Gonçalo de Abreu Silvério Cabrita
|
|
Data da última atualização
»Last update
:
18/09/2013 |
Dados pessoais (Personal data)
Nome completo
Full name |
Gonçalo de Abreu Silvério Cabrita |
Nome em citações bibliográficas
Quoting name |
Cabrita, Gonçalo de Abreu Silvério |
Categoria profissional
Position |
Investigador Principal |
Domínio científico de atuação
Scientific domain |
Engenharia e Tecnologia-Engenharia Electrotécnica, Electrónica e Informática.
|
Endereço profissional
Professional address |
Universidade de Coimbra Instituto de Sistemas e Robótica Pinhal de Marrocos, Pólo 2 Coimbra 3030-290 Coimbra Portugal Telefone: (+351)239796277 Fax: (+351)406672 Correio electrónico: goncabrita@isr.uc.pt Homepage: http://lse.isr.uc.pt/ |
Sexo
Gender |
Masculino»Male |
Graus Académicos
(Academic Degrees)
2003-2009 |
Mestrado Master degree |
Engenharia Electrotécnica e Computadores
(5 anos » years)
.
Universidade de Coimbra,
Portugal.
|
Vínculos profissionais
(Professional Positions)
Set/2009-Actual |
Investigador Principal |
Projetos de Investigação (Research projects)
Participação como Investigador Participation as Researcher |
Referência do projeto»Project reference: FP6-IST-045269.
|
Participação como Doutorando Participation as Phd student |
Referência do projeto»Project reference: FP7/2007-2013.
|
Línguas (Languages)
Compreende Understandig |
Inglês (Bem). |
Fala Speaking |
Inglês (Bem). |
Lê Reading |
Inglês (Bem). |
Escreve Writing |
Inglês (Bem). |
Produção científica, técnica e artística/cultural
(Scientific, technical and artistical/cultural
production)
Trabalhos completos/resumidos em eventos com arbitragem científica Papers in conference proceedings with scientific refereeing |
1. |
Cabrita, Gonçalo A. S; Marques, Lino. 2011. "Environmental Monitoring with the Particle Plume Explorer Algorithm", Trabalho apresentado em IROS 2011 Workshop on Robotics for Environmental Monitoring , In IROS 2011 Workshop on Robotics for Environmental Monitoring , San Francisco. This paper presents a modified version of the Particle Plume Explorer algorithm for environmental moni- toring applications.
This algorithm is supported by the point cloud based plume mapping method called Particle Plume also presented here. The exploratory
nature of Particle Plume Explorer is combined with the use of an expire time on the Particle Plume odor mapping algorithm
to achieve a monitoring behavior. The developed algorithm was validated through extensive real world experiments on multiple
indoor environments using a robot equipped with a gas sensors, showing that Particle Plume Explorer is a robust solution for
indoor environmental monitoring.
. |
|
|
|
2. |
Osório, Luís; Cabrita, Gonçalo A. S; Marques, Lino. 2011. "Mobile Robot Odor Plume Tracking Using Three Dimensional Information", Trabalho apresentado em 2011 European Conference on Mobile Robots (ECRM 2011), In 2011 European Conference on Mobile Robots, Orebro. This paper explores the possibility of using data gathered from multiple gas sensors placed vertically on a mobile robot to
perform plume tracking algorithms, in order to determine if three dimensional plume acquisition can provide any advantage
is terms of plume tracking over traditional two dimensional plume acquisition. This was accomplished by testing a few well
known plume tracking algorithms (Surge-Caste, Casting and Gradient following) against a modified version of each one of the
algorithms, designed to input odor data from the gas sensor vertical array. Extensive real world experiments were conducted
on an indoor environment. It was determined that three dimensional plume acquisition outperforms the two dimensional version
when applied for plume tracking.
.
|
|
|
|
3. |
Cabrita, Gonçalo A. S; Sousa, Pedro; Marques, Lino. 2011. "Odor Guided Exploration and Plume Tracking - Particle Plume Explorer", Trabalho apresentado em 2011 European Conference on Mobile Robots (ECRM 2011), In 2011 European Conference on Mobile Robots, Orebro. This paper presents a new algorithm for single robot odor exploration called Particle Plume Explorer. This algorithm is supported
by a novel point cloud based plume mapping method called Particle Plume also presented here. The developed algorithm was validated
through extensive real world experiments on multiple environments using a single robot equipped with a gas sensor.
