Search

[Resumen] Este artículo aborda la identificación de parámetros borrosos mediante técnicas de optimización de enjambre de partículas (PSO) y su aplicación al control de un sistema de suspensión activa. En particular, se adopta un controlador de tipo Takagi-Sugeno de orden cero con Partición Difusa Estándar de sus antecedentes. A diferencia de trabajos previos, donde el aprendizaje se limitaba a los parámetros de escala del control, el método propuesto permite la optimización de los conjuntos borrosos de los antecedentes. La metodología propuesta se ha experimentado con éxito sobre un sistema físico de un cuarto de vehículo. Este trabajo ha sido financiado parcialmente por los proyectos CICYT DPI 2011-22443 and DPI2015-65186-R https://doi.org/10.17979/spudc.9788497498081

Improvements in telecommunications and digitalization directly improve the efficacy of a wide variety of processes. Recently, detection systems have received considerable attention because of the importance of tracking infected people contacts during SARS-CoV-2 pandemic. Such implementations can be useful in the task of finding potential victims in the context of emergency response, especially in situations where GPS is not available or inspection by imaging is not practical. Radio signals come into play, and specifically from devices that transmit periodically and with low power consumption. With the rise of Internet of Things over the last years, the number of wearable devices that support BLE, such as smartbands, smartwatches or smartphones, has been increasing constantly, as well as the number of users that carry them. Those devices can provide considerable assistance in locating injured or unconscious people. This work presents a system for detecting victims by means of a terrestrial search and rescue (SAR) robot. A real implementation of a close detection robotic platform based on BLE for SAR interventions is laid out. To estimate the distance between a robotic agent and potential victims within an experimental area, a Log-distance path loss model is presented. The proposed scheme has been tested in realistic scenarios during SAR exercises. This work was partially funded by the Spanish project RTI2018-093421-B-I00. It has been also performed in the framework of the Horizon 2020 project LOCUS (ICT-871249) receiving funds from the European Union. This work has been also partially funded by Junta de Andalucía and ERDF projects: Consejería de Transformación Económica, Industria, Conocimiento y Universidades, Proyecto de Excelencia PENTA, P18-FR-4647; postdoctoral grant (Ref., DOC 01154, “selección de personal investigador doctor convocado mediante Resolución de 21 de mayo de 2020”, PAIDI 2020) and the I Plan Propio de Investigación, Transferencia y Divulgación Científica of the University of Málaga. The authors want to thank the collaboration of the Chair for Safety, Emergencies and Disasters of the University of Malaga, led by Prof. Jesús Miranda, as well as Javier Serón Barba for his support during the experiments. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

This paper describes a cooperative search and rescue exercise where an unmanned ground vehicle (UGV) is used by a military rescue team for extraction and evacuation of a casualty from an unsafe man-made disaster area. This experimental validation was performed within a full-scale emergency response exercise organized on June 2019 by the Chair of Safety, Emergencies and Disasters at Universidad de Málaga (Spain). With this purpose, we adapted the skid-steer Rambler robot to carry a stretcher with appropriate roll-in and locking mechanisms. The mission consisted of two phases: first, extraction from the hot zone was performed with remote teleoperation using a dummy; second, casualty evacuation (CASEVAC) to an aeromedical evacuation point was done with sightline teleoperation moving an actual volunteer. The realistic one-shot exercise was performed by actual rescue personnel with no previous experience with the robotic system. The paper shares insight and lessons learned from this concept validation experience. This work was partially supported by the project ``TRUST-ROB: Towards Resilient UGV and UAV Manipulator Teams for Robotic Search and Rescue Tasks'', funded by the Spanish Government (RTI2018-093421-B-I00). Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

Autonomy on rovers is desirable in order to extend the traversed distance, and therefore, maximize the number of places visited during the mission. It depends heavily on the information that is available for the traversed surface on other planet. This information may come from the vehicle’s sensors as well as from orbital images. Besides, future exploration missions may consider the use of reconfigurable rovers, which are able to execute multiple locomotion modes to better adapt to different terrains. With these considerations, a path planning algorithm based on the Fast Marching Method is proposed. Environment information coming from different sources is used on a grid formed by two layers. First, the Global Layer with a low resolution, but high extension is used to compute the overall path connecting the rover and the desired goal, using a cost function that takes advantage of the rover locomotion modes. Second, the Local Layer with higher resolution but limited distance is used where the path is dynamically repaired because of obstacle presence. Finally, we show simulation and field test results based on several reconfigurable and non-reconfigurable rover prototypes and a experimental terrain.

