New low cost sensors and the new open free libraries for 3D image processing are permitting to achieve important advances for robot vision applications such as tridimensional object recognition, semantic mapping, navigation and localization of robots, human detection and/or gesture recognition for human-machine interaction. In this paper, a method to recognize the human hand and to track the fingers is proposed. This new method is based on point clouds from range images, RGBD. It does not require visual marks, camera calibration, environment knowledge and complex expensive acquisition systems. Furthermore, this method has been implemented to create a human interface in order to move a robot hand. The human hand is recognized and the movement of the fingers is analyzed. Afterwards, it is imitated from a Barret hand, using communication events programmed from ROS. ; This work was supported in part by the Valencia Regional Government and the Research and Innovation Vice-president Office of the University of Alicante for their financial support through the projects GV2012/102 and GRE10-16, respectively.
Current wearable robots mostly focus on applications in military, rehabilitation and load lifting in the health sector, while they are hardly used in industry and manufacturing. In this paper, a sensor and control concept for a wearable robot for assistance in manual handling of loads in industry is presented. Special requirements such as low costs, direct contact between the human and the load and easy set-up are addressed. A wall-mounted test stand of an actuated elbow joint was built up to evaluate the proposed sensors and control algorithms. By using a torque sensor in the elbow joint as reference it is shown that low cost force sensors in the forearm can be used to measure the human-robot interaction. A torque-based and a velocity-based impedance control approach are compared which allow the user to move freely while not handling any loads and which also allow to incorporate a human command signal for regulation of force support. The former is shown to be superior to the position-based approach. Further, the influence of the human impedance characteristics onto stability of the controllers is discussed.
This paper presents themeasurement of gas concentration and wind intensity performed with amobile robot in a customturbulent wind tunnel designed for experimentation with customizable wind and gas leak sources.This paper presents the representation in different information layers of the measurements obtained in the turbulent wind tunnel under different controlled environmental conditions in order to describe the plume of the gas and wind intensities inside the experimentation chamber.Theinformation layers have been generated from the measurements gathered by individual onboard gas and wind sensors carried out by an autonomous mobile robot. On the one hand, the assumption was that the size and cost of these specialized sensors do not allow the creation of a net of sensors or other measurement alternatives based on the simultaneous use of several sensors, and on the other hand, the assumption is that the information layers created will have application on the development and test of automatic gas source location procedures based on reactive or nonreactive algorithms. ; This work was partially funded by the Spanish Ministry of Economy and Competitiveness, Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica: TEC2011-26143 and TEC2014-59229-R and by the Government of Catalonia (Comissionat per a Universitats i Recerca, Departament d'Innovació, Universitats i Empresa) and the European Social Fund (ECO/1639/2013).
19th International Workshop of Physical Agents (WAF). Madrid (22-23 Noviembre 2018) ; ABSTRACT: This paper presents a personalized contingency feedback adaptation system that aims to encourage infants aged 6 to 8 months to gradually increase the peak acceleration of their leg movements. The ultimate challenge is to determine if a socially assistive humanoid robot can guide infant learning using contingent rewards, where the reward threshold is personalized for each infant using a reinforcement learning algorithm. The model learned from the data captured by wearable inertial sensors measuring infant leg movement accelerations in an earlier study. Each infant generated a unique model that determined the behavior of the robot. The presented results were obtained from the distributions of the participants' acceleration peaks and demonstrate that the resulting model is sensitive to the degree of differentiation among the participants; each participant (infant) should have his/her own learned policy. ; This work was supported by NSF award 1706964 (PI: Smith, Co-PI: Matarić). In addition, this work was developed during an international mobility program at the University of Southern California being also partially funded by the European Union ECHORD++ project (FP7-ICT-601116), the LifeBots project (TIN2015-65686-C5) and THERAPIST project (TIN2012-38079).
