Guilherme Pereira | UFMG - The Federal University of Minas Gerais (original) (raw)

Papers by Guilherme Pereira

This work presents a safe navigation approach for a car-like robot. It is based on a Velocity Vec... more This work presents a safe navigation approach for a car-like robot. It is based on a Velocity Vector Field along with a Dynamic Window Approach for avoiding unmodeled obstacles. The vector field is associated to a controller whose outputs are validated, and eventually modified, by the Dynamic Window Approach and then applied as control inputs for the car. Experiments show that the vehicle was able to track the vector field and avoid obstacles in its way. Resumo— Este trabalho aborda o problema de navegação segura de um carro autônomo. Para tanto, ´ e utilizado um planejamento de movimento por meio de Campos Vetoriais de Velocidade aliado ao Método da Janela Dinâmica para o desvio de obstáculos não modelados. Basicamente, o campo vetoriaí e associado a um controlador cujas saídas são validadas, e eventualmente modificadas, pelo Método da Janela Dinâmica e aplicadas como entradas de controle do carro. Resultados experimentais mostraram que a metologia foi capaz de guiar um carro autôn...

Since the beginning of the movement for quality management programs based on ISO 9000 or/and ISO/... more Since the beginning of the movement for quality management programs based on ISO 9000 or/and ISO/IEC 17025 that were adopted by many type of industries, calibration laboratories have been under pressure to increase productivity. This work is about a computational system to automate the entire instrument calibration process. The computer vision system proposed is to be used to read the display of both analogue as well as digital instruments that do not have communication interfaces to computers such as GPIB or RS-232. In order to figure out instrument indication, the system employs an optical character recognition technique in digital displays and Canny's method for edge detection and the Hough's transform method for line localization in analogue displays, accelerating the data acquisition process and makes it less prone to errors. Consequently, it contributes to improve calibration and reduce costs, increasing the number of instruments with quality assured measurements.

This work presents an obstacle detection system for an autonomous car using stereo vision. The sy... more This work presents an obstacle detection system for an autonomous car using stereo vision. The system is based on the " V " disparity map, which is obtained by a simple transformation of the traditional disparity map. With this map, planes in the image are easily detected, classified and used to navigate the vehicle. To exemplify the system applicability to obstacle avoidance, it was used together with the vector field histogram (VFH) method. Experimental results show that the technique is promising and may be used to safely navigate an autonomous car in environments with obstacles. Resumo— Este artigo apresenta um sistema de detecção de obstáculos e planos trafegáveis para um carro autônomo a partir de um sistema de visão estéreo. O sistemá e baseado no mapa de disparidade " V " , qué e uma transformação do mapa de disparidade convencional. Com este mapa, planos na imagem são facilmente detectados e classificados, podendo assim ser usados para navegação do veícu...

Resumo: Este artigo apresenta um sistema para leitura de instrumentos de medição por meio de visã... more Resumo: Este artigo apresenta um sistema para leitura de instrumentos de medição por meio de visão computacional. Este sistema será parte de um produto maior que visa a calibração automática de instrumentos com ou sem interface de comunicação com o computador. O artigo propõe técnicas simples e de baixo custo que permitem a leitura de instrumentos digitais e analógicos em tempo de execução (15Hz). Os resultados apresentados indicam que o sistema poderá ser utilizado com sucesso no processo de calibração. Palavras chave: leitura de instrumentos de medição, visão computacional, automação, calibração de instrumentos. 1. INTRODUÇÃO A ação humana em determinados sistemas é muito sujeita a erros. Trabalhos repetitivos e esforços desnecessários são exemplos de situações que produzem desconforto para quem os faz e podem causar resultados negativos em uma aplicação. Na calibração de instrumentos de medição, por exemplo, o técnico deve adquirir valores e anotá-los um a um em uma planilha, rep...

Resumo-Este artigo apresenta uma nova solução para o problema de orientação de objetos com um rob... more Resumo-Este artigo apresenta uma nova solução para o problema de orientação de objetos com um robô móvel. A metodologiaé baseada em campos vetorias artificiais e não requer um conhecimento explícito da geometria do objeto, sendo aplicável tanto para objetos convexos como para os não convexos. O método pode ser facilmente integrado a técnicas de transporte para permitir a manipulação completa do objeto. Apesar da prova de convergência da metodologia assumir robôs holonômicos e pontuais, experimentos com robôs não-holonômicos circulares mostram sua aplicação para robôs móveis reais.

