Abstract
The digital twin has been gaining significant attention from the academia and industry sectors in the last few years. The digital twin concept enables monitoring, diagnosis, optimisation, and decision support tasks to improve industrial systems operation. One of the identified challenges in this field is the need to improve the decision support cycle by decreasing decision-making time and improving the accuracy of recommendations by considering human intervention in the cycle. Bearing this in mind, the paper explores the use of trust models to improve the recommendation cycle in the digital twin. For this purpose, a literature overview on trust applied in recommendation systems was performed, focusing on the concept, its properties and previous models. Considering this analysis, a trust-based model is specified in a digital twin artificial intelligence-based recommendation system. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
The manufacturing domain faces a challenge in making timely decisions due to the large amounts of data generated by digital technologies such as Internet-of-Things, Artificial Intelligence (AI), Digital Twin, and Big Data. By integrating recommendation systems is possible to support the decision-makers in handling large amounts of data by delivering personalised, accurate, and quality recommendations. One example is the SimQL recommendation model that incorporates AI algorithms with trust and similarity measures to enhance recommendation quality. This paper aims to analyse the sensitivity of the SimQL model's parameters, such as dataset conditions, trust and learning factors, and their impact on the final recommendation quality. A fuzzy logic approach is employed to evaluate the model and identify optimal operating conditions for the recommendation system. By implementing the findings of this study, manufacturers can improve the acceptance and adoption of the SimQL trustworthy recommendation system in this field.

Abstract

Abstract
Robotic competitions stand as platforms to propel the forefront of robotics research while nurturing STEM education, serving as hubs of both applied research and scientific innovation. In Portugal, the Portuguese Robotics Open (FNR) is an event with several robotic competitions, including the Robot@Factory 4.0 competition. This competition presents an example of deploying autonomous robots on a factory shop floor. Although the literature has works proposing frameworks for the original version of the Robot@Factory competition, none of them proposes a system framework for the Robot@Factory 4.0 version that presents the hardware, firmware, and software to complete the competition and achieve autonomous navigation. This paper proposes a complete robotic framework for the Robot@Factory 4.0 competition that is modular and open-access, enabling future participants to use and improve it in future editions. This work is the culmination of all the knowledge acquired by winning the 2022 and 2023 editions of the competition.

Abstract
The extraction of geometric information from the environment may be of interest to localisation and mapping algorithms. Existent literature on extracting geometric features from 2D laser data focuses mainly on detecting lines. Regarding corners, most methodologies use the intersection of line segment features. This paper presents a feature extraction algorithm for corner-like points in the 2D laser scan. The proposed methodol-ogy defines arrival and departure neighbourhoods around each scan point and performs local line fitting evaluated in multiple distance-based scales. Then, a set of indicators based on line fitting error, the angle between arrival and departure lines, and consecutive observation of the same keypoint across different scales determine the existence of a corner-like feature. The experiments evaluated the corner-like features regarding their relative position and observability, achieving standard deviations on the relative position lower than the sensor noise and visibility ratios higher than 75% with very low false positives rates. © 2024 IEEE.

Abstract
Precision spraying in agriculture is crucial for optimizing the application of pesticides while minimizing environmental impact. Despite significant advancements in control models for spraying systems, predictive control algorithms were not used. This paper addresses this gap by proposing a real-time control framework that integrates predictive control strategies to ensure consistent pressure output in a trailer sprayer. Based on information from various sensors, the framework anticipates and adapts to dynamic environmental conditions, enhancing accuracy and sustainability in spraying practices. A methodology is developed to define a proportional valve model. Based on this valve model, the predictive control model optimizes valve movements to minimize errors between predicted and reference pressures, thereby improving spraying efficiency. This study demonstrates the viability of predictive control in improving precision spraying systems applicable to autonomous robots, encouraging future advances in agricultural spraying technologies.