[EN] There are great physical and cognitive benefits for older adults who are engaged in active aging, a process that should involve daily exercise. In our previous work on the PHysical Assistant RObot System (PHAROS), we developed a system that proposed and monitored physical activities. The system used a social robot to analyse, by means of computer vision, the exercise a person was doing. Then, a recommender system analysed the exercise performed and indicated what exercise to perform next. However, the system needed certain improvements. On the one hand, the vision system captured the movement of the person and indicated whether the exercise had been done correctly or not. On the other hand, the recommender system was based purely on a ranking system that did not take into account temporal evolution and preferences. In this work, we propose an evolution of PHAROS, PHAROS 2.0, incorporating improvements in both of the previously mentioned aspects. In the motion capture aspect, we are now able to indicate the degree of completeness of each exercise, identifying the part that has not been done correctly, and a real-time performance correction. In this way, the recommender system receives a greater amount of information and so can more accurately indicate the exercise to be performed. In terms of the recommender system, an algorithm was developed to weigh the performance, temporal evolution and preferences, providing a more accurate recommendation, as well as expanding the recommendation to a batch of exercises, instead of just one. ; This work was partly supported by the FCT-Fundacao para a Ciencia e Tecnologia through the Post-Doc scholarship SFRH/BPD/102696/2014 and by the Spanish Government TIN2016-76515-R Grant supported with Feder funds. ; Martinez-Martin, E.; Araujo, A.; Cazorla, M. (2019). PHAROS 2.0-A PHysical Assistant RObot System Improved. Sensors. 19(20):1-18. https://doi.org/10.3390/s19204531 ; S ; 1 ; 18 ; 19 ; 20 ; World Alzheimer Report 2018—The State of the Art of Dementia Research: New ...
1 12 33 ; S ; This is the author's version of a work that was accepted for publication in Mechatronics. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Mechatronics, Vol. 33, (2016)] DOI 10.1016/j.mechatronics.2015.11.007. Several pneumatic grippers with accelerometers attached to their fingers have been developed and tested. The first gripper is able to classify the hardness of different cylinders, estimate the pneumatic pressure, monitor the position and speed of the gripper fingers, and study the phases of the action of grasping and the influence of the relative position between the gripper and the cylinders. The other grippers manipulate and assess the firmness of eggplants and mangoes. To achieve a gentle manipulation, the grippers employ fingers with several degrees of freedom in different configurations and have a membrane filled with a fluid that allows their hardness to be controlled by means of the jamming transition of the granular fluid inside it. To assess the firmness of eggplants and mangoes and avoid the influence of the relative position between product and gripper, the firmness is estimated while the products are being held by the fingers. Better performance of the accelerometers is achieved when the finger employs the granular fluid. The article presents methods for designing grippers capable of assessing the firmness of irregular products with accelerometers. At the same time, it also studies the possibilities that accelerometers, attached to different pneumatic robot gripper fingers, offer as tactile sensors. (C) 2015 Elsevier Ltd. All rights reserved. This research is supported by the MANI-DACSA project (Grant number RTA2012-00062-C04-02), which is partially funded by the Spanish Government (Ministerio de Economia y ...
This is the author's version of a work that was accepted for publication in Mechatronics. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Mechatronics, Vol. 33, (2016)] DOI 10.1016/j.mechatronics.2015.11.007. ; Several pneumatic grippers with accelerometers attached to their fingers have been developed and tested. The first gripper is able to classify the hardness of different cylinders, estimate the pneumatic pressure, monitor the position and speed of the gripper fingers, and study the phases of the action of grasping and the influence of the relative position between the gripper and the cylinders. The other grippers manipulate and assess the firmness of eggplants and mangoes. To achieve a gentle manipulation, the grippers employ fingers with several degrees of freedom in different configurations and have a membrane filled with a fluid that allows their hardness to be controlled by means of the jamming transition of the granular fluid inside it. To assess the firmness of eggplants and mangoes and avoid the influence of the relative position between product and gripper, the firmness is estimated while the products are being held by the fingers. Better performance of the accelerometers is achieved when the finger employs the granular fluid. The article presents methods for designing grippers capable of assessing the firmness of irregular products with accelerometers. At the same time, it also studies the possibilities that accelerometers, attached to different pneumatic robot gripper fingers, offer as tactile sensors. (C) 2015 Elsevier Ltd. All rights reserved. ; This research is supported by the MANI-DACSA project (Grant number RTA2012-00062-C04-02), which is partially funded by the Spanish Government (Ministerio de Economia y Competitividad.). ...
