Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Machine-Learning Techniques for Robotics
share announcement

Machine-Learning Techniques for Robotics

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Robotics and Automation".

Deadline for manuscript submissions: closed (10 December 2021) | Viewed by 13266

Special Issue Editors

Dr. Kouroush Jenab

E-Mail Website
Guest Editor
Department of Engineering Sciences, Morehead State University, 150 University Blvd, Morehead, KY 40351, USA
Interests: intelligent fault detection and recovery; condition based monitoring, reliability; manufacturing systems; robotics; VR/RL based failure analysis
Special Issues, Collections and Topics in MDPI journals
Dr. Jorge A. Ortega-Moody

E-Mail Website
Guest Editor
Department of Engineering and Technology Management, Morehead State University, 150 University Blvd, Morehead, KY 40351, USA
Interests: intelligent control systems; heuristic algorithms applied to industrial processes and automation

Special Issue Information

Dear Colleagues,

Robots are common in manufacturing and in other fields, such as medicine and education, where they operate directly alongside humans in the various processes involved. The rise of collaborative robotics has opened up new possibilities for societies and industry. They are becoming smarter, gaining the ability to carry out complex activities that require more adaptation and intelligence. Artificial intelligence and its subset, machine learning, can power robots to complete substantial activities.
As a result, further development in machine learning for robotics is becoming more important than ever before. Therefore, this Special Issue will bring together papers which particularly describe recent advances in artificial intelligence, machine learning, and deep learning, with an emphasis on robotics in manufacturing and healthcare. Papers that include practical experimental results are particularly encouraged.

Dr. Kouroush Jenab
Dr. Jorge A. Ortega-Moody
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Artificial intelligence in robotics
  • Machine learning in robotics
  • Deep learning and robotic
  • Fault detection and machine learning
  • Quality and reliability with machine learning
  • Smart robots
  • Big data for robotics
  • Virtual reality for robotic platform
  • Automation
  • Learning machine algorithms
  • Learning machine and robotic scheduling

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

12 pages, 8373 KiB  
Article
Robo-HUD: Interaction Concept for Contactless Operation of Industrial Cobotic Systems
by Dominykas Strazdas, Jan Hintz and Ayoub Al-Hamadi
Appl. Sci. 2021, 11(12), 5366; https://0-doi-org.brum.beds.ac.uk/10.3390/app11125366 - 09 Jun 2021
Cited by 8 | Viewed by 2569
Abstract
Intuitive and safe interfaces for robots are challenging issues in robotics. Robo-HUD is a gadget-less interaction concept for contactless operation of industrial systems. We use virtual collision detection based on time-of-flight sensor data, combined with augmented reality and audio feedback, allowing the operators [...] Read more.
Intuitive and safe interfaces for robots are challenging issues in robotics. Robo-HUD is a gadget-less interaction concept for contactless operation of industrial systems. We use virtual collision detection based on time-of-flight sensor data, combined with augmented reality and audio feedback, allowing the operators to navigate a virtual menu by “hover and hold” gestures. When incorporated with virtual safety barriers, the collision detection also functions as a safety feature, slowing or stopping the robot if a barrier is breached. Additionally, a user focus recognition module monitors the awareness, enabling the interaction only when intended. Early case studies show that these features present good use-cases for inspection tasks and operation in difficult environments, where contactless operation is needed. Full article
(This article belongs to the Special Issue Machine-Learning Techniques for Robotics)
►▼ Show Figures

Graphical abstract

14 pages, 5726 KiB  
Article
A Portable Intuitive Haptic Device on a Desk for User-Friendly Teleoperation of a Cable-Driven Parallel Robot
by Jae-Hyun Park, Min-Cheol Kim, Ralf Böhl, Sebastian Alexander Gommel, Eui-Sun Kim, Eunpyo Choi, Jong-Oh Park and Chang-Sei Kim
Appl. Sci. 2021, 11(9), 3823; https://0-doi-org.brum.beds.ac.uk/10.3390/app11093823 - 23 Apr 2021
Cited by 5 | Viewed by 2336
Abstract
This paper presents a compact-sized haptic device based on a cable-driven parallel robot (CDPR) mechanism for teleoperation. CDPRs characteristically have large workspaces and lightweight actuators. An intuitive and user-friendly remote control has not yet been achieved, owing to the unfamiliar multiple-cable configuration of [...] Read more.
This paper presents a compact-sized haptic device based on a cable-driven parallel robot (CDPR) mechanism for teleoperation. CDPRs characteristically have large workspaces and lightweight actuators. An intuitive and user-friendly remote control has not yet been achieved, owing to the unfamiliar multiple-cable configuration of CDPRs. To address this, we constructed a portable compact-sized CDPR with the same configuration as that of a larger fully constrained slave CDPR. The haptic device is controlled by an admittance control for stiffness adjustment and implemented in an embedded microprocessor-based controller for easy installation on an operator’s desk. To validate the performance of the device, we constructed an experimental teleoperation setup by using the prototyped portable CDPR as a master and larger-size CDPR as a slave robot. Experimental results showed that a human operator can successfully control the master device from a remote site and synchronized motion between the master and slave device was performed. Moreover, the user-friendly teleoperation could intuitively address situations at a remote site and provide an operator with realistic force during the motion of the slave CDPR. Full article
(This article belongs to the Special Issue Machine-Learning Techniques for Robotics)
►▼ Show Figures

Figure 1

17 pages, 1933 KiB  
Article
Variable Compliance Control for Robotic Peg-in-Hole Assembly: A Deep-Reinforcement-Learning Approach
by Cristian C. Beltran-Hernandez, Damien Petit, Ixchel G. Ramirez-Alpizar and Kensuke Harada
Appl. Sci. 2020, 10(19), 6923; https://0-doi-org.brum.beds.ac.uk/10.3390/app10196923 - 02 Oct 2020
Cited by 92 | Viewed by 7541
Abstract
Industrial robot manipulators are playing a significant role in modern manufacturing industries. Though peg-in-hole assembly is a common industrial task that has been extensively researched, safely solving complex, high-precision assembly in an unstructured environment remains an open problem. Reinforcement-learning (RL) methods have proven [...] Read more.
Industrial robot manipulators are playing a significant role in modern manufacturing industries. Though peg-in-hole assembly is a common industrial task that has been extensively researched, safely solving complex, high-precision assembly in an unstructured environment remains an open problem. Reinforcement-learning (RL) methods have proven to be successful in autonomously solving manipulation tasks. However, RL is still not widely adopted in real robotic systems because working with real hardware entails additional challenges, especially when using position-controlled manipulators. The main contribution of this work is a learning-based method to solve peg-in-hole tasks with hole-position uncertainty. We propose the use of an off-policy, model-free reinforcement-learning method, and we bootstraped the training speed by using several transfer-learning techniques (sim2real) and domain randomization. Our proposed learning framework for position-controlled robots was extensively evaluated in contact-rich insertion tasks in a variety of environments. Full article
(This article belongs to the Special Issue Machine-Learning Techniques for Robotics)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop