Leonardo Olivi - Academia.edu (original) (raw)
Papers by Leonardo Olivi
2014 11th IEEE/IAS International Conference on Industry Applications, 2014
There are several methods to control robot's trajectories. The potential fields technique is one ... more There are several methods to control robot's trajectories. The potential fields technique is one of the simplest algorithms that require less computational resources. This work presents a modified version of the potential fields method using variable charge and adapted attractive fields that allows the robot to achieve the goal in dynamical and complex environment which the original approach is not able to solve. The algorithm has been validated using the MobileSim simulator together with Matlab. The results prove the algorithm efficiency in schemes with multiple local minima, goal close to obstacles and less oscillation in narrow passages. This control method can be used in industrial applications such as automatic forklift operation, robotic manipulators and wheeled robots. I.
2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing, 2011
Abstract This paper presents the design, implementation, and evaluation of a cloud computing envi... more Abstract This paper presents the design, implementation, and evaluation of a cloud computing environment for networked robotics. The environment aims to support distributed robotics applications that require large shares of computing resources and very low ...
The field of Assistive Robotics is concerned with technologies for mobility aids for people who h... more The field of Assistive Robotics is concerned with technologies for mobility aids for people who have physical impairments. This work proposes a motion control system that recognizes narrow passages in unknown environments and moves a robot through them without the support of Simultaneous Localization And Mapping (SLAM) techniques. It focuses on intelligent wheelchairs, which commonly have large dimensions for typical home and office passages, proving to be a challenge to motion controllers which aim at guaranteeing both the safety and the comfort of the users. The proposed motion controller identifies the available accesses in the environment and calculates the safest route for the robot through them. A nonlinear controller navigates the robot with the help of a Kalman Filter, which locates the robot and completes the online path planning task. Simulated and experimental results are presented to validate the proposed motion control system. Keywords— Assistive mobile robots, Shared c...
— An individual’s motor ability, such as walking, can be easily compromised by a wide range of fa... more — An individual’s motor ability, such as walking, can be easily compromised by a wide range of factors, such as traumatic spinal cord injury, cerebral vascular accidents, limb amputations, multiple sclerosis, etc. Some technologies can be applied to assist these individuals improving their mobility and quality of life. Such technologies are often referred to as assistive technologies and one fitting this scenario is mobile robotics. This paper proposes a lightweight sEMG (surface Electromyography) control based approach aimed for assistive systems where all signal processing and robot’s control is embedded on a Android based cellphone. The system also provides a simple collision avoidance based on the velocity control upon obstacle detection.
The Settlement Price of Differences (SPD) is a variable used to determinate the value to be settl... more The Settlement Price of Differences (SPD) is a variable used to determinate the value to be settled in the Chamber of Electric Energy Commercialization (CEEC) relative to the difference between the amount of energy that has been supplied to a company and the amount that had been contracted. This variable changes on a weekly basis and is calculated based on statistical and mathematical models of optimization, and therefore its behavior is highly non-linear. This paper predicts the SPD value one week ahead of time using an LSTM recurrent neural network architecture and a correction filter, avoiding the most common pitfalls of using recurrent networks in time series forecasting. The results show how dealing with the right input variables leads to a trustworthy prediction of the SPD. Resumo: O Preço de Liquidação das Diferenças (PLD) é uma variável utilizada para determinar o valor a ser cobrado pelos volumes de energia que serão liquidados na CCEE (Câmara de Comercialização de Energia ...