Worldwide demand for robotic aircraft such as unmanned aerial vehicles (UAVs) and micro aerial vehicles (MAVs) is surging. Not only military but especially civil applications are being developed at a rapid pace. Unmanned vehicles offer major advantages when used for aerial surveillance, reconnaissance, and inspection in complex and inhospitable environments. UAVs are better suited for dirty or dangerous missions than manned aircraft and are more cost-effective. UAVs can operate in contaminated environments, for example, and at altitudes both lower and higher than those typically traversed by manned aircraft. Many technological, economic, and political factors have encouraged the development and operation of UAVs. New sensors, microprocessors, and propulsion systems are smaller, lighter, and more capable, leading to levels of endurance, efficiency, and autonomy that exceed human capacities. Comprising the latest research, this book describes step by step the development of small or miniature unmanned aerial vehicles and discusses in detail the integrated prototypes developed at the robotics laboratory of Chiba University. With demonstration videos, the book will interest not only graduate students, scientists, and engineers but also newcomers to the field.
Abstract Although containment testing of fume cupboards (FC) according to the standards EN 14175-3 (2019) or ANSI/ASHRAE 110 (2016) is well established for type testing, its application is currently much less accepted and practised for evaluating containment on-site. Few of the several million FC in the market have been tested at installation and commissioning, and even less undergo verification of containment during their service life in the laboratories. Several reasons have led to this unsafe situation. To address this challenge, a new concept has been developed to allow for rapid on-site testing of FC to gain knowledge as to the functional efficiency as well as to safety aspects for the operator. The concept consists of a movable robot-aided test equipment that can be installed quickly to the FC in running labs. Multiple sensors detect the tracer gas isopropanol. Within a test run of only 10-min data is collected to quantify containment at the sash opening and to determine purge efficiency. The method reveals impact from interfering effects such as draughts, air distribution, and movements and from equipment installed, and is a tool for the optimization of operating conditions of a lab. This article presents an advanced alternative to the existing containment tests, particularly for on-site testing. The method assesses not only proper operation of the FC in its environment, but also the suitability of a FC for a given use under aspects of health and safety evaluation.
In this dissertation, we study multi-robot coordination in the context of multi-target tracking. Specifically, we are interested in the coordination achieved by means of submodular function optimization. Submodularity encodes the diminishing returns property that arises in multi-robot coordination. For example, the marginal gain of assigning an additional robot to track the same target diminishes as the number of robots assigned increases. The advantage of formulating coordination problems as submodular optimization is that a simple, greedy algorithm is guaranteed to give a good performance. However, often this comes at the expense of unrealistic models and assumptions. For example, the standard formulation does not take into account the fact that robots may fail, either randomly or due to adversarial attacks. When operating in uncertain conditions, we typically seek to optimize the expected performance. However, this does not give any flexibility for a user to seek conservative or aggressive behaviors from the team of robots. Furthermore, most coordination algorithms force robots to communicate at each time step, even though they may not need to. Our goal in this dissertation is to overcome these limitations by devising coordination algorithms that are parsimonious in communication, allow a user to manage the risk of the robot performance, and are resilient to worst-case robot failures and attacks. In the first part of this dissertation, we focus on designing parsimonious communication strategies for target tracking. Specifically, we investigate the problem of determining when to communicate and who to communicate with. When the robots use range sensors, the tracking performance is a function of the relative positions of the robots and the targets. We propose a self-triggered communication strategy in which a robot communicates its own position with its neighbors only when a certain set of conditions are violated. We prove that this strategy converges to the optimal robot positions for tracking a single target and in practice, reduces the number of communication messages by 30%. When tracking multiple targets, we can reduce the communication by forming subsets of robots and assigning one subset to track a target. We investigate a number of measures for tracking quality based on the observability matrix and show which ones are submodular and which ones are not. For non-submodular measures, we show a greedy algorithm gives a 1/(n+1) approximation, if we restrict the subset to n robots. In optimizing