Http Dx Doi Org 10 1080 01691864 2013 778942, May 14, 2013

ABSTRACT This paper presents a decentralized controller to guide a group of aerial robots to conv... more ABSTRACT This paper presents a decentralized controller to guide a group of aerial robots to converge to and to move along a simple closed curve specified in a three-dimensional environment. This curve may be considered as a perimeter to be surveilled by the robots. The solution presented in this paper is based on an artificial vector field modulated by a collision avoidance scheme and relies only on local sensing. Proofs of asymptotic stability of the proposed controller are devised for a team of kinematically controlled rotorcrafts. Experimental results with a group of autonomous quadrotors are presented to validate the applicability and performance of the approach.

2007 Ieee Rsj International Conference on Intelligent Robots and Systems, Oct 1, 2007

This paper presents experimental results on the localization of a mobile robot equipped with rela... more This paper presents experimental results on the localization of a mobile robot equipped with relative frequent and absolute infrequent sensors. The relative sensors used are two: a wheel based odometry and a visual based odometry. The absolute sensor is a vision based landmark detector that computes the pose of the robot relative to a pre-mapped visual beacon. This would be

Materia, Dec 1, 2006

Este trabalho determina as relações entre os ângulos das articulações interfalangeanas e metacarp... more Este trabalho determina as relações entre os ângulos das articulações interfalangeanas e metacarpofalangeanas para os dedos indicador, médio, anular e mínimo da mão humana durante alguns movimentos de pinça com o objetivo de desenvolver uma prótese multifuncional de mão com movimentos antropomórficos. Uma das grandes dificuldades encontradas para o desenvolvimento destas relações é o fato da mão apresentar um elevado número de graus de liberdade, dificultando a análise dos dados. Utiliza-se um sistema de captura de imagem em apenas um plano para analisar o movimento. Determinam-se as relações para os movimentos de flexão e extensão dos dedos, desprezando adução e abdução durante a realização destas pinças.

42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475), 2003

We present a method to coordinate a large number of underactuated robots by designing control law... more We present a method to coordinate a large number of underactuated robots by designing control laws on a small dimensional manifold, independent on the number and ordering of the robots. The small dimensional description of the team has a product structure of a Lie group, which captures the dependence of the ensemble on the world frame, and a shape manifold, which is an intrinsic description of the team. We design decoupled controls for group and shape. The individual control laws which are mapped to the desired collective behavior can be realized by feedback depending only on the current state of the robot and the state on the small dimensional manifold, so that the robots have to broadcast their states and only have to listen to some coordinating agent with small bandwidth.

SMC 2000 Conference Proceedings. 2000 IEEE International Conference on Systems, Man and Cybernetics. 'Cybernetics Evolving to Systems, Humans, Organizations, and their Complex Interactions' (Cat. No.00CH37166), 2000

... Observed Small Robots Guilherme A. S. Pereira, MBrio F. M. Campos, and Luis A. Aguirre ... I ... more ... Observed Small Robots Guilherme A. S. Pereira, MBrio F. M. Campos, and Luis A. Aguirre ... I I I I - - A I I Z ' 2 1 g . 1 I I I - - A I I I I I I REFERENCES KR Kozlowski and P. Dutkiewicz, Experimental identifi-cation of parameters for a class of geared robots, Robotica, vol. 14, no. 5, pp. ...

Tsinghua Science & Technology, 2005

This paper addresses the problem of collecting sensoring information from wireless sensor network... more This paper addresses the problem of collecting sensoring information from wireless sensor networks using mobile robots. We consider that sensors may interact with each other only to maintain the network topology. Because transmitting sensoring data over the network to a remote base is a very power consuming operation, we deploy mobile robots through the sensor field in order to collect such information. We present a multi-target, dynamical, potential field strategy where a robot is attracted to the sensors that have less remaining data storage capacity. Moreover, the robot is also attracted to other sensors in its path without compromising its principal mission. Our controllers guarantee the robot will never get stuck in undesirable local minima. Simulated examples with a single robot collecting data in a sensor field illustrate the elegancy of the methodology.

