Revistas
Autores:
López-de Ipina, K. (Autor de correspondencia); Iradi, J.; Fernández, E.; et al.
Revista:
SENSORS
ISSN:
1424-8220
Año:
2023
Vol.:
23
N°:
3
Págs.:
1170
The workplace is evolving towards scenarios where humans are acquiring a more active and dynamic role alongside increasingly intelligent machines. Moreover, the active population is ageing and consequently emerging risks could appear due to health disorders of workers, which requires intelligent intervention both for production management and workers' support. In this sense, the innovative and smart systems oriented towards monitoring and regulating workers' well-being will become essential. This work presents HUMANISE, a novel proposal of an intelligent system for risk management, oriented to workers suffering from disease conditions. The developed support system is based on Computer Vision, Machine Learning and Intelligent Agents. Results: The system was applied to a two-arm Cobot scenario during a Learning from Demonstration task for collaborative parts transportation, where risk management is critical. In this environment with a worker suffering from a mental disorder, safety is successfully controlled by means of human/robot coordination, and risk levels are managed through the integration of human/robot behaviour models and worker's models based on the workplace model of the World Health Organization. The results show a promising real-time support tool to coordinate and monitoring these scenarios by integrating workers' health information towards a successful risk management strategy for safe industrial Cobot environments.
Autores:
Chunab-Rodriguez, M. A.; Santana-Diaz, A.; Rodriguez-Arce, J. (Autor de correspondencia); et al.
Revista:
APPLIED SCIENCES
ISSN:
2076-3417
Año:
2022
Vol.:
12
N°:
14
Págs.:
7277
In recent years, engineering degree programs have become fundamental to the teaching of robotics and incorporate many fundamental STEM concepts. Some authors have proposed different platforms for teaching different topics related to robotics, but most of these platforms are not practical for classroom use. In the case of teaching autonomous navigation algorithms, the absence of platforms in classrooms limits learning because students are unable to perform practice activities or cannot evaluate and compare different navigation algorithms. The main contribution of this study is the implementation of a free platform for teaching autonomous-driving algorithms based on the Robot Operating System without the use of a physical robot. The authors present a case study using this platform as a teaching tool for instruction in two undergraduate robotic courses. Students evaluated the platform quantitatively and qualitatively. Our study demonstrates that professors and students can carry out different tests and compare different navigation algorithms to analyze their performance under the same conditions in class. In addition, the proposed platform provides realistic representations of environments and data visualizations. The results claim that the use of simulations helps students better understand the theoretical concepts, motivates them to pay attention, and increases their confidence.
Revista:
INTERNATIONAL JOURNAL OF SOCIAL ROBOTICS
ISSN:
1875-4791
Año:
2021
Vol.:
13
N°:
6
Págs.:
1473 - 1484
The growing introduction of robotics in non-industrial applications where the environment is unstructured and changing, has led to the need of development of safer and more intuitive, human-robot interfaces. In such environments, the use of collaborative robots has potential benefits, due to the combination of user experience, knowledge and flexibility with the robot's accuracy, stiffness and repeatability. Nevertheless, in order to guarantee a functional collaboration in these environments, the interaction between user and robot must be intuitive, natural, fast and easy to use. On one hand, commercial collaborative robots are less accurate and less stiff than the traditional industrial ones, on the other hand, the later have not intuitive interaction interfaces. There are tasks in which the stiffness of industrial robots and the intuitive interaction interfaces of collaborative commercial robots, are desirable. This is the case of some robotic assisted surgical procedures, such as robotic assisted spine surgery, with high accuracy demands and with the need of intuitive surgeon-robot interaction. This paper presents a hand guiding methodology for functional human-robot collaboration and the introduction of novel algorithms to enhance its behavior. Also its implementation on a robotic surgical assistant for spine procedures is presented. It is emphasized how a traditional industrial robot can be used as a collaborative one when the available commercial collaborative robots do not have the required accuracy and stiffness for the task.
Autores:
Rodriguez, J. (Autor de correspondencia); Gutierrez, T.; Portillo, O.; et al.
