Vitor Manuel Filipe

Abstract
The manual monitoring of refilling stations in industrial environments can lead to inefficiencies and errors, which can impact the overall performance of the production line. In this paper, we present an unsupervised detection pipeline for identifying refilling stations in industrial environments. The proposed pipeline uses a combination of image processing, pattern recognition, and deep learning techniques to detect refilling stations in visual data. We evaluate our method on a set of industrial images, and the findings demonstrate that the pipeline is reliable at detecting refilling stations. Furthermore, the proposed pipeline can automate the monitoring of refilling stations, eliminating the need for manual monitoring and thus improving industrial operations’ efficiency and responsiveness. This method is a versatile solution that can be applied to different industrial contexts without the need for labeled data or prior knowledge about the location of refilling stations. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Artificial intelligence (AI) has gained significant evolution in recent years that, if properly harnessed, may meet or exceed expectations in a wide range of application fields. However, because Machine Learning (ML) models have a black-box structure, end users frequently seek explanations for the predictions made by these learning models. Through tools, approaches, and algorithms, Explainable Artificial Intelligence (XAI) gives descriptions of black-box models to better understand the models’ behaviour and underlying decision-making mechanisms. The AI development in companies enables them to participate in Industry 4.0. The need to inform users of transparent algorithms has given rise to the research field of XAI. This paper provides a brief overview and introduction to the subject of XAI while highlighting why this topic is generating more and more attention in many sectors, such as industry. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
To tackle wildfires and improve forest biomass management, cost effective and reliable mowing and pruning robots are required. However, the development of visual perception systems for forestry robotics needs to be researched and explored to achieve safe solutions. This paper presents two main contributions: an annotated dataset and a benchmark between edge-computing hardware and deep learning models. The dataset is composed by nearly 5,400 annotated images. This dataset enabled to train nine object detectors: four SSD MobileNets, one EfficientDet, three YOLO-based detectors and YOLOR. These detectors were deployed and tested on three edge-computing hardware (TPU, CPU and GPU), and evaluated in terms of detection precision and inference time. The results showed that YOLOR was the best trunk detector achieving nearly 90% F1 score and an inference average time of 13.7ms on GPU. This work will favour the development of advanced vision perception systems for robotics in forestry operations.

Abstract
In the current technological scenario of artificial intelligence growth, especially using machine learning, large datasets are necessary. Recommender systems appear with increasing frequency with different techniques for information filtering. Few large wine datasets are available for use with wine recommender systems. This work presents X-Wines, a new and consistent wine dataset containing 100,000 instances and 21 million real evaluations carried out by users. Data were collected on the open Web in 2022 and pre-processed for wider free use. They refer to the scale 1-5 ratings carried out over a period of 10 years (2012-2021) for wines produced in 62 different countries. A demonstration of some applications using X-Wines in the scope of recommender systems with deep learning algorithms is also presented.

Abstract
Bin picking is a challenging task involving many research domains within the perception and grasping fields, for which there are no perfect and reliable solutions available that are applicable to a wide range of unstructured and cluttered environments present in industrial factories and logistics centers. This paper contributes with research on the topic of object segmentation in cluttered scenarios, independent of previous object shape knowledge, for textured and textureless objects. In addition, it addresses the demand for extended datasets in deep learning tasks with realistic data. We propose a solution using a Mask R-CNN for 2D object segmentation, trained with real data acquired from a RGB-D sensor and synthetic data generated in Blender, combined with 3D point-cloud segmentation to extract a segmented point cloud belonging to a single object from the bin. Next, it is employed a re-configurable pipeline for 6-DoF object pose estimation, followed by a grasp planner to select a feasible grasp pose. The experimental results show that the object segmentation approach is efficient and accurate in cluttered scenarios with several occlusions. The neural network model was trained with both real and simulated data, enhancing the success rate from the previous classical segmentation, displaying an overall grasping success rate of 87.5%.