Automation and robotics in real operative conditions, like modern factories, are constantly evolving. Collaborative robots represent one of the major changes in industrial robotics and their market is undergoing strong growth. A collaborative robot is designed for direct interaction with a human to improve the work experience and to reduce the risk of injuries. Among the most important challenges in the development of collaborative robots are those related to performing tasks in unstructured environments, moving in a shared workspace, manipulating objects, and learning from expert operators (Caccavale et al., 2019). In order to achieve such goals, collaborative robots can take advantage of recent innovations in machine learning, as well as of advances in algorithms for robot perception and new sensor technologies (Chiaravalli et al., 2020; Monica and Aleotti, 2020).
The goal of this Research Topic was to investigate new methods for intelligent collaborative robots. Authors were encouraged to submit papers discussing new research findings that have been successfully evaluated by conducting experiments in real environments. A particular focus of the Research Topic has been the development of novel methods and solutions for task planning, human-robot interaction and programming by demonstration.
The Research Topic is a collection of four original research papers. In the work by Iturrate et al. a complete system for learning gluing and dispensing tasks from a single demonstration was presented that encompasses a full pipeline of demonstration, encoding and execution. The main contribution is the design of a novel unified controller for kinesthetic teaching and execution of in-contact tasks.
In their work, Mangin et al. present a method to plan supportive actions for a robot in collaborative human-robot assembly tasks. The method models uncertainty in the task by means of a Partially Observable Markov Decision Process. Unlike most works in literature, where the goal is to model uncertainty in the physical interactions or the environment, the goal here is to handle uncertainty in the human’s intentions. The resulting system supports on-the-fly replanning and error recovery.
The coordination of a task, shared between a human and a robot, is investigated in the work by Angleraud et al. from a high-level perspective. The presented coordination system is based on a set of high-level actions triggered by human commands. Both a speech-based and a graphical interface are developed and tested in typical industrial tasks like hand-over and kitting.
The work by Kramberger et al. presents a comprehensive framework for the human-robot cooperative assembly of timber structures, comprising the design of novel interlocking joints, Learning from Demonstration strategies for cooperative assembly under different operating conditions, and an enhanced simulation of the process through a digital twin.
Statements
Author contributions
All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication.
Acknowledgments
The guest editors wish to express their gratitude to the Editorial Board and staff members. We also express our sincere gratitude to the many reviewers who contributed to this Research Topic with their time and expertise. This research topic has been accepted while M. Saveriano was at the Intelligent and Interactive Systems Group, Department of Computer Science, University of Innsbruck, Innsbruck, Austria.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
1
CaccavaleR.SaverianoM.FinziA.LeeD. (2019). Kinesthetic Teaching and Attentional Supervision of Structured Tasks in Human-Robot Interaction. Auton. Robot43, 1291–1307. 10.1007/s10514-018-9706-9
2
ChiaravalliD.PalliG.MonicaR.AleottiJ.RizziniD. L. (2020). “Integration of a Multi-Camera Vision System and Admittance Control for Robotic Industrial Depalletizing,” in 25th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) (Vienna: IEEE), 1, 667–674. 10.1109/etfa46521.2020.9212020
3
MonicaR.AleottiJ. (2020). Point Cloud Projective Analysis for Part-Based Grasp Planning. IEEE Robot. Autom. Lett.5, 4695–4702. 10.1109/lra.2020.3003883
Summary
Keywords
human-robot collaboration, deep learning methods, robot perception, industrial robots, motion and task planning
Citation
Aleotti J, Saveriano M and Monica R (2022) Editorial: Learning, Perception, and Collaboration for Robots in Industrial Environments. Front. Robot. AI 9:888971. doi: 10.3389/frobt.2022.888971
Received
03 March 2022
Accepted
17 March 2022
Published
14 April 2022
Volume
9 - 2022
Edited and reviewed by
Kostas Alexis, Norwegian University of Science and Technology, Norway
Updates
Copyright
© 2022 Aleotti, Saveriano and Monica.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Jacopo Aleotti, jacopo.aleotti@unipr.it
This article was submitted to Field Robotics, a section of the journal Frontiers in Robotics and AI
Disclaimer
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.