A mobilidade e uma competencia humana extremamente valiosa, e pode ser perdida por diversas razoe... more A mobilidade e uma competencia humana extremamente valiosa, e pode ser perdida por diversas razoes, tais como traumas na coluna vertebral, acidentes vasculares cerebrais, dentre outras. Algumas tecnologias desenvolvidas para as areas medicas, como eletroencefalografia e eletromiografia, podem ser empregadas no desenvolvimento de Interfaces Humano-Maquina (Human-Machine Interface, ou, HMI) com o objetivo de permitir que pessoas com capacidades motoras severamente comprometidas possam comunicar e operar os mais diversos equipamentos. Assim, esses usuarios podem conduzir robos moveis por meio de uma HMI adaptada para suas capacidades motoras e cognitivas. Entretanto, essas interfaces apresentam erros na identificacao da acao pretendida pelo usuario, os quais comprometem sobremaneira a experiencia desse usuario na interacao com o mundo exterior. Para o caso dos robos moveis assistivos, o conceito de controle compartilhado (shared control) foi concebido para compensar as taxas de erros d...
2018 Simposio Brasileiro de Sistemas Eletricos (SBSE), 2018
This paper presents the short-term prediction of the Settlement Price of Differences, which is th... more This paper presents the short-term prediction of the Settlement Price of Differences, which is the price of electricity in the Brazilian short-term market, published weekly by the Electric Energy Trading Chamber, through an artificial intelligence tool. This strategy combines an artificial neural network with autoregressive techniques in order to provide the network with the learning capacity for dynamic stochastic systems. The recurrent neural network is used for the prediction of multiple steps in the future for the time series of the Settlement Price of Differences, which has great variability with unequal energy dispatch characteristics. The results show that the proposed network has the ability to predict upward and downward price trends, as well as the difference between sub region prices, as an attractive tool to aid in the planning and reduction of energy purchase risks.
A trend in today’s mobile robotics is to perform the control of mobile robots in a distributed fa... more A trend in today’s mobile robotics is to perform the control of mobile robots in a distributed fashion. This control scheme requires a wireless communication network connecting the robot to the other existing devices in the environment. WiFi and Bluetooth are examples of such networks. Ad-hoc networks such as wireless sensor networks (WSN) can be deployed instantly and offer a wide coverage by employing a large number of communicating nodes. In addition to provide a communication link to the robots, a WSN can aid the robot’s navigation, localization, and also enhance its sensory capabilities. This paper presents a network architecture for supporting the control and communication of mobile robots through WSNs.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Computer Science and Robotics are becoming strong and consistent methods in teaching Science, Tec... more Computer Science and Robotics are becoming strong and consistent methods in teaching Science, Technology, Engineering, Arts and Mathematics (STEAM) in schools all over the world. In this sense, robots have been developed for schools and teaching, in several ways of configurations. There are many ways of locomotion for mobile robots, mainly based in wheels and mechanical legs. Unfortunately, there are few legged robots available in the market, and to the best of our knowledge there isn't a commercial model made in Brazil, which makes it more expensive to import. This paper proposes the development of a low cost fully functional hexapod, for educational purposes, describing its hardware and software, and also, showing control tests. The developed hexapod was conceived with 3D-printed legs and low-cost servomotors, that can be easily acquired and assembled. A transparent and effective API to control its movements, LEDs and other functionalities was developed to provide a quick learning curve for the user. The Hexapod's Kinematics chain and its motion strategy are discussed in depth, with a pseudo-Inverse Jacobian method to execute the legs Inverse Kinematic, allied with quintic polynomial function servo planner, successfully leading to a smooth movement to each hexapod's leg. The goal is to produce a low-cost, 3D printable robot for school education.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Anais do 14º Simpósio Brasileiro de Automação Inteligente