submodular functions, a common assumption is that the function value is deterministic, which may not hold in practice. For example, the sensor performance may depend on environmental conditions which are not known exactly. In the second part of the dissertation, we design an algorithm for stochastic submodular optimization. The standard formulation for stochastic optimization optimizes the expected performance. However, the expectation is a risk-neutral measure. Instead, we optimize the Conditional Value-at-Risk (CVaR), which allows the user the flexibility of choosing a risk level. We present an algorithm, based on the greedy algorithm, and prove that its performance has bounded suboptimality and improves with running time. We also present an online version of the algorithm to adapt to real-time scenarios. In the third part of this dissertation, we focus on scenarios where a set of robots may fail naturally or due to adversarial attacks. Our objective is to track as many targets as possible, a submodular measure, assuming worst-case robot failures. We present both centralized and distributed resilient tracking algorithms to cope with centralized and distributed communication settings. We prove these algorithms give a constant-factor approximation of the optimal in polynomial running time. ; Doctor of Philosophy ; Today, robotics and autonomous systems have been increasingly used in various areas such as manufacturing, military, agriculture, medical sciences, and environmental monitoring. However, most of these systems are fragile and vulnerable to adversarial attacks and uncertain environmental conditions. In most cases, even if a part of the system fails, the entire system performance can be significantly undermined. As robots start to coexist with humans, we need algorithms that can be trusted under real-world, not just ideal conditions. Thus, this dissertation focuses on enabling security, trustworthiness, and long-term autonomy in robotics and autonomous systems. In particular, we devise coordination algorithms that are resilient to attacks, trustworthy in the face of the uncertain conditions, and allow the long-term operation of multi-robot systems. We evaluate our algorithms through extensive simulations and proof-of-concept experiments. Generally speaking, multi-robot systems form the "physical" layer of Cyber-Physical Sytems (CPS), the Internet of Things (IoT), and Smart City. Thus, our research can find applications in the areas of connected and autonomous vehicles, intelligent transportation, communications and sensor networks, and environmental monitoring in smart cities.
Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Faculdade de Ciências e Tecnologia ; Nas últimas décadas as investigações em veículos autónomos têm vindo a crescer e a envolver cada vez mais gente devido aos seus vastos potenciais. Todos os anos aparecerem cada vez mais robots móveis e dispositivos eletrónicos na nossa vida diária.As melhorias feitas no poder de processamento e na redução dos microcontroladores, permitiu que o campo da robótica móvel tenha aumentado tremendamente. Os veículos autónomos têm uma enorme importância na área dos robots de campo, visto que eles podem executar tarefas enfadonhas e perigosas para os seres humanos, com tempos de resposta mais rápidos, ou em situações sem acesso humano. Os robots de campo podem ser usados ¿¿em experiências cientificas utilizando barcos autónomos para patrulhar os rios, recolher parâmetros das águas e realizar estudos de batimetria. Em operações militares usando drones autónomos para realizar mapeamento e vigilância de áreas críticas. Ou em situações de sentido oposto, como por exemplo com o objetivo de limpar regiões pós-combate de minas terrestres sem a intervenção humana. Em projetos de exploração planetária como a missão "Mars Exploration Rovers", que usa robots autónomos para pousar, explorar, e estudar a geologia da superfície marciana. E claro, a competição mais recente que todos os fabricantes do ramo das tecnologias e dos veículos automóveis quer ganhar, a criação de um automóvel que consiga conduzir de forma completamente autónoma.Quando estes robôs são utilizados no exterior eles sofrem da imprevisibilidade de tudo o que os rodeia. Objetos que estavam parado a um momento atrás, pode começar a mover-se e tornarem-se obstáculos. Às vezes, estes objetos têm contornos diferentes do esperado e fora da área de leitura dos sensores, o que leva a situações de difíceis de processar e manusear para os robots. As condições do terreno também podem mudar de dia para dia e áreas facilmente acessíveis hoje podem-se tornar inacessíveis amanhã. Todos estes problemas fazem a navegação exterior muito mais difícil do que o que normalmente se encontra dentro de uma casa.Para poderem ser chamados de robots autónomos, estes robots devem ser capazes de detetar tudo o que o rodeia, navegar sem ajuda humana, e serem capazes de completar as suas tarefas com sucesso. Para a realização destas tarefas um dos aspetos mais importantes é que estes robots tenham uma localização precisa e repetitiva. Em muitas ocasiões não é permitido que um robot passe pelo mesmo lugar duas vezes e reporte posições diferentes visto que isso pode levar a resultados catastróficos.As técnicas mais comuns para