Cookies Policy
We use cookies to improve our site and your experience. By continuing to browse our site you accept our cookie policy. Find out More
Close
  • Menu
Facts & Numbers
000
Presentation

Robotics and Autonomous Systems

At CRAS, our mission is to develop innovative robotic solutions for complex environments and multiple operations, including data gathering, inspection, mapping, surveillance, and intervention.

We work in four main areas of research: autonomous navigation; long-term deployments; sensing, mapping, and intervention; multiple platform operations.

Latest News
Networked Intelligent Systems

Underwater mining is already possible and has signature of INESC TEC

Underwater mining is already possible. It proved to be both economically profitable and favourable for the environment.

28th December 2018

Networked Intelligent Systems

First Portuguese Scientist-astronaut is a researcher at INESC TEC

In October, Ana Pires became the first Portuguese woman to obtain the scientist-astronaut diploma in the PoSSUM Scientist Astronaut Qualification Program, which was supported by NASA and taught at the Embry-riddle Aeronautical University (Florida, USA), one of the most prestigious universities in the United States for already having trained several astronauts.

26th December 2018

Networked Intelligent Systems

Event about Geosciences with the collaboration of INESC TEC

Ana Cristina Pires participated in the conference entitled “The Near Surface Geoscience Conference & Exhibition 2018”.

13th December 2018

Networked Intelligent Systems

INESC TEC participates in symposium about AUVs

Alfredo Martins, Aníbal Matos, Eduardo Silva and Nuno Cruz, collaborators of INESC TEC’s Centre for Robotics and Autonomous Systems (CRAS) were part of the International Committee of the organisation of the AUV - Autonomous Underwater Vehicle Symposium, an event dedicated to technology and its corresponding applications in autonomous maritime vehicles.

26th November 2018

INESC TEC participates in international conference on intelligent robotics

Alfredo Martins and José Almeida, researchers of INESC TEC’s Centre for Robotics and Autonomous Systems (CRAS), participated in IROS 2018, which took place between 1 and 5 October in Madrid, Spain.

19th November 2018

Interest Topics
002

Featured Projects

ENDURANCE

Underwater wireless energy and communications enabling long-term deep-sea presence

2018-2020

FEEDFIRST

Desenvolvimento de uma nova tecnologia para cultivo de larvas de peixes à primeira alimentação

2018-2020

Team
001

Laboratories

Robotics and Autonomous Systems Laboratory

Publications

CRAS Publications

View all Publications

2018

An FPGA array for cellular genetic algorithms: Application to the minimum energy broadcast problem

Authors
dos Santos, PV; Alves, JC; Ferreira, JC;

Publication
Microprocessors and Microsystems

Abstract
The genetic algorithm is a general purpose optimization metaheuristic for solving complex optimization problems. Because the algorithm usually requires a large number of iterations to evolve a population of solutions to good final solutions, it normally exhibits long execution times, especially if running on low-performance conventional processors. In this work, we present a scalable computing array to parallelize and accelerate the execution of cellular GAs (cGAs). This is a variant of genetic algorithms which can conveniently exploit the coarse-grain parallelism afforded by custom parallel processing. The proposed architecture targets Xilinx FPGAs and was implemented as an auxiliary processor of an embedded soft-core CPU (MicroBlaze). To facilitate the customization for different optimization problems, a high-level synthesis design flow is proposed where the problem-dependent operations are specified in C++ and synthesised to custom hardware, thus demanding of the programmer only minimal knowledge of low-level digital design for FPGAs. To demonstrate the efficiency of the array processor architecture and the effectiveness of the design methodology, the development of a hardware solver for the minimum energy broadcast problem in wireless ad hoc networks is employed as a use case. Implementation results for a Virtex-6 FPGA show significant speedups, especially when comparing to embedded processors used in current FPGA devices. © 2018

2018

Urban@CRAS dataset: Benchmarking of visual odometry and SLAM techniques

Authors
Gaspar, AR; Nunes, A; Pinto, AM; Matos, A;