Revista:
INTERNATIONAL JOURNAL OF HUMAN-COMPUTER STUDIES
ISSN:
1071-5819
Año:
2018
Vol.:
110
Págs.:
86 - 94
Previous studies on learning force patterns (fine motor skills) have focused on providing "punctual information", which means users only receive information about their performance at the Current time step. This work proposes a new approach based on "contextual information", in which users receive information not only about the current time step, but also about the past (how the target force has changed over time) and the future (how the target force will change). A test was run to compare the performance of the contextual approach in relation to the punctual information, in which each participant had to memorize and then reproduce a pattern of force after training with a multimodal system. The findings suggest that the contextual approach is a useful strategy for force pattern learning. The advantage of the contextual information approach over the punctual information approach is that users receive information about the evolution of their performance (helping to correct the errors), and they also receive information about the next forces to be exerted (providing them with a better understanding of the target force profile). Finally, the contextual approach could be implemented in medical training platforms or surgical robots to extend the capabilities of these systems.
Autores:
Leizea, I.; Mendizabal, A.; Alvarez, H.; et al.
Revista:
IEEE COMPUTER GRAPHICS AND APPLICATIONS
ISSN:
0272-1716
Año:
2017
Vol.:
37
N°:
1
Págs.:
56 - 68
One of the most challenging problems in robot-assisted surgical systems is to provide surgical realism at interactive simulation rates. The proposed visual tracking system can track and register object deformations in real time using a physically based formulation, despite the occlusions produced by the robotic system itself. The results obtained provide an accurate visual representation of the deformed solid and will thus enable new assistance approaches to help surgeons during surgical procedures.
Revista:
JOURNAL OF THE MECHANICAL BEHAVIOR OF BIOMEDICAL MATERIALS
ISSN:
1751-6161
Año:
2015
Vol.:
45
N°:
5
Págs.:
1 - 10
Interactive surgical simulators capable of providing a realistic visual and haptic feedback to users are a promising technology for medical training and surgery planification. However, modelling the physical behaviour of human organs and tissues for surgery simulation remains a challenge. On the one hand, this is due to the difficulty to characterise the physical properties of biological soft tissues. On the other hand, the challenge still remains in the computation time requirements of real-time simulation required in interactive systems. Real-time surgical simulation and medical training must employ a sufficiently accurate and simple model of soft tissues in order to provide a realistic haptic and visual response. This study attempts to characterise the brain tissue at similar conditions to those that take place on surgical procedures. With this aim, porcine brain tissue is characterised, as a surrogate of human brain, on a rotational rheometer at low strain rates and large strains. In order to model the brain tissue with an adequate level of accuracy and simplicity, linear elastic, hyperelastic and quasi-linear viscoelastic models are defined. These models are simulated using the ABAQUS finite element platform and compared with the obtained experimental data. (C) 2015 Elsevier Ltd. All rights reserved.
Revista:
REVISTA IBEROAMERICANA DE AUTOMATICA E INFORMATICA INDUSTRIAL
ISSN:
1697-7912
Año:
2015
Vol.:
12
N°:
1
Págs.:
80 - 91
In this research work, a new prototype of collaborative robot-assisted surgical platform for transpedicular fixation surgeries is presented. The usage of assistive robotic systems during conventional surgical procedures improves surgical outcomes, as they ensure high levels of precision and safety. Hence, robustness and dexterity of the mechatronic devices must be guaranteed, even in the neighborhood of unstable configurations during their performance. Bearing this in mind, a singularity management strategy has been implemented in the robotic platform, based on the Damped Least Squares method using an adaptive damping factor together with a methodology for optimization of joint redundancy of the platform manipulator, Mitsubishi PA10-7C.
Autores:
Nirit, Y.; Rodriguez, J.; Gutierrez, T.; et al.
Revista:
JOURNAL OF INTERACTIVE LEARNING RESEARCH
ISSN:
1093-023X
Año:
2014
Vol.:
25
N°:
4
Págs.:
487 - 507
The current study hypothesized that integrating partly observational learning into virtual reality training systems (VRTS) can enhance training efficiency for procedural tasks. A common approach in designing VRTS is the enactive approach, which stresses the importance of physical actions within the environment to enhance perception and improve learning. However, based on embodied cognition theory, we hypothesized that for procedural tasks observational learning can successfully replace a portion of the active training using VRTS, reducing training time without sacrificing performance. The hypothesis was tested using a virtual reality system to train a 75-step Lego assembly task. Two conditions were compared: Active, in which the trainee had to both identify each correct brick and place it correctly in the Lego model; and Partly Observational Learning, in which the trainee was required only to select the correct brick, and then observed how the system automatically positioned it. Results demonstrated that training time was reduced with the incorporation of an observational learning phase, while performance time with the real Lego test as well as the number of final errors and the number of corrected errors were similar for both conditions. In conclusion, partly observational learning can enhance training efficiency for some procedural tasks without necessarily sacrificing performance if integrated properly within virtual reality training.
