Unidade de Investigação - INESCC-DL – Instituto de Engenharia de Sistemas e Computadores de Coimbra [delegação Politécnico de Leiria]
URI permanente desta comunidade:
Navegar
Percorrer Unidade de Investigação - INESCC-DL – Instituto de Engenharia de Sistemas e Computadores de Coimbra [delegação Politécnico de Leiria] por Objetivos de Desenvolvimento Sustentável (ODS) "08:Trabalho Digno e Crescimento Económico"
A mostrar 1 - 7 de 7
Resultados por página
Opções de ordenação
- Industrial Robot Trajectory Generation and Execution for 3D Printing using an ABB IRB 1200Publication . Cavalcanti, Marcella; Costelha, Hugo; Neves, CarlosThe use of industrial robots in additive manufacturing processes has become increasingly important, offering more flexibility and the capability of multi-directional printing. This integration facilitates the production of more complex geometries, free from the limitations of small build volumes and support structures, opening new possibilities for innovation in advanced manufacturing systems. As the complexity of the printed structures grows, optimizing robot trajectories is essential to ensure high-quality results. This work presents a comparative analysis of robot trajectory generation and execution using ABB's 3D Printing Power Pack and generated RAPID coding in both simulated and real environments. The objective is to assess the use of the Power Pack in term of trajectory accuracy and efficiency, as well as how the simulated results compare with the real ones, considering the use-case of 3D printing. To support this analysis, a "test pattern" was designed to account for different trajectories, consisting of a single line extrusion path featuring long linear segments, corners, and curved sections. The path was converted into both G-code and RAPID code. The G-code was first validated on a standard 3D printer and then used as input in the 3D Printing Power Pack application to generate a RAPID program for the robot. Separately, another RAPID program was created manually to execute the same path, based on the G-code. Both programs were executed on a simulated environment in RobotStudio, and on an ABB IRB 1200 robot. Throughout the tests, the robot’s Tool Center Point (TCP) position was captured using ABB’s Externally Guided Motion (EGM) application.
- Predicting Order Activity Sequence Using Contextual Process MiningPublication . Barbeiro, Diogo A.; Martinho, Ricardo F. G.; Ferreira, Carlos J. R.Logistics processes depend heavily on changing conditions and making accurate forecasts is becoming more and more important to preventing delays and/or predict risks. Predictive Process Monitoring has advanced through deep learning and process-mining approaches, yet current methods often lack interpretability and lose accuracy when context varies. Recent research shows that contextual factors can improve predictions, but their integration into transparent, model-driven frameworks remains limited. This article presents a context-aware predictive approach that filters historical event logs by important attributes, discovers process models with the Inductive Miner, and predicts future activities and timestamps using token-based replay and polynomial regression. Experiments with real logistics data show that incorporating context reduces prediction errors, while the use of process mining ensures an interpretable and operationally practical forecasting solution for logistics environments.
- A review on Robot-Assisted Additive Manufacturing Systems and TechnologiesPublication . Cavalcanti, M.; Costelha, Hugo; Neves, CarlosAbstract. The general use of robot manipulators in the Additive Manufacturing (AM) world could cause a paradigm shift on how these technologies are used today. Adding more degrees of freedom to the AM systems decreases the limita tions of current mainstream additive technologies, such as restricted build volume, high manufacturing times, and the use of support structures. However, existing traditional techniques for slicing 3D models and path planning generation do not translate smoothly into the requirements and constraints of robot manipulator systems. This paper presents a state-of-the-art review on the current systems and technologies, as well as advantages and challenges on the use of robot manipulators in AM, focusing on extrusion-based processes.
- Robotic Path Planning Algorithms for Additive Manufacturing Using Advanced Simulation ToolsPublication . Ferreira, Marco; Costelha, Hugo; Conde Bento, Luis; Neves, CarlosRobotics-based additive manufacturing (AM), or 3D printing, enables flexible printing systems. This paper analyses path planning algorithms for robotic manipulators aiming at dynamic AM environments. Using the cuRobo library, the study evaluates the path planning algorithm MotionGen and Model Predictive Control (MPC) using NVIDIA’s Isaac Sim with ROS2 and MoveIt2. Docker provided a modular development environment, and an Intel RealSense camera was used to enable real-world and real-time obstacle detection. Results show that MotionGen outperforms MPC in energy consumption and time efficiency, generating smoother and more efficient trajectories, more suitable for real-time AM contexts. The project shows the potential of advanced robotic control algorithms to optimize AM, using NVIDIA’s Isaac platform. Future work will focus on applying this to real robots.
