Navegação de veículos autônomos em ambientes externos não estruturados baseada em visão computacional

Klaser, Rafael Luiz

doi:10.11606/d.55.2014.tde-22092014-095209

Cited by 7 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Each node of the network can DOI: 10.3384/ecp181561 operate in the client/server mode, which allows direct interaction between the nodes, or by publishing/signing messages, which allows the use of sensors [2]. The use of the turtlebot for mapping and navigation based on the ROS is already widespread, which offers a lot of technical support, based on bibliography available on web, as an example of the proposed use of ROS in [3] where the autonomous robot was developed for navigation and the same deviates from persons and objects, according to their respective control algorithm, and navigation of structured and unstructured external environments [4]. Moreover, besides the aforementioned examples, a robotic system assistance has been proposed and deployed in [5] and an autonomous tunnel structural inspection and assessment has been evaluated in [6].…”

Section: System Architecturementioning

confidence: 99%

Proposal of an Autonomous System for Inspection of Structures

Oliveira

Silva

et al. 2018

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

Inspection of defects in civil infrastructure has been a constant field of research. The enlargement of a crack, along the time, can increase the deterioration of the structure, which can result in slight problems on the material's surface until, in the serious case, the rupture of the concrete structure. In the current operational paradigm, a technician is responsible to go physically to the field in order to measure cracks in the structures. However, in terms of efficiency, the manual inspection presents many problems, such as the low accuracy of measurements taken in the field and problems for accessing high-rises, narrows places, nuclear plants, among others. Hence, the current project developed at the Federal University of ABC aims to develop a fully autonomous system capable to automate the crack measurement detection and measurement process. The proposed system uses a set of robots capable to navigate and process data by itself, ground and aerial platforms, machine vision algorithms embedded into a processing device and a remote station in order to manage all the tasks to be done. In the current proposal, the ground platform adopted is the Turtlebot 2 ®, which uses an embedded computer to process the programs. The aerial platform to be adopted is an eight-engine drone-octocopter that will make use of the flight controller Pixhawk 2.1 ®. Both of them will be integrated and controlled from the network interconnection of several programs, such as mapping, navigation, and image processing programs. Thus, simulations will be performed by using the Gazebo ® program and the Robot Operating System ®, wherein the system will be exposed to the real situations to evaluate the system efficiency. As result, once the autonomous system detects cracks, the embedded vision system algorithm must be able to process the image and assess the type and the damage caused to the inspected structure.

show abstract

Section: System Architecturementioning

confidence: 99%

Proposal of an Autonomous System for Inspection of Structures

Oliveira

Silva

et al. 2018

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…Posteriormente, houve uma migração visando uma adoção mais relacionada a sensores que permitam uma melhor descrição tridimensional do ambiente e de seus obstáculos e elementos. Passou-se a utilizar câmeras estéreo e o Velodyne (laser com 32 feixes adotado no CaRINA 2) (Klaser, 2014), assim como foi dada uma atenção especial aos problemas de calibração e fusão de sensores.…”

Section: Ros -Robotic Operating Systemunclassified

“…No desenvolvimento desta tese foram realizados inicialmente trabalhos que permitiram o estudo, acompanhamento de trabalhos, desenvolvimento e implementação de diferentes métodos de percepção do ambiente em 2D e 3D (p.ex. sensores laser do tipo LIDAR , visão monocular Shinzato et al, 2010) e visão estéreo Klaser, 2014), além da atuação no projeto e desenvolvimento de veículos inteligentes, resultando em importantes contribuições no desenvolvimento do projeto CaRINA (abordado no capítulo 2).…”

Section: Introductionunclassified

Uma contribuição ao desenvolvimento de sistemas baseados em visão estéreo para o auxílio a navegação de robôs móveis e veículos inteligentes

Fernandes¹

View full text Add to dashboard Cite

show abstract

“…Cabe destacar que o presente projeto visa dar continuidade aos trabalhos em desenvolvimento junto ao LRM-ICMC/USP e INCT-SEC, focados no estudo e desenvolvimento de métodos e algoritmos para a detecção de obstáculos visando à navegação autônoma de robôs móveis, onde podemos destacar três dissertações de mestrado defendidas recentemente (HATA, 2010;SHINZATO, 2010;MENDES, 2012;KLASER, 2013) que deram origem a diversas publicações importantes e novos projetos.…”

Section: Figura 13 -A) Projeto Carina I B) Projetounclassified

Fusão de informações obtidas a partir de múltiplas imagens visando à navegação autônoma de veículos inteligentes em abiente agrícola

Utino¹

View full text Add to dashboard Cite

his work presents a support system to the autonomous navigation for ground vehicles with focus on structured environments in an agricultural scenario. The estimated obstacle positions are generated based on the fusion of the detections from the processing of data from two cameras, one stereo and other thermal. Three modules obstacle detection have been developed. The first module uses monocular images of the stereo camera to detect novelties in the environment by comparing the current state with the previous state. The second module uses Stixel technique to delimit the obstacles above the ground plane. Finally, the third module uses thermal images to find signatures that reveal the presence of obstacle. The detection modules are fused using the Dempster-Shafer theory that provides an estimate of the presence of obstacles in the environment. The experiments were executed in real agricultural environment. System validation was performed in well-lit scenarios, with uneven terrain and different obstacles. The system showed satisfactory performance considering the use of an approach based on only three detection modules with methods that do not prioritize obstacle confirmation, but the search for new ones. This dissertation presents the main components of an obstacle detection system and the necessary steps for its design as well as results of experiments with the use of a real vehicle.

show abstract

Navegação de veículos autônomos em ambientes externos não estruturados baseada em visão computacional

Cited by 7 publications

References 37 publications

Proposal of an Autonomous System for Inspection of Structures

Proposal of an Autonomous System for Inspection of Structures

Uma contribuição ao desenvolvimento de sistemas baseados em visão estéreo para o auxílio a navegação de robôs móveis e veículos inteligentes

Fusão de informações obtidas a partir de múltiplas imagens visando à navegação autônoma de veículos inteligentes em abiente agrícola

Contact Info

Product

Resources

About