Abstract
Robotics and intelligent systems are key technologies to promote efficient and innovative applications in the most diverse domains (industry, healthcare, agriculture, construction, mobility, etc [...]

Abstract
Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is unfeasible for open-field robots with limited energy. This work benchmarks the performance of different heterogeneous platforms for object detection in real-time. This research benchmarks three architectures: embedded GPU-Graphical Processing Units (such as NVIDIA Jetson Nano 2 GB and 4 GB, and NVIDIA Jetson TX2), TPU-Tensor Processing Unit (such as Coral Dev Board TPU), and DPU-Deep Learning Processor Unit (such as in AMD-Xilinx ZCU104 Development Board, and AMD-Xilinx Kria KV260 Starter Kit). Methods: The authors used the RetinaNet ResNet-50 fine-tuned using the natural VineSet dataset. After the trained model was converted and compiled for target-specific hardware formats to improve the execution efficiency.Conclusions and Results: The platforms were assessed in terms of performance of the evaluation metrics and efficiency (time of inference). Graphical Processing Units (GPUs) were the slowest devices, running at 3 FPS to 5 FPS, and Field Programmable Gate Arrays (FPGAs) were the fastest devices, running at 14 FPS to 25 FPS. The efficiency of the Tensor Processing Unit (TPU) is irrelevant and similar to NVIDIA Jetson TX2. TPU and GPU are the most power-efficient, consuming about 5 W. The performance differences, in the evaluation metrics, across devices are irrelevant and have an F1 of about 70 % and mean Average Precision (mAP) of about 60 %.

Abstract
This paper presents an approach for a multi-agent-based cyber-physical system dedicated to operating the warehouse plant with a distributed approach. The recent technological evolution has improved the quality and robustness of the services for current warehouses. However, systems that operate warehouses do not follow this evolution, presenting predominantly central monolithic or hierarchical approaches, resulting in fragility related to flexibility, scalability, and robustness in the face of disturbances. In the proposed approach, each warehouse physical component has a computational unit associated, i.e. a cyber agent, with communication, negotiation, and data analysis capabilities. Agents contain all the information, algorithms, and functions necessary to operate the physical component, and instead of receiving orders from higher-layer agents, they negotiate and collaborate to perform the tasks. The proposed system was tested in a laboratory testbed, composed of six racks and up to eight robots for transporting products. Extensive experiments show the feasibility of the approach. Copyright (c) 2023 The Authors.

Abstract
Os autores apresentam a Aprendizagem Baseada em Soluções Efetivas que deriva da Aprendizagem Baseada em Projeto, mas aplicada a problemas reais com objetivo de contruir soluções efetivas. A enfase é colocada na efetividade no pressuposto que incentiva a um maior envolvimento e comprometimento por parte dos alunos, assegurando um contexto que se pretende mais aliciante e próximo do que será a realidade profissional dos alunos. A efetividade é aferida pelas funcionalidades consideradas essenciais à plena utilização e resolução do problema, mas também pela viabilidade da aplicação ser efetivamente utilizada, sem que seja necessário a continuidade do envolvimento dos alunos. As evidências empíricas apontam um claro aumento da aquisição de competências, do número de aprovados e das classificações. Permitiu também definir um posicionamento estratégico de cooperação com a comunidade envolvente, em que todas as partes beneficiam (formandos, docentes, instituição de ensino, entidades locais e regionais e empregadores).

Abstract
In contemporary society, there is a growing demand for professionals with the essential skills required in the 21st century. The STEAM (Science, Technology, Engineering, Arts, and Mathematics) disciplines have emerged as pivotal in facilitating the acquisition of these skills. Indeed, these disciplines have exhibited their capacity to enhance workforce performance and fortify a nation's innovation potential, emphasizing the critical need to promote STEAM education among students and integrate it into existing educational curricula. Nonetheless, the inclusion of students with intellectual or developmental disabilities (IDD) in these disciplines presents formidable challenges. These challenges can be attributed to prevailing low expectations regarding the potential of disabled individuals to excel in STEAM fields, the inaccessibility of STEAM education curricula, and the limitations that educators face in fully supporting the integration of students with disabilities. In response to these challenges, we introduce the RoboSTEAMSEN project. The principal objective of the RoboSTEAMSEN project is to bolster educational processes by equipping teachers working with students with IDD with methodologies and tools that employ Robotics and Active Learning Methodologies to promote STEAM education. The project's overarching goals encompass comprehending the specific needs of disabled students and adapting robotics and active learning techniques to accommodate various disabilities, designing comprehensive training programs for teachers to enable them to individualize the learning experiences of students with IDD, establishing a community of practice supported by a technological ecosystem that serves as a central hub for educators and decision-makers to engage in discourse on how to achieve success in STEAM education for IDD students. The primary outcome of this project will be the enhancement of STEAM education for students with IDD. To achieve this objective, we will develop a taxonomy for the categorization of resources tailored to this demographic, institute a user model for personalized learning, generate guides, resources, and courses for teachers, formulate workshop models for the wider dissemination of project findings, and establish a technological ecosystem to facilitate a thriving community of practice dedicated to this important educational domain. © 2023 Copyright for this paper by its authors.

Abstract
The smart cities paradigm covers multiple domains which span from citizens' accessibility and mobility to general infrastructures and services. Hence, smart cities can be seen as an excellent showcase of heterogeneity, namely at the data level. For this reason, they are a perfect candidate for linked data and semantic web concept applications. This powerful combination leads to interoperability at the data level which is one of the ultimate goals of the Internet of Things (IoT). In this reference frame, NGSI-LD is an open framework for context information processing consisting of both a semantic information model and a RESTful Application Programming Interface (API). This paper proposes a methodology for creating semantic data models in the context of IoT, namely to represent and describe data associated with digital twins. The methodology is presented in a practical way, through the process of creating an NGSI-LD semantic data model for the VALLPASS project, inserted in the traffic domain, which is one of the most popular in smart cities.