This paper presents the ongoing development of a computer vision based human-robot interface. We ... more This paper presents the ongoing development of a computer vision based human-robot interface. We propose the use of efficient, well known computer vision algorithms and context sensitive language recognition tools. In order to be robust to the common misinterpretation in vision based sign recognition, we subdivide a robot command into small visual symbols, easier to identify than a complex one, and apply a finite-state machine to interpret a sequence of such symbols. Since the output of our vision system is stochastic we map this machine to a Markov chain and use it to process the vision events and recognize a command. Preliminary experimental results suggest that this methodology will yield robust recognition with low ocurrence of false positives.

This paper presents a vector field based methodology for coverage of curves in threedimensional s... more This paper presents a vector field based methodology for coverage of curves in threedimensional spaces with large groups of fixed-wing aerial robots. We model the robots as spheres with an associated nonholonomic kinematic model with minimum forward speed constraint. Under certain assumptions we guarantee that the robots will converge to and circulate along a desired curve avoiding inter-robot collisions while satisfying the constraints.

Pattern Recognition Letters, 2011

This paper presents a robust technique for temporally aligning multiple video sequences that have... more This paper presents a robust technique for temporally aligning multiple video sequences that have no spatial overlap between their fields of view. It is assumed that (i) a moving target with known trajectory is viewed by all cameras at non-overlapping periods in time, (ii) the target trajectory is estimated with a limited error at a constant sampling rate, and (iii) the sequences are recorded by stationary cameras with constant frame rates and fixed intrinsic and extrinsic parameters. The proposed approach reduces the problem of synchronizing N non-overlapping sequences to the problem of robustly estimating a single line from a set of appropriately-generated points in R Nþ1 . This line describes all temporal relations between the N sequences and the moving target. Our technique can handle arbitrarily-large misalignments between the sequences and does not require any a priori information about their temporal relations. Experimental results with real-world and synthetic sequences demonstrate that our method can accurately align the videos.

2013 International Conference on Unmanned Aircraft Systems (ICUAS), 2013

ABSTRACT This paper addresses the ongoing process of development of a small hand-held multiple un... more ABSTRACT This paper addresses the ongoing process of development of a small hand-held multiple unmanned aerial vehicle platform for surveillance and monitoring. The project cover all phases of development, from aerodynamic design and mechanical assembly, through fine tuning low level control loops and design of an attitude and heading reference system, up to implementation of navigation algorithms and finally flight testing. Commercial hardware is used to speed up development, allowing the team responsible for implementing the navigation algorithms to execute and test while the team responsible for the aerodynamics and electronics can design and compare results.

IEEE Transactions on Intelligent Transportation Systems, 2014

This paper presents the model identification and the velocity control of an autonomous car. The c... more This paper presents the model identification and the velocity control of an autonomous car. The control system was designed so that the car is controlled at low speeds, where the main applications for the vehicle's autonomous operations include parking and urban adaptive cruise control. A longitudinal model of the car was used in the control loop to compensate the nonlinear behavior of its dynamics. Since the determination of the vehicle's model is a difficult step in the design of model-based controllers, the main contribution of this paper is the use of an empirically determined model to this end. In this paper, the structure of the model was conceived from the car's physics equations, but its parameters were estimated using data-based identification techniques. An important contribution of this paper is the fact that, although the model is strictly linear, we can change its parameters as a function of the operation point of the vehicle to represent the engine's and the transmission's nonlinear behaviors. Moreover, in this paper, we propose a way to include changes in the longitudinal dynamics caused by the automatic gear shifting. The validation of the proposed controller was conducted by computer simulations and real-world experiments.

2008 XXI Brazilian Symposium on Computer Graphics and Image Processing, 2008

This paper describes a method to estimate the temporal alignment between N unsynchronized video s... more This paper describes a method to estimate the temporal alignment between N unsynchronized video sequences captured by cameras with non-overlapping fields of view. The sequences are recorded by stationary video cameras, with fixed intrinsic and extrinsic parameters. The proposed approach reduces the problem of synchronizing N nonoverlapping sequences to the robust estimation of a single line in R N +1 . This line captures all temporal relations between the sequences and a moving sensor in the scene, whose locations in the world coordinate system may be estimated at a constant sampling rate. Experimental results with real-world sequences show that our method can accurately align the videos.