estimar a posição incluem a odometria, o sistema de navegação por satélite e o sistema de navegação inercial. De todos estes sistemas, o único que consegue obter verdadeiramente uma posição absoluta é o sistema de navegação por satélite, mas ao mesmo tempo baseia-se em serviços disponibilizados por terceiros e que pode ser desativados, o que se torna numa grande desvantagem.Para melhorar a estimação da posição, devem-se reduzir os erros associados com os recetores de satélite, e ao mesmo tempo implementar um sistema de navegação inercial de modo a que o nosso sistema de posicionamento pode ter duas fontes medições independentes e que consiga reduzir os erros de ambos os sistemas. Como o sistema de navegação inercial tem uma boa precisão a curto prazo e taxas de atualização elevadas, quando utilizado num sistema de fusão de dados permite tirar proveito das vantagens de ambos os sistemas.Nesta dissertação vão ser explicados os problemas existentes na navegação por satélite e inercial, e como reduzir os seus erros. É também explicado e implementado uma fusão de dados de ambos os sistemas a fim de alcançar uma maior precisão para o uso em robots de campo. No último capítulo é testada a fusão de dados assim como os sistemas individualmente. ; In the last decades, research in autonomous vehicles has been growing and involving more and more people due to their vast application potentials. Every year more mobile robots and electronic devices are joining our daily life.The improvements made in the processing power and the size reduction in the microcontrollers and similar processing boards, allowed the field of robotics to boost tremendously. These autonomous vehicles can have a tremendous importance for field robots and they can perform tedious and dangerous tasks to humans, with faster response times or in situations without human access. They can be used in scientific experiments using autonomous boats to patrol rivers, gathering water parameters and perform bathymetry studies. In military operations using autonomous drones to perform mapping and surveillance of critical areas. Or in an opposite sense, to clear post-combat regions of land mines using the robots to map wide areas without human interaction. To perform planetary exploration with mission like the Mars Exploration Rovers, that uses autonomous robots to land, explore, and study the geology of the Martian surface. And of course, the most actual contest that every big brand in the tech and mobile vehicles manufacturers is trying to win, to create a true self driving car.When these robots navigate outdoors they suffer from the unpredictability of everything that surround them. Objects that were stationary one moment ago, can start moving and becoming obstacles. Sometimes these objects have different contours than what we expect and out of the sensors range, which will lead to difficult situations for the robot to handle. The terrain conditions can change from day to day and undergo interactions by humans and weather conditions, making an easily travelled routed today inaccessible tomorrow. All these problems make outdoors navigation a lot more difficult than what we normally find indoors.In order to be truly called autonomous, these robots must be able to sense its environment, navigate without human input, and be able to complete their tasks. To performing such critical tasks, one of the most important aspects needed for these robots is an accurate and repetitive localization. On many critical occasions it is not allowed for a robot to drive by the same place twice and report different positions for that place, as such situation can lead catastrophic results.Some of the most common techniques used to estimate a position include the odometry, the Global Navigation Satellite System, and the Inertial Navigation System. From all these systems, the only one that can obtain a truly absolute position is the GNSS, but at the same time it relies on third party services which can be disabled or the satellites it depends on be temporarily occluded by obstacles.To improve the position estimation, one should reduce the errors associated with the GNSS receivers and at the same time implement an Inertial Navigation System, so that our new positioning system can have two independent measurements sources. As the INS can provide higher accuracy in the short-term and also good update rates, the estimated position obtained from the data fusion has the advantage of being accurate in short and long term, and at the same time have good update rates for a robot to navigate dynamically.The Global Navigation Satellite System (GNSS) and the Inertial Navigation System (INS) are two navigation systems commonly used nowadays that can be used to determine the robot's localization. Both systems have advantages and disadvantages, but they can complement each other when fused together in a GNSS/INS Navigation System. In this dissertation, it is going to explain the main problems when using this type of systems and how to reduce them. It's also explained and implemented a data fusion of both systems in order to achieve a higher precision. In the last chapter the implemented fusion is tested, and compared with others GNSS receivers available in the market with different prices and characteristics.
