http://hdl.handle.net/10256/16667 2025-08-13T09:16:16Z http://hdl.handle.net/10256/17768 A novel approach to obstacle avoidance for an I-AUV: Preliminary Simulation Results Simoni, Roberto; Ridao Rodríguez, Pere; Cieśląk, Patryk; Youakim Isaac, Dina Nagui This paper presents a novel approach to obstacle avoidance approach for an I-AUV in a framework of setbased task-priority kinematic control algorithm. The approach is divided into two modes: Mode (1) navigation and inspection and Mode (2) intervention. For navigation we fully wrap the I-AUV with two safety spheres at the vehicle and one at the arm. For intervention we use more safety spheres with smaller sizes to fully wrap the I-AUV to allow more precise movements of the I-AUV near the intervention areas.The novel approach was implemented and simulated with the 8-DOF IAUV GIRONA500 in a scenario for inspection and maintenance (valve turning) of a BOP (blowout preventer) structure used in oil and gas industry. The BOP structure was represented by an octomap and each occupied cell of the octomap was considered as an obstacle in our model Comunicació de congrés presentada a: IROS 2018 Workshop (5 octubre 2018: Madrid): New Horizon For Underwater Intervention Missions: From Current Technologies to Future Applications. https://www.iros2018.org/workshops 2018-01-01T00:00:00Z http://hdl.handle.net/10256/17715 Tackling the Problem of Data Imbalancing for Melanoma Classification Rastgoo, Mojdeh; Lemaitre, Guillaume; Massich i Vall, Joan; Morel, Olivier; Marzani, Frank; García Campos, Rafael; Meriaudeau, Fabrice Malignant melanoma is the most dangerous type of skin cancer, yet melanoma is the most treatable kind of cancer when diagnosed at an early stage. In this regard, Computer-Aided Diagnosis systems based on machine learning have been developed to discern melanoma lesions from benign and dysplastic nevi in dermoscopic images. Similar to a large range of real world applications encountered in machine learning, melanoma classification faces the challenge of imbalanced data, where the percentage of melanoma cases in comparison with benign and dysplastic cases is far less. This article analyzes the impact of data balancing strategies at the training step. Subsequently, Over-Sampling (OS) and Under-Sampling (US) are extensively compared in both feature and data space, revealing that NearMiss-2 (NM2) outperform other methods achieving Sensitivity (SE) and Specificity (SP) of 91.2% and 81.7%, respectively. More generally, the reported results highlight that methods based on US or combination of OS and US in feature space outperform the others Comunicació de congrés presentada a: 3rd International Conference on Bioimaging, BIOIMAGING 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016, Roma, Italy 2016-02-21T00:00:00Z http://hdl.handle.net/10256/17712 ROSPlan: Planning in the Robot Operating System Cashmore, Michael; Fox, Maria; Long, Derek; Magazzeni, Daniele; Ridder, Bram; Carrera Viñas, Arnau; Palomeras Rovira, Narcís; Hurtós Vilarnau, Natàlia; Carreras Pérez, Marc The Robot Operating System (ROS) is a set of software libraries and tools used to build robotic systems. ROS is known for a distributed and modular design. Given a model of the environment, task planning is concerned with the assembly of actions into a structure that is predicted to achieve goals. This can be done in a way that minimises costs, such as time or energy. Task planning is vital in directing the actions of a robotic agent in domains where a causal chain could lock the agent into a dead-end state. Moreover, planning can be used in less constrained domains to provide more intelligent behaviour. This paper describes the ROSPLAN framework, an architecture for embedding task planning into ROS systems. We provide a description of the architecture and a case study in autonomous robotics. Our case study involves autonomous underwater vehicles in scenarios that demonstrate the flexibility and robustness of our approach Comunicació de congrés presentada a: International Conference on Automated Planning and Scheduling (25th: 7-11 Juny 2015: Jerusalen, Israel), Session 2b: Robotics II 2015-06-07T00:00:00Z http://hdl.handle.net/10256/17356 Learning by demonstration applied to underwater intervention Carrera Viñas, Arnau; Palomeras Rovira, Narcís; Hurtós Vilarnau, Natàlia; Kormushev, Petar; Carreras Pérez, Marc Performing subsea intervention tasks is a challenge due to the complexities of the underwater domain. We propose to use a learning by demonstraition algorithm to intuitively teach an intervention autonomous underwater vehicle (IAUV) how to perform a given task. Taking as an input few operator demonstrations, the algorithm generalizes the task into a model and simultaneously controls the vehicle and the manipulator (using 8 degrees of freedom) to reproduce the task. A complete framework has been implemented in order to integrate the LbD algorithm with the different onboard sensors and actuators. A valve turning intervention task is used to validate the full framework through real experiments conducted in a water tank Comunicació de congrés presentada a: 17th International Conference of the Catalan Association for Artificial Intelligence, Barcelona, Catalonia, Spain, October 22-24, 2014 2014-01-01T00:00:00Z