Search and rescue operations in the context of emergency response to human or natural disasters have the major goal of finding potential victims in the shortest possible time. Multi-agent teams, which can include specialized human respondents, robots and canine units, complement the strengths and weaknesses of each agent, like all-terrain mobility or capability to locate human beings. However, efficient coordination of heterogeneous agents requires specific means to locate the agents, and to provide them with the information they require to complete their mission. The major contribution of this work is an application of Wireless Sensor Networks (WSN) to gather information from a multi-agent team and to make it available to the rest of the agents while keeping coverage. In particular, a canine agent has been equipped with a mobile node installed on a harness, providing information about the dog’s location as well as gas levels. The configuration of the mobile node allows for flexible arrangement of the system, being able to integrate static as well as mobile nodes. The gathered information is available at an external database, so that the rest of the agents and the control center can use it in real time. The proposed scheme has been tested in realistic scenarios during search and rescue exercises.

Las implementaciones existentes en la actualidad sobre sensores virtuales no emplean un marco comun matematicamente riguroso. Por ello, en este trabajo tenemos como objetivo homogeneizar el soporte teorico de los sensores virtuales a bajo nivel, es decir, tratando directamente sus datos en bruto, de tal modo que puedan ser empleados en diagnostico de fallos, recuperacion de datos y otras funcionalidades sin cambiar el paradigma de base. La inferencia bayesiana constituye una manera gen ́erica y rigurosa de abordar este problema; ademas, nos permite integrar conocimiento procedente de diversas fuentes (los propios dispositivos sensoriales, sentido comun humano, datos del entorno, etc.) y se puede hibridar con otras metodolog ́ıas como las redes neuronales o la logica borrosa. Dado que el potencial de esta solucion es considerablemente amplio, nos centramos aqu ́ı en el diagnostico de aver ́ıas, recuperacion de datos y funcionalidades de integracion de conocimiento externo. Nuestros resultados con un robot movil real equipado con dos sensores de proximidad y con otros dispositivos mas simples, demuestran que este marco tiene muchas posibilidades de mejorar el sistema sensorial de un robot por medio de t ́ecnicas de razonamiento de alto nivel. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

A new robotic system for Search And Rescue (SAR) operations based on the automatic wristband placement on the victims’ arm, which may provide identification, beaconing and remote sensor readings for continuous health monitoring. This paper focuses on the development of the automatic target localization and the device placement using an unmanned aerial manipulator. The automatic wrist detection and localization system uses an RGB-D camera and a convolutional neural network based on the region faster method (Faster R-CNN). A lightweight parallel delta manipulator with a large workspace has been built, and a new design of a wristband in the form of a passive detachable gripper, is presented, which under contact, automatically attaches to the human, while disengages from the manipulator. A new trajectory planning method has been used to minimize the torques caused by the external forces during contact, which cause attitude perturbations. Experiments have been done to evaluate the machine learning method for detection and location, and for the assessment of the performance of the trajectory planning method. The results show how the VGG-16 neural network provides a detection accuracy of 67.99%. Moreover, simulation experiments have been done to show that the new trajectories minimize the perturbations to the aerial platform. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.

International Workshop on Robotac: New Progress in Tactile Perception and Learning in Robotics Novel tactile sensors allow treating pressure lectures as standard images due to its highresolution. Therefore, computer vision algorithms such as Convolutional Neural Networks (CNNs) can be used to identify objects in contact. In this work, a high-resolution tactile sensor has been attached to a robotic end-effector to identify objects in contact. Moreover, two CNNs-based approaches have been tested in an experiment of classification of pressure images. These methods include a transfer learning approach using a pre-trained CNN on an RGB images dataset and a custom-made CNN trained from scratch with tactile information. A comparative study of performance between them has been carried out. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. Spanish project DPI2015-65186-R, the European Commission under grant agreement BES-2016-078237, the educational project PIE-118 of the University of Malaga

This paper 1 describes the use of two artificial intelligence methods for object recognition via pressure images from a high-resolution tactile sensor. Both meth- ods follow the same procedure of feature extraction and posterior classification based on a supervised Supported Vector Machine (SVM). The two approaches differ on how features are extracted: while the first one uses the Speeded-Up Robust Features (SURF) descriptor, the other one employs a pre-trained Deep Convolutional Neural Network (DCNN). Besides, this work shows its applica- tion to object recognition for rescue robotics, by distinguishing between differ- ent body parts and inert objects. The performance analysis of the proposed methods is carried out with an experiment with 5-class non-human and 3-class human classification, providing a comparison in terms of accuracy and compu-tational load. Finally, it is discussed how feature-extraction based on SURF can be obtained up to five times faster compared to DCNN. On the other hand, the accuracy achieved using DCNN-based feature extraction can be 11.67% superior to SURF. Proyecto DPI2015-65186-R European Commission under grant agreement BES-2016-078237. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.