Autonomous manipulation in semi-structured environments where human operators can interact is an increasingly common task in robotic applications. This paper describes an intelligent multi-sensorial approach that solves this issue by providing a multi-robotic platform with a high degree of autonomy and the capability to perform complex tasks. The proposed sensorial system is composed of a hybrid visual servo control to efficiently guide the robot towards the object to be manipulated, an inertial motion capture system and an indoor localization system to avoid possible collisions between human operators and robots working in the same workspace, and a tactile sensor algorithm to correctly manipulate the object. The proposed controller employs the whole multi-sensorial system and combines the measurements of each one of the used sensors during two different phases considered in the robot task: a first phase where the robot approaches the object to be grasped, and a second phase of manipulation of the object. In both phases, the unexpected presence of humans is taken into account. This paper also presents the successful results obtained in several experimental setups which verify the validity of the proposed approach. ; This work was partially funded by the Ministry of Education and Science of the Spanish Government through the research projects DPI2008-02647 and DPI2011-22766.
Depth cameras, typically in RGB-D configurations, are common devices in mobile robotic platforms given their appealing features: high frequency and resolution, low price and power requirements, among others. These sensors may come with significant, non-linear errors in the depth measurements that jeopardize robot tasks, like free-space detection, environment reconstruction or visual robot-human interaction. This paper presents a method to calibrate such systematic errors with the help of a second, more precise range sensor, in our case a radial laser scanner. In contrast to what it may seem at first, this does not mean a serious limitation in practice since these two sensors are often mounted jointly in many mobile robotic platforms, as they complement well each other. Moreover, the laser scanner can be used just for the calibration process and get rid of it after that. The main contributions of the paper are: i) the calibration is formulated from a probabilistic perspective through a Maximum Likelihood Estimation problem, and ii) the proposed method can be easily executed automatically by mobile robotic platforms. To validate the proposed approach we evaluated for both, local distortion of 3D planar reconstructions and global shifts in the measurements, obtaining considerably more accurate results. A C++ open-source implementation of the presented method has been released for the benefit of the community. ; Research projects WISER (DPI2017-84827-R), funded by the Spanish Government and the European Regional Development's Funds (FEDER), MoveCare (ICT-26-2016b-GA-732158), funded by the European H2020 program, the European Social Found through the Youth Employment Initiative for the promotion of young researchers, and a postdoc contract from the IPPIT program of the University of Malaga. Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech.
This paper presents the application of a mobile robot designed as an Assistant Personal Robot (APR) as a walk-helper tool. The hypothesis is that the height and weight of this mobile robot can be used also to provide a dynamic physical support and guidance to people while they walk. This functionality is presented as a soft walking aid at home but not as a substitute of an assistive cane or a walker device, which may withstand higher weights and provide better stability during a walking. The APR operates as a walk-helper tool by providing user interaction using the original arms of the mobile robot and by using the onboard sensors of the mobile robot in order to avoid obstacles and guide the walking through free areas. The results of the experiments conducted with the walk-helper have showed the automatic generation of smooth walking trajectories and a reduction in the number of manual trajectory corrections required to complete a walking displacement. ; This work was partially funded by Indra and Adecco Fundation, accessibility grant 2017, the University of Lleida, UdL-Impuls Grant, the RecerCaixa 2013 grant, the Government of Catalonia (Comissionat per a Universitats i Recerca, Departament d'Innovació, Universitats i Empresa), and by the European Social Fund (ECO/1794/2015).