Revista:
IEEE-ASME TRANSACTIONS ON MECHATRONICS
ISSN:
1083-4435
Año:
2012
Vol.:
17
N°:
1
Págs.:
174 - 182
This paper investigates the effect of user grasping position on the performance of haptic rendering. Two dynamic models, with seven and eleven parameters, respectively, have been used to characterize the PHANToM haptic interface and the user. The parameter variability analysis shows that user grasping position significantly affects system dynamics. This variation also influences the phase margin of the system, leading to different damping factors in response to contacts with rigid virtual objects. To compensate this effect, an adaptive haptic rendering has been developed and successfully implemented, imposing a similar damping factor in the transient responses for all grip positions.
Autores:
Melo-Uribe, J.; Bertelsen-Simonetti, A.; Borro, D.; et al.
Revista:
DYNA
ISSN:
0012-7361
Año:
2012
Vol.:
87
N°:
6
Págs.:
647 - 654
This work presents the control system strategy implemented in a new cooperative human-robot system for transpedicular fixation, a type of spine surgery consisting in the immobilization of two or more vertebrae by means of screws and metal bars. The prototype uses a PA-10 robotic arm. The main parts of the control strategy are the admittance module and the generation of virtual fixtures (active constraints) that assist the surgeon and prevent contact with surrounding critical areas. The virtual fixtures are obtained directly from the surgical planner with the purpose of increasing the precision in screw insertion and having safer interventions, reducing radiation doses, invasiveness and the probability of error. Differing from other surgery robotic assistants, the one proposed in this work oilers a larger workspace and a degree of versatility that permits its adaptation to different types of surgeries.
Revista:
JOURNAL OF ROBOTICS
ISSN:
1687-9600
Año:
2011
Vol.:
2011
N°:
Article ID 759764
This paper presents a survey of existing robotic systems for lower-limb rehabilitation. It is a general assumption that robotics will play an important role in therapy activities within rehabilitation treatment. In the last decade, the interest in the field has grown exponentially mainly due to the initial success of the early systems and the growing demand caused by increasing numbers of stroke patients and their associate rehabilitation costs. As a result, robot therapy systems have been developed worldwide for training of both the upper and lower extremities. This work reviews all current robotic systems to date for lower-limb rehabilitation, as well as main clinical tests performed with them, with the aim of showing a clear starting point in the field. It also remarks some challenges that current systems still have to meet in order to obtain a broad clinical and market acceptance.
Revista:
DYNA
ISSN:
0012-7361
Año:
2010
Vol.:
85
N°:
3
Págs.:
237 - 244
Los interfaces hápticos son dispositivos robóticos que permiten tocar la realidad virtual. A diferencia de la robótica industrial tradicional, en la que los robots se encuentran confinados en células haciendo trabajos repetitivos, las interfaces hápticas están diseñadas para que el usuario los sujete con la mano.Por ello, también se les puede considerar como un interfaz de ordenador, que no sólo permite mover el cursor en un espacio virtual 3D, si no que también si el cursor `colisiona¿ algún objeto virtual, el usuario lo percibirá como si lo estuviera tocando. Las aplicaciones más habituales de los hápticos se encuentran en los videojuegos, herramientas de diseño CAD y simuladores (ej. conducción de vehículos, ensamblaje de máquinas, planificadores de cirugía, etc), donde el objetivo que se persigue es lograr una mayor sensación de inmersión. De esta forma el objetivo de este trabajo es presentar la tarjeta de control EOS V.2.0, aportando así, una solución de bajo coste para el control de sistemas hápticos. Utilizando tecnología FPGA (del inglés, Field Programmable Gate Array o Matriz Programable de Puertas Lógicas) se ha desarrollado con la tarjeta EOS, un sistema reconfigurable que permite controlar dispositivos hápticos de hasta 6 grados de libertad (GdL).Para comprobar el correcto funcionamiento de la misma, se presenta una sencilla aplicación en la que se utiliza la tarjeta EOS para controlar el dispositivo háptico LHIfAM de 6 GdL.