Publication
Robotics and Autonomous Systems

Abstract

2018

A Safety Monitoring Model for a Faulty Mobile Robot

Authors
Leite, A; Pinto, A; Matos, A;

Publication
ROBOTICS

Abstract
The continued development of mobile robots (MR) must be accompanied by an increase in robotics' safety measures. Not only must MR be capable of detecting and diagnosing faults, they should also be capable of understanding when the dangers of a mission, to themselves and the surrounding environment, warrant the abandonment of their endeavors. Analysis of fault detection and diagnosis techniques helps shed light on the challenges of the robotic field, while also showing a lack of research in autonomous decision-making tools. This paper proposes a new skill-based architecture for mobile robots, together with a novel risk assessment and decision-making model to overcome the difficulties currently felt in autonomous robot design.

2018

The last frontier: Coupling technological developments with scientific challenges to improve hazard assessment of deep-sea mining

Authors
Santos, MM; Jorge, PAS; Coimbra, J; Vale, C; Caetano, M; Bastos, L; Iglesias, I; Guimarães, L; Reis Henriques, MA; Teles, LO; Vieira, MN; Raimundo, J; Pinheiro, M; Nogueira, V; Pereira, R; Neuparth, T; Ribeiro, MC; Silva, E; Castro, LFC;

Publication
Science of the Total Environment

Abstract
The growing economic interest in the exploitation of mineral resources on deep-ocean beds, including those in the vicinity of sensitive-rich habitats such as hydrothermal vents, raise a mounting concern about the damage that such actions might originate to these poorly-know ecosystems, which represent millions of years of evolution and adaptations to extreme environmental conditions. It has been suggested that mining may cause a major impact on vent ecosystems and other deep-sea areas. Yet, the scale and the nature of such impacts are unknown at present. Hence, building upon currently available scientific information it is crucial to develop new cost-effective technologies embedded into rigorous operating frameworks. The forward-thinking provided here will assist in the development of new technologies and tools to address the major challenges associated with deep sea-mining; technologies for in situ and ex situ observation and data acquisition, biogeochemical processes, hazard assessment of deep-sea mining to marine organisms and development of modeling tools in support of risk assessment scenarios. These technological developments are vital to validate a responsible and sustainable exploitation of the deep-sea mineral resources, based on the precautionary principle. © 2018 Elsevier B.V.

2018

Supervised classification for hyperspectral imaging in UAV maritime target detection

Authors
Freitas, S; Almeida, C; Silva, H; Almeida, J; Silva, E;

Publication
18th IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2018

Abstract
This paper addresses the use of a hyperspectral image system to detect vessels in maritime operational scenarios. The developed hyperspectral imaging classification methods are based on supervised approaches and allow to detect the presence of vessels using real hyperspectral data. We implemented two different methods for comparison purposes: SVM and SAM. The SVM method, which can be considered one of most utilized methods for image classification, was implemented using linear, RBF, sigmoid and polynomial kernels with PCA for dimensionality reduction, and compared with SAM using a two classes definition, namely vessel and water. The obtained results using real data collected from a UAV allow to conclude that the SVM approach is suitable for detecting the vessel presence in the water with a precision and recall rates favorable when compared to SAM. © 2018 IEEE.

Supervised Theses

2018

Multi-Robot 3D Target Estimation Under Uncertainty

Author
André Miguel Pinheiro Dias

Institution
Outra

2017

Physical Design Implementation and Engineering Change Order Flow

Author
Afonso Ferreira Pinto Gomes Moreira

Institution
UP-FEUP

2017

Mapeamento e odometria visual em ambiente subáquatico

Author
Alexandra Pereira Nunes

Institution
UP-FEUP

2017

Navegação e mapeamento subaquáticos simultâneos

Author
Ana Rita da Silva Gaspar

Institution
UP-FEUP

2017

Integração de um Manipulador numa Embarcação Robótica

Author
André Filipe Sousa Pinto

Institution
UP-FEUP

Facts & Figures

1Concluded PhD theses

2016

10Academic Staff

2016

1246EU Programmes (k€)

2016

Contacts