.
|
|
|
|
4. |
Cabrita, Gonçalo A. S; Sousa, Pedro; Marques, Lino. 2010. "PlumeSim - Player/Stage Plume Simulator", Trabalho apresentado em ICRA 2010 Workshop for Networked and Mobile Robot Olfaction in Natural, Dynamic Environments, In ICRA 2010 Workshop for Networked and Mobile Robot Olfaction in Natural, Dynamic Environments, Anchorage. The article describes a Player/Stage simulation framework for mobile robot olfactory experiments. The PlumeSim framework simulates
odor transport in the environment, as well as olfactory detection systems. The odor transport can be based on analytical theoretical
models, or on data generated by dedicated computational fluid dynamics (CFD) software packages, or data acquired in a real
environment. The odor sensing process is modeled against data acquired by different time response sensors gas sensors. The
complete framework is validated through the comparison of the results obtained by simulated and by real mobile robot olfactory
experiments in a controlled environment.
.
|
|
|
|
5. |
Cabrita, Gonçalo A. S; Sousa, Pedro; Marques, Lino; Almeida, Aníbal T. 2010. "Infrastructure Monitoring With Multi-Robot Teams", Trabalho apresentado em IROS 2010 Workshop on Robotics for Environmental Monitoring, In IROS 2010 Workshop on Robotics for Environmental Monitoring, Taipei. This article presents the first steps toward an automatic indoor environmental monitoring system through the use of a group
of mobile robots. A metric map is provided a priori to the robots, ensuring the navigation, localization and extraction of
points of interests for patrolling. The communication layer is robust and allows any robot to enter or leave the patrolling
task. The monitoring of the environment is achieved by acquiring environmental information during the patrolling. If an abnormal
condition is detected, the system should react, providing a fine coverage of the suspicious area and an accurate identification
of its source. Experiments were conducted inside a building and data was gathered and post processed. The yet preliminary
results demonstrate the effectiveness of the method employed to control the system, showing good area coverage from the patrolling
algorithm and acceptable representations of the collected variables (alcohol concentration and temperature).
. |
|
|
|
Artigos em revistas sem arbitragem científica Papers in periodics without scientific refereeing |
1. |
Tavakoli, M.; Cabrita, G.; Faria, R.; Marques, L.; de Almeida, A. T. 2012. "Cooperative multi-agent mapping of three-dimensional structures for pipeline inspection applications", The International Journal of Robotics Research 31, 12: 1489 - 1503.
|
|
|
|
2. |
Turduev, Mirbek; Cabrita, Gonçalo; Kirtay, Murat; Gazi, Veysel; Marques, Lino. 2012. "Experimental studies on chemical concentration map building by a multi-robot system using bio-inspired algorithms", Autonomous Agents and Multi-Agent Systems, 1: 1 - 29.
|
|
|
|
Trabalhos completos/resumidos em eventos sem arbitragem científica Papers in conference proceedings without scientific refereeing |
1. |
Cabrita, Gonçalo A. S; Marques, Lino. 2013. "Divergence-based Odor Source Declaration", Trabalho apresentado em 2013 IEEE Asian Control Conference (ASCC2013), In 2013 IEEE Asian Control Conference, Istabul. |
|
|
|
2. |
Cabrita, Gonçalo A. S; Marques, Lino; Gazi, Veysel. 2013. "Virtual Cancelation Plume for Multiple Odor Source Localization", Trabalho apresentado em 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2013), In 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, Tokyo. |
|
|
|
3. |
Cabrita, Gonçalo A. S; Marques, Lino. 2013. "Odor plume detection in water streams", Trabalho apresentado em RSS 2013 Workshop on Robotics for Environmental Monitoring, In RSS 2013 Workshop on Robotics for Environmental Monitoring, Berlin. |
|
|
|
4. |
Prado, José; Cabrita, Gonçalo A. S; Marques, Lino. 2013. "Bayesian Sensor Fusion for Land-mine Detection Using a Dual-sensor Hand-held Device", Trabalho apresentado em 39th Annual Conference of the IEEE Industrial Electronics Society, In 39th Annual Conference of the IEEE Industrial Electronics Society, Vienna, Austria. |
|
|
|
5. |
Cabrita, Gonçalo A. S; Marques, Lino. 2013. "Estimation of Gaussian Plume Model Parameters Using the Simulated Annealing Algorithm", Trabalho apresentado em ROBOT 2013 First Iberian Robotics Conference, In Springer Series in Advances in Intelligent Systems and Computing, Madrid. |
