Artur José Cordeiro

Abstract
Robotic bin-picking is a critical operation in modern industry, which is characterised by the detection, selection, and placement of items from a disordered and cluttered environment, which can be boundary limited or not, e.g. bins, boxes or containers. In this context, perception systems are employed to localise, detect and estimate grasping points. Despite the considerable progress made, from analytical approaches to recent deep learning methods, challenges still remain. This is evidenced by the growing innovation proposing distinct solutions. This paper aims to review perception methodologies developed since 2009, providing detailed descriptions and discussions of their implementation. Additionally, it presents an extensive study, detailing each work, along with a comprehensive overview of the advancements in bin-picking perception.

Abstract
This article introduces Friday, a Mobile Manipulator (MoMa) solution designed at iiLab - INESC TEC. Friday is versatile and applicable in various contexts, including warehouses, naval shipyards, aerospace industries, and production lines. The robot features an omnidirectional platform, multiple grippers, and sensors for localisation, safety, and object detection. Its modular hardware and software system enhances functionality across different industrial scenarios. The system provides a stable platform supporting scientific advancements and meeting modern industry demands, with results verified in the aerospace, automotive, naval, and logistics.

Abstract
The implementation of deep learning approaches based on instance segmentation data remains a challenge for customized scenarios, owing to the time-consuming nature of acquiring and annotating real-world instance segmentation data, which requires a significant investment of semi-professional user labour. Obtaining high-quality labelled data demands expertise and meticulous attention to detail. This requirement can significantly impact the overall implementation process, adding to the complexity and resource requirements of customized scenarios with diverse objects. The proposed work addresses the challenge of generating labelled data for large-scale robotic bin-picking datasets by proposing an easy-to-use automated framework designed to create customized data with accurate labels from CAD models. The framework leverages a photorealistic rendering engine integrated with physics simulation, minimizing the gap between synthetic and real-world data. Models trained using the synthetic data generated by this framework achieved an Average Precision of 86.95%, comparable to the performance of models trained on real-world datasets. Furthermore, this paper provides a comprehensive multi-metric analysis across diverse objects representing distinct industrial applications, including naval, logistics, and aerospace domains. The evaluation also includes the use of three distinct instance segmentation networks, alongside a comparative analysis of the proposed approach against two generative model techniques.

Abstract
The high level of precision and consistency required for pallet detection in industrial environments and logistics tasks is a critical challenge that has been the subject of extensive research. This paper proposes a system for detecting pallets and its pockets using the You Only Look Once (YOLO) v8 Open Neural Network Exchange (ONNX) model, followed by the segmentation of the pallet surface. On the basis of the system a pipeline built on the ROS Action Server whose structure promotes modularity and ease of implementation of heuristics. Additionally, is presented a comparison between the YOLOv5 and YOLOv8 models in the detection task, trained with a customised dataset from a factory environment. The results demonstrate that the pipeline can consistently perform pallet and pocket detection, even when tested in the laboratory and with successive 3D pallet segmentation. When comparing the models, YOLOv8 achieved higher average metric values, with YOLOv8m providing better detection performance in the laboratory setting.

Abstract
Numerous pose estimation methodologies demonstrate a decrement in accuracy or efficiency metrics when subjected to highly cluttered scenarios. Currently, companies expect high-efficiency robotic systems to close the gap between humans and machines, especially in logistic operations, which is highlighted by the requirement to execute operations, such as navigation, perception and picking. To mitigate this issue, the majority of strategies augment the quantity of detected and matched features. However, in this paper, it is proposed a system which adopts an inverse strategy, for instance, it reduces the types of features detected to enhance efficiency. Upon detecting 2D polygons, this solution perceives objects, identifies their corners and edges, and establishes a relationship between the features extracted from the perceived object and the known object model. Subsequently, this relationship is used to devise a weighting system capable of predicting an optimal final pose estimation. Moreover, it has been demonstrated that this solution applies to different objects in real scenarios, such as intralogistic, and industrial, provided there is prior knowledge of the object's shape and measurements. Lastly, the proposed method was evaluated and found to achieve an average overlap rate of 89.77% and an average process time of 0.0398 seconds per object pose estimation.