- A simple heuristic for the identification of the case ID attribute in unlabelled process mining event logsPublication . Vicente, André; Grilo, Carlos; Rijo, Rui; Martinho, RicardoThis study addresses the critical challenge of identifying and labelling the case ID attribute in unlabelled event logs, a fundamental task in process mining. Case IDs uniquely associate events with individual process instances, enabling accurate analysis and discovery of operational insights. Manual identification of case IDs is error-prone and labour-intensive, often hindering the scalability and reliability of process mining analyses. This paper introduces a novel heuristic method that automates case ID identification, improving efficiency and accuracy for diverse real-world datasets. The proposed heuristic leverages unique temporal patterns observed in event logs to distinguish case ID attributes from other attributes. It calculates a weighted average of temporal spans and applies customisable parameters to prioritise relevant attributes. The method was validated using 27 datasets from the Business Process Intelligence (BPI) Challenge, representing a variety of industries and event log complexities. Performance metrics, including success rates and computational efficiency, were benchmarked against existing approaches. The heuristic achieved an 85.2% top-1 success rate, and remains effective provided at least one repeating categorical attribute is present - a condition met by virtually all publicly available business and industrial logs. It consistently ranked case IDs among the top attributes even in challenging scenarios, such as cyclic processes and multi-correlated data. The method demonstrated robustness across diverse datasets, processing large event logs within seconds, highlighting its practicality for real-world applications. This research contributes an innovative and explainable approach to case ID identification that requires only raw event logs, contrasting with existing methods reliant on pre-labelled data or complex pipelines. Its simplicity, efficiency, and adaptability to various process types make it a valuable tool for advancing process mining capabilities.
- Smart Remote Control Design for SeniorsPublication . Pereira, António; Silva, Fernando; Ribeiro, José; Marcelino, Isabel; Barroso, JoãoTechnology is present in almost all aspects of our modern lives, and technological advances have been more and more prevalent. One would expect this to facilitate everybody’s life, rendering common tasks more practical and easier to perform, but that is often not the case - at least not for the elderly. Older people have significant difficulties in using technological equipment due to the visual, physical, cognitive and hearing limitations associated with the natural aging process; these aspects must be taken into account if the intention is that of integrating technology in the lives of the elderly. In order to improve the quality of life of the elderly, as well as to prevent their social isolation, a mobile device application was developed to act as an intelligent remote control. This mobile application deals with data from two different platforms that were previously developed for improving the quality of life of the senior population: HbbTV and +Social. The features built into this virtual remote control include the integration with the +Social platform, as well as a speech recognition mechanism, and the possibility of making and receiving video calls with an integrated contacts list. A comprehensive study was carried out, focusing on recommendations and rules for graphical interfaces for the elderly, so as to allow equipping the application with adequate usability standards. The most relevant result was the definition of a list of guidelines used to steer the development of the interface. An investigation of mechanisms and technologies for enabling the implementation of the required functionalities was also carried out in order to define methodologies for freeing the user from the need of possessing any level of computer literacy. A series of usability tests was also performed to validate the viability of the remote control application. These tests allowed assessing the quality of the application, especially concerning the Graphical User Interface, as well as to receive feedback from potential end users. Based on the data collected during the test phase we conclude that this product is useful and that it responds to a current need.
- VE4OCPM: An Object-Centric Process Mining Variant Explorer Visualisation ApproachPublication . Gaspar, Marco A. P.; Martinho, Ricardo F. G.; Ferreira, Carlos J. R.This work presents the Variant Explorer, a dual-mode visualisation for Object-Centric Process Mining that reveals control-flow variability and object interactions across process variants, combining object details and subway-map views for intuitive analysis of complex processes. Understanding process variants is essential to detect deviations, exceptions, and improvement opportunities. However, traditional process mining tools assume one case per process instance, which do not work well when events involve multiple objects, such as orders, products, and packages. Existing Object-Centric approaches, like OCπ and Object-Centric Process Analysis (OCPA), introduced models and libraries to support multi-object analysis, but many face technical and usability limitations. To address this gap, this proposal provides two complementary visualisations that show object participation and variant differences side-by-side. Evaluation with real logistics data and user interpretation tests shows that users are able to identify repetitions, skipped activities, deviations, and object interactions clearly. This work offers a practical and interpretable solution for variant analysis in Object-Centric Process Mining (OCPM) and supports better understanding for analysts and business stakeholders.