|
|
|
6. |
Fraga, Jorge; Sousa, João; Cabrita, Gonçalo A. S; Coimbra, Paulo; Marques, Lino. 2013. "Squirtle: an ASV for Inland Water Environmental Monitoring", Trabalho apresentado em ROBOT 2013 First Iberian Robotics Conference, In Springer Series in Advances in Intelligent Systems and Computing, Madrid. |
|
|
|
7. |
Prado, José; Cabrita, Gonçalo A. S; Marques, Lino. 2013. "Efficient area coverage for an autonomous demining robot", Trabalho apresentado em ROBOT 2013 First Iberian Robotics Conference, In Springer Series in Advances in Intelligent Systems and Computing, Madrid. |
|
|
|
8. |
Cabrita, Gonçalo A. S; Marques, Lino. 2012. "Tools and methodologies for gathering plume tracking skills from dogs", Trabalho apresentado em IROS 2012 Workshop on Robotics for Environmental Monitoring, In IROS 2012 Workshop on Robotics for Environmental Monitoring, Vilamoura, Algarve. |
|
|
|
9. |
Cabrita, Gonçalo; Sousa, Pedro; Marques, Lino. 2010. "Player/Stage simulation of olfactory experiments", Trabalho apresentado em 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), In 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, Taipei.
|
|
|
|
Software sem registo ou patente Software without patent or official record |
1. |
Cabrita, Gonçalo A. S. LSE MiniQ,2013.
|
2. |
Cabrita, Gonçalo A. S. Squirtle Driver,2013. |
3. |
Cabrita, Gonçalo A. S. Pole Structure Mapper,2012.
|
4. |
Cabrita, Gonçalo A. S; Sousa, Pedro. Particle Plume Explorer,2011. PPExplorer is a an odor oriented exploration algorithm that builds on top of the odor mapping package particle_plume.
The PPE algorithm is in charge of odor oriented exploration and plume tracking. This is accomplished in four steps. (1) Initially
a circle of radius r is drawn around the robot and divided into n slices. (2) Next the slices which overlap with obstacles
are removed. (3) The slices which contain a percentage of explored area over a certain threshold are then also removed. (4)
Finally the cost of each remaining slice is calculated using a cost function. The slice with the lowest cost is chosen and
the goal is set. The variables used fore the cost function are the amount of explored area, the angular distance to the odor
gradient and the angular distance to the current heading of the robot.
.
|
5. |
Cabrita, Gonçalo A. S; Sousa, Pedro. Particle Plume,2011. Particle Plume is a 3D odor mapping algorithm. It intends to tackle the problems of plume intermittence, gas sensor noise
and chemical data sharing between robots when applicable.
Particle Plume represents plumes as point clouds using PCL. A grid of visited cells us also generated, allowing to distinguish
between visited locations with no odor present and locations which were not yet visited.
.
|
6. |
Cabrita, Gonçalo A. S; Sousa, Pedro. PlumeSim,2010. PlumeSim is a plume simulation software. It was originally a plugin driver designed to work with Player/Stage, bringing plume
simulation into the world of mobile robotics. It is capable of feeding simulated chemical plumes into a simulated or real
robot from a wide range of sources, from mathematical models to data generated by computational fluid dynamics (CFD) software.
It is also able to use data collected from real world experiments, enabling it to playback a recorded chemical plume over
and over again.
This software package is a great tool for developing odor search algorithms, providing a smooth path of progression from a
simulated robot and environment, to a real robot with a simulated plume and finally to a real experiment.
In this stack a ROS version of PlumeSim can be found, with visualization support over rviz.
|
7. |
Cabrita, Gonçalo A. S; Sousa, Pedro. WifiComm,2010. WifiComm allows multi-robot peer-2-peer style communication. The discovery node works together with olsrd to publish information
related to available neighbors. A library is also available to allow for easy opening and closing of foreign_relays, the method
by which local topics are published on a foreign roscore, thus providing the communication channel.
.
|
8. |
Cabrita, Gonçalo A. S; Sousa, Pedro. CerealPort,2010. CerealPort was design to make life easier when developing drivers for ROS. CerealPort includes various methods for reading
data from a serial port, including threaded streaming.
