secure communication between three different operating systems. Experiments in a multi-agent manufacturing center validate the effectiveness of the proposed method. Tests demonstrate the efficiency of the data transfer between the vision system and the multi-platform software application and the Selective Compliance Articulated Robot Arm robot. This data transfer can be controlled in a high accuracy manner without any additional manual parameters tuning.

show abstract

“…The source code is available online: https://github.com/PeizhiShi/SsdNet. machine fault diagnosis [5], predictive maintenance [6], 3D object acquisition [7], retrieval [8], and recognition [9] for manufacturing automation), as well as in other research areas (e.g. image retrieval [10], medical volume segmentation [11]).…”

Section: Introductionmentioning

confidence: 99%

Intersecting Machining Feature Localization and Recognition via Single Shot Multibox Detector

Shi

Qin

et al. 2021

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

In Industrie 4.0, machines are expected to become autonomous, self-aware and self-correcting. One important step in the area of manufacturing is feature recognition that aims to detect all the machining features from a 3D model. In this research area, recognising and locating a wide variety of highly intersecting features are extremely challenging as the topology information of features is substantially damaged because of the feature intersection. Motivated by the single shot multibox detector (SSD), this paper presents a novel deep learning approach named SsdNet to tackle the machining feature localisation and recognition problem. The typical SSD is designed for 2D image objection detection rather than 3D feature recognition. Therefore, the network architecture and output of SSD are modified to fulfil the purpose of this research. In addition, some advanced techniques are also utilised to further enhance the recognition performance. Experimental results on the benchmark dataset confirm that the proposed method achieves the state-of-the-art feature recognition performance (95.20% F-score), localisation performance (90.62% F-score) and recognition efficiency (243.85 milliseconds per model).

show abstract

Intelligent Seven-DoF Robot With Dynamic Obstacle Avoidance and 3-D Object Recognition for Industrial Cyber–Physical Systems in Manufacturing Automation

Cited by 47 publications

References 87 publications

The Study of Mechanical Arm and Intelligent Robot

The Study of Mechanical Arm and Intelligent Robot

Intelligent Selective Compliance Articulated Robot Arm robot with object recognition in a multi-agent manufacturing system

Intersecting Machining Feature Localization and Recognition via Single Shot Multibox Detector

Contact Info

Product

Resources

About