Search

Energy communities can support the energy transition, by engaging citizens through collective energy actions and generate positive economic, social and environmental outcomes. Renewable Energy Sources (RES) are gaining increasing share in the electricity mix as the economy decarbonises, with Photovoltaic (PV) plants to becoming more efficient and affordable. By incorporating Artificial Intelligence (AI) techniques, innovative applications can be developed to provide added value to energy communities. In this context, the scope of this paper is to compare Machine Learning (ML) and Deep Learning (DL) algorithms for the prediction of short-term production in a solar plant under an energy cooperative operation. Three different cases are considered, based on the data used as inputs for forecasting purposes. Lagged inputs are used to assess the historical data needed, and the algorithms' accuracy is tested for the next hour's PV production forecast. The comparative analysis between the proposed algorithms demonstrates the most accurate algorithm in each case, depending on the available data. For the highest performing algorithm, its performance accuracy in further forecasting horizons (3 hours, 6 hours and 24 hours) is also tested. [ABSTRACT FROM AUTHOR]

Virtual reality (VR) technology is increasingly vital in various sectors, particularly for simulating real environments in training and teleoperation. However, it has primarily focused on static, controlled settings like indoor industrial shopfloors. This paper proposes a novel method for remotely controlling robots in hazardous environments safely, without compromising efficiency. Operators can execute tasks from remote locations ensuring continuity regardless of distance. Real‐time efficiency is achieved by updating the virtual environment from on‐site sensors and mirroring the real environment, utilizing 3D reconstruction, Google Images, and video streams. Communication between VR and the remote robot is facilitated through a remote robot operating system connection. The efficacy of this concept will be validated through real road maintenance interventions. [ABSTRACT FROM AUTHOR]

Human–Robot Collaborative (HRC) workcells aim to elevate the conventional industrial lines, by enabling seamless interaction between operators and machines. Shifting away from standard (mainly static) workcells, with operators and machines following strictly defined limits and schedules, the new era of manufacturing introduces versatile workspaces, shared between the manufacturing resources. The non-deterministic workflow of such workspaces raises concerns over planning of task and actions among the resources, as the workcell is now a dynamic environment. Following these demands, this study introduces a solution in scheduling and assignment of assembly tasks to both human and robot resources, aiming for effective emergence of alternative task-resource assignment sequences. The proposed framework is optimized to provide a human-centered approach on the assembly line and alleviate human operators from exhaustive or unsafe tasks, while accounting for environment changes, such as positioning of resources and parts. This tool was used in a use case from the industrial modules manufacturing sector. © 2020 The Authors, Published by Elsevier B.V. Peer review under the responsibility of the scientific committee of CIRP [ABSTRACT FROM AUTHOR]

Nowadays, in order to cover the needs of market for product mass customization, industries have started to move to hybrid production cells, involving both robots and human operators. Research has been done during previous years to promote and improve the collaboration between humans and robots, trying to address topics such as safety, awareness and cognitive support in form of Augmented Reality based instructions. Results of previous research show bottlenecks related to the way of interaction of the operators with such supportive systems though. Direct interaction approach with the use of push buttons or indirect-gesture based interaction, which are most often adopted by the researchers, require operators to constantly occupy their hands performing the relevant button presses or gestures. Moreover, previous approaches are hardware dependent and need a lot of customization to work with different hardware. This work tries to address these bottlenecks proposing the usage of wearable devices enhanced with AI in order to support the interaction of human operators with robots in human-robot collaborative environments in a seamless and non-intrusive way, wrapped around a framework called "Operator Support Module" (OSM). Among others, OSM supports a variety of hardware to easily fit in various industrial scenarios. Two case studies will be presented to demonstrate the approach. [ABSTRACT FROM AUTHOR]

Over the last years both Research and Industry have tried to address the requirement for flexible production by introducing technologies that allow humans and robots to coexist and share production tasks. The focus has been to ensure the safety of humans while interacting with robots. Previous EU funded projects provided proof that humans and robots destiny is collaboration rather than competition. It has been revealed though that Human Robot Collaborative (HRC) applications present drawbacks that limit industrial adoption. SHERLOCK EU project aims to exploit the lessons learnt and the technical excellence, developing the first high payload collaborative robot (COMAU AURA), dynamically reconfigurable safety monitoring systems and smart Human Robot (HR) interfaces allowing the seamless integration of operators and robots in a common workflow. The aim is to introduce the latest safe robotic technologies including high payload collaborative arms, exoskeletons and mobile manipulators in diverse production environments, enhance them with smart mechatronics and AI based cognition and thus create efficient HRC stations that are designed to be safe and guarantee the acceptance and wellbeing of operators. [ABSTRACT FROM AUTHOR]