.
|
9. |
Cabrita, Gonçalo A. S. Xsens MTi Driver,2010. Xsens MTi node. The existing xsens_mti node is distributed in the form of a library and requires the MTi to be set to a determined
configuration to work. We had some old code laying around so we just ported it to ROS. This sends the MTi to configuration
mode at start and sets it to the propper mode of operation.
.
|
10. |
Cabrita, Gonçalo A. S. Roomba 500 Driver,2010. iRobot Roomba 500 package based on the iRobot Open Interface Specification. There are two nodes available, a light node which
exposes odometry and velocity commands, and a full node which exposes all capabilities of the underlying library.
.
|
11. |
Cabrita, Gonçalo A. S. Scout Driver,2010. Wraper for the Ndirect library, allowing control of a Scout robot on ROS.
.
|
12. |
Cabrita, Gonçalo A. S. Windsonic Driver,2010. A ROS node to provide access to Gill Instruments Windsonic, an ultrasonic wind sensor.
.
|
Produto sem registo ou patente Product without patent or official record |
1. |
Cabrita, Gonçalo A. S. LSE MiniQ,2013. Tipo de produto: Projeto;Natureza do produto: Aparelho.
|
2. |
Cabrita, Gonçalo A. S; Marques, Lino. Squirtle,2013. Tipo de produto: Protótipo;Natureza do produto: Aparelho. |
3. |
Cabrita, Gonçalo A. S; Marques, Lino. Noseduino Nano,2011. Tipo de produto: Protótipo;Natureza do produto: Aparelho. The goal of this project is to develop a small e-nose with a single MOX gas sensor based on the Arduino Nano. This e-nose
will be used on mobile robots to allow the testing of odor related algorithms where the nature of the chemical being used
is not relevant. The following subsection highlights the features for the device.
Features
• Compact, small size;
• Low power consumption, USB powered; •
Single MOX sensor with temperature control;
• Temperature and humidity sensor;
• Able to run with or without sampling chamber;
• Ability to control the sampling chamber pump. |
Apresentação oral de trabalho Oral work presentation |
1. |
Cabrita, Gonçalo A. S. What is ROS?,ROS @ ISR Coimbra,Coimbra,2011 (Simpósio). Keynote presentation on what is ROS, what it's for and how it can help the robotics research community.
.
|
Organização de evento Event organization |
1. |
Cabrita, Gonçalo A. S; Sousa, Pedro; Marques, Lino; Portugal, David. ROS @ ISR Coimbra,2011 (Simpósio / Outra). 1. Overview
ROS is an open source distributed robotics platform designed to accelerate robotics research and development, including commercial
application development. ROS is a high-quality, actively maintained, well-documented software platform intended to support
the academic and industrial robotics communities. ROS includes reusable components that implement a variety of low- and high-level
functionality, such as base navigation, mapping, visual odometry, arm planning and control, data visualization, object recognition,
and task-level execution. ROS supports a number of research robots and common robot simulators.
All ROS software is released under an Open Source license, and the great majority of it is licensed under a BSD-style license
that allows users and companies to build applications on top without licensing constraints.
2. Audience
The primary audience is robot software developers and algorithm researchers from the ISR as well as students from the DEEC.
3. Motivation and objectives
The motive for this event is to introduce ROS to the ISR and DEEC researcher and student community.
.
|
Indicadores de produção
(Production indicators)
Produção científica
Scientific production |
Produção técnica
Technical production |
Produção científica Scientific production |
16 |
Artigos científicos em revistas Papers in periodics |
2 |
Sem arbitragem científica Without scientific refereeing |
2 |
Trabalhos em eventos Papers in conference proceedings |
14 |
Com arbitragem científica With scientific refereeing |
5 |
Sem arbitragem científica Without scientific refereeing |
9 |
Produção técnica Technical production |
17 |
Software sem registo ou patente Software without patent or official record |
12 |
Produtos sem registo ou patente Products without patent or official record |
3 |
Outros tipos de produção técnica Other technical production |
2 |
Visualizações do curriculum [
1405
]
|
Página gerada pela Plataforma de Curricula DeGóis promovida pela FCT e pelo Gávea/DSI/UM
em
14-06-2021
às
03:14:20
|
Plataforma de Curricula DeGóis: http://www.degois.pt/ | Icons by Axialis Team |
|