Intelligent Robotic and Mechatronic Systems in Agricultural and Environmental Education

A special issue of Robotics (ISSN 2218-6581). This special issue belongs to the section "Agricultural and Field Robotics".

Deadline for manuscript submissions: 31 October 2024 | Viewed by 699

Special Issue Editors


E-Mail Website
Guest Editor
Department of Natural Resources Development and Agricultural Engineering, School of Environment and Agricultural Engineering, Agricultural University of Athens, 75 Iera Odos Street, 11855 Athens, Greece
Interests: IoT networks; artificial intelligence; embedded systems; robotics; innovative systems in agriculture; engineering education
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Natural Resources Development and Agricultural Engineering, School of Environment and Agricultural Engineering, Agricultural University of Athens, 75 Iera Odos Street, 11855 Athens, Greece
Interests: process control; computational intelligence; automation in agriculture; wireless sensor networks; microgrids’ management
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Natural Resources Development and Agricultural Engineering, School of Environment and Agricultural Engineering, Agricultural University of Athens, 75 Iera Odos Street, 11855 Athens, Greece
Interests: renewable energy and environmental technologies’ development and implementation, including applications in agriculture and food processing; water processing powered by renewable energy (solar photovoltaic and wind) and other energy sources; development and application of microgrids; development of systems for power supply based on the organic Rankine cycle (ORC) and on biofuels’ deployment for power production
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Historically, technology has aimed to find solutions in order to tackle intense problems, like the increased nutritional needs of the population on Earth, the depletion of natural resources, the lack of human labor, and the harsh working and living environment. Modern disciplines like robotics and mechatronics, integrating elements including, but not limited to, mechanical, electrical, and electronic engineering, control, measurement, networking, and computer science, are amongst the most promising technological pillars of the abovementioned efforts. Indeed, machines are tireless workers able to perform repetitive tasks at a constantly high quality. Furthermore, they become smarter and capable of more composite interaction with the environment and humans. Consequently, the emerging progress in the area is further raising the need for well-educated personnel to be involved in constructing, parameterizing, servicing, or utilizing the corresponding robotic and mechatronic systems.

At the other end of the spectrum, one of the greatest challenges for educational institutions is that modern students should be prepared for jobs that, in many cases, have not yet been invented, combining a lot of diverse disciplines. Unfortunately, multidisciplinary capabilities are not among the strengths of teachers nor professors, while the selection of the right mixture of hardware and software components and teaching methods is not an easy task. In order to bridge this gap, modern robotic and mechatronic systems can be compiled to create educationally beneficial examples to better prepare students for the digital era. Indeed, these systems, even in simplified trimmed-down versions, constitute multi-perspective cases of innovation that can drastically facilitate the understanding of a wider set of cutting-edge technologies already transforming our way of living and working. Beyond this, the study of their idiosyncrasies provides inspiration for a more efficient exploitation of technology for the common good, like making agriculture more efficient and environmentally friendly or increasing the performance of renewable resource management systems.

This Special Issue encourages submissions that are willing to offer guidelines, experiences, or prototype exemplification in line with the abovementioned directions. Review works, as well as novel research findings, drawing a paradigm from secondary to postgraduate education and vocational training, that discuss intelligent robotic and mechatronic systems, preferably of an agricultural or environmental character, are welcome to be submitted to this Special Issue.

Dr. Dimitrios Loukatos
Dr. Konstantinos G. Arvanitis
Prof. Dr. Georgios Papadakis
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. Robotics is an international peer-reviewed open access monthly 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 1800 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

  • intelligent robotics
  • mechatronic systems
  • agricultural robotics
  • engineering education

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 9110 KiB  
Article
Imitation Learning from a Single Demonstration Leveraging Vector Quantization for Robotic Harvesting
by Antonios Porichis, Myrto Inglezou, Nikolaos Kegkeroglou, Vishwanathan Mohan and Panagiotis Chatzakos
Robotics 2024, 13(7), 98; https://doi.org/10.3390/robotics13070098 - 30 Jun 2024
Viewed by 495
Abstract
The ability of robots to tackle complex non-repetitive tasks will be key in bringing a new level of automation in agricultural applications still involving labor-intensive, menial, and physically demanding activities due to high cognitive requirements. Harvesting is one such example as it requires [...] Read more.
The ability of robots to tackle complex non-repetitive tasks will be key in bringing a new level of automation in agricultural applications still involving labor-intensive, menial, and physically demanding activities due to high cognitive requirements. Harvesting is one such example as it requires a combination of motions which can generally be broken down into a visual servoing and a manipulation phase, with the latter often being straightforward to pre-program. In this work, we focus on the task of fresh mushroom harvesting which is still conducted manually by human pickers due to its high complexity. A key challenge is to enable harvesting with low-cost hardware and mechanical systems, such as soft grippers which present additional challenges compared to their rigid counterparts. We devise an Imitation Learning model pipeline utilizing Vector Quantization to learn quantized embeddings directly from visual inputs. We test this approach in a realistic environment designed based on recordings of human experts harvesting real mushrooms. Our models can control a cartesian robot with a soft, pneumatically actuated gripper to successfully replicate the mushroom outrooting sequence. We achieve 100% success in picking mushrooms among distractors with less than 20 min of data collection comprising a single expert demonstration and auxiliary, non-expert, trajectories. The entire model pipeline requires less than 40 min of training on a single A4000 GPU and approx. 20 ms for inference on a standard laptop GPU. Full article
Show Figures

Figure 1

Back to TopTop