Ricardo José Sabatine

University of São Paulo, San Paulo, São Paulo, Brazil

Are you Ricardo José Sabatine?

Claim your profile

Publications (8)0 Total impact

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Self-localization is a fundamental problem in mobile robotics. It consists of estimating the position of a robot given a map of the environment and information obtained by sensors. Among the algorithms used to address this issue, the Monte Carlo technique has obtained a considerable attention by the scientific community due to its simplicity and efficiency. Monte Carlo localization is a sample-based technique that estimates robot´s pose using a probability density function represented by samples (particles). The complexity of this algorithm scales proportionally to the number of particles used. The larger the environment, the more particles are required for robot localization. This fact limits the use of this algorithm in large size environments. In order to improve the efficiency of the Monte Carlo technique and allow it to be used in large environments we propose a parallel implementation of it. Our implementation is based on OpenMP and MPI message passing interface. Experimental results are used to show the efficiency of our approach. Abstract Self-localization is a fundamental problem in mobile robotics. It consists of estimating the position of a robot given a map of the environment and information obtained by sensors. Among the algorithms used to address this issue, the Monte Carlo technique has obtained a considerable attention by the scientific community due to its simplicity and efficiency. Monte Carlo localization is a sample-based technique that estimates robot´s pose using a probability density function represented by samples (particles). The complexity of this algorithm scales proportionally to the number of particles used. The larger the environment, the more particles are required for robot localization. This fact limits the use of this algorithm in large size environments. In order to improve the efficiency of the Monte Carlo technique and allow it to be used in large environments we propose a parallel implementation of it. Our implementation is based on OpenMP and MPI message passing interface. Experimental results are used to show the efficiency of our approach.
    International Journal of Future Generation Communication and Networking International Journal of Future Generation Communication and Networking. 01/2010; 2(2):49-64.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Navigation is the foundation of mobile robots. In order to plan its path and successfully move in the environment a robot must know its on position in it. The problem is called self-localization and it consists of estimating the position of a robot given a map of the environment and information obtained by sensors. One of the most efficient algorithms used to address this issue is the Monte Carlo technique, which has obtained a considerable attention the scientific community due to its simplicity and precision. The complexity of this algorithm scales proportionally to the number of particles used. The larger the environment, the more particles are required for robot localization. This fact limits the use of this algorithm to medium size environments. In order to improve the efficiency of the Monte Carlo technique and allow it to be used in large environments we propose a parallel implementation. Our implementation is based on OpenMP and MPI message passing interface. Experimental results are used to show the efficiency of our approach.
    Convergence Information Technology, International Conference on. 11/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Navigation is the foundation of mobile robots. In order to plan its path and successfully move in the environment a robot must know its on position in it. The problem is called self-localization and it consists of estimating the position of a robot given a map of the environment and information obtained by sensors. One of the most efficient algorithms used to address this issue is the Monte Carlo technique, which has obtained a considerable attention the scientific community due to its simplicity and precision. The complexity of this algorithm scales proportionally to the number of particles used. The larger the environment, the more particles are required for robot localization. This fact limits the use of this algorithm to medium size environments. In order to improve the efficiency of the Monte Carlo technique and allow it to be used in large environments we propose a parallel implementation. Our implementation is based on OpenMP and MPI message passing interface. Experimental results are used to show the efficiency of our approach.
    Computer Sciences and Convergence Information Technology, 2009. ICCIT '09. Fourth International Conference on; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Self-localization is a fundamental problem in mobile robotics. It consists of estimating the position of a robot given a map of the environment and information obtained by sensors. Among the algorithms used to address this issue, the Monte Carlo technique has obtained a considerable attention by the scientific community due to its simplicity and precision. Monte Carlo localization is a sample-based technique that estimates robot's pose using a probability density function represented by samples (particles). The complexity of this algorithm scales proportionally to the number of particles used. The larger the environment, the more particles are required for robot localization. This fact limits the use of this algorithm to medium size environments. In order to improve the efficiency of the Monte Carlo technique and allow it to be used in large environments we propose a parallel implementation. Our implementation is based on OpenMP and MPI message passing interface. Experimental results are used to show the efficiency of our approach.
    Proceedings of the 2009 International Conference on Hybrid Information Technology, ICHIT 2009, Daejeon, Korea, August 27-29, 2009; 01/2009
  • G.M. Marques, R.J. Sabatine, K.R.L.J. Branco
    [Show abstract] [Hide abstract]
    ABSTRACT: The objective of this paper is to offer alternatives of process scheduling and to compare their performances. The environments obtained were considered by applying parallel processing of medical images using the comparison of their performance's time to measure them.
    Industrial Technology, 2008. ICIT 2008. IEEE International Conference on; 01/2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: The proposed mobile agent collects the load index and performs the distributed scheduling considering the behavior of the different kinds of applications. The environments obtained were considered due to the application of parallel processing of using medical images as well as the comparison of their performance time to measure them. The objective of this paper is to offer alternatives of processes scheduling aiming at maximize the use of the machines.
    Fourth International Conference on Networking and Services, ICNS 2008, 16-21 March 2008, Gosier, Guadeloupe; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper aims at demonstrating the viability in the use of parallel distributed computing to improve the image processing. Image processing techniques were implemented in the sequential and parallel way using the Java language and the parallel virtual libraries mpiJava and JPVM. A algorithm that executes the median filter was implemented and processed with different size of masks. From the results it was possible to make a comparison between the sequential and parallel implementation, and show that the gain using parallel distributed computing depending on the amount of data to be processed. Resumo. Este artigo tem como objetivo demonstrar a viabilidade da melhoria no tempo de execução de algoritmos utilizados para o processamento de imagens através do uso da computação paralela distribuída. Técnicas de processamento de imagens foram implementadas de forma seqüencial e paralela, utilizando a linguagem Java e as bibliotecas de trocas de mensagens mpiJava e JPVM. Foi implementado o algoritmo filtragem mediana, sendo executado com diferentes tamanhos de máscaras. A partir dos resultados obtidos foi possível construir uma base de comparação entre a implementação seqüencial e a paralela, e mostrar que o ganho de desempenho obtido com o paralelismo dependendo depende da quantidade de dados a ser processada.
  • Source