The Settlement Price of Differences (SPD) is one of the main variables in the Electric Energy Fre... more The Settlement Price of Differences (SPD) is one of the main variables in the Electric Energy Free Market, and is disclosed by the Electric Energy Trading Chamber. Its behavior is nonlinear and contaminated by random variables. For any market participant, knowing their behavior is imperative to define their energy strategies. This work consists in the development of a model for prediction of SPD in the Brazilian Short-Term Market. The model is based on Artificial Neural Networks delayed in time with Levenberg-Marquardt method with Momentum. As input variables, SPD and its explanatory variables were used, Subsystem Induced Natural Energy, Energy Exchange and Stored Energy. As an output, the future SPD is obtained one week ahead. The results show an efficient methodology for the prediction, with the monitoring of its tendencies. Resumo: O Preço de Liquidação das Diferenças (PLD) é uma das principais variáveis no Mercado Livre de Energia Elétrica, e é divulgada pela Câmara de Comercialização de Energia Elétrica. Seu comportamento é não-linear e contaminado por variáveis aleatórias. Para qualquer participante do mercado, conhecer seu comportamento é imperativo para definir suas estratégias energéticas. Este trabalho consiste no desenvolvimento de um modelo para predição do PLD no Mercado de Curto Prazo Brasileiro. O modelo é baseado em Redes Neurais Artificiais atrasadas no tempo com método de Levenberg-Marquardt com Momentum. Como variáveis de entrada foram utilizados o PLD e suas variáveis explanatórias, a Energia Natural Afluente por Subsistema, o Intercâmbio de Energia e a Energia Armazenada. Como saída, obtêm-se o PLD futuro uma semana afrente. Os resultados mostram uma eficiente metodologia para a predição, com o acompanhamento de suas tendências.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
The medical area in conjunction with engineering have developed techniques that can create Human-... more The medical area in conjunction with engineering have developed techniques that can create Human-Machine Interfaces, facilitating the interaction between equipment and people with disabilities. The use of mobile robots associated with assistive technologies can restore the mobility of these people. These interfaces have inherent classification errors and thus require shared controls between the machine and the human in order to supervise navigation and compensate for the classification errors inherent in those interfaces. In this article we propose the shared control of a wheelchair using fuzzy logic, capable of adapting to any type of environment, making navigation safe, accurate and free of collision risks. Resumo: A área médica em conjunto com a engenharia tem desenvolvido técnicas que podem criar Interfaces Humano-Máquina, facilitando a interação entre equipamentos e pessoas portadoras de deficiências. O uso de robôs móveis associados a tecnologias assistivas podem recuperar a mobilidade dessas pessoas. Essas interfaces possuem erros de classificação inerentes, e, assim, necessitam-se de controles compartilhados entre a máquina e o humano, de modo a supervisionar a navegação e compensar os erros de classificação inerentes a essas interfaces. Neste artigo é proposto o controle compartilhado de uma cadeira de rodas utilizando lógica fuzzy, capaz de se adaptar a quaisquer tipos de ambientes, possibilitando uma navegação, segura, acurada e livre de riscos de colisão.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Despite the rapid development of the robotics' field, overall the equipment's employed are still ... more Despite the rapid development of the robotics' field, overall the equipment's employed are still expensive or even inaccessible, therefore the ground truth and precise tests must be taken in simulation. Although several simulators are available, in most cases these tools are complicated and require a steep learning curve. This paper presents the development of a robotic simulator which is cross-platform, lightweight, language agnostic, able to simulate differential mobile robots. This simulator takes into account environmental and robot variables, such as constructive and random errors, in a simple way of configuring and accessing. Thus the effort is applied in the required task instead of simulation construction, providing a fast and accurate simulator. The simulator follows the cross-platform paradigm and is compatible with several programming languages through a external binding system. Some tests were performed using path planning algorithms to evaluate the simulator and have shown positive results. The main aim of this work is to produce a simulator ready-to-go in educational environments.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Robot soccer is a dynamic, versatile and real-time execution environment, so the knowledge of the... more Robot soccer is a dynamic, versatile and real-time execution environment, so the knowledge of the position of the elements of the game in the field, such as robots, ball, field lines, goals, among others, becomes essential to have play and reach the goal goal. In this context, tracking the ball is an important tool to know the position of the ball in the field and predictions of future positions contributes to the efficiency of the robot in its trajectory of chasing the ball. In the present work the tracking of the ball was developed through the Kalman Filter, by means of the modeling of the equations that represent the position and speed of the ball, as well as its validation. The results show that the method developed in this work obtains accurate predictions, amplifying the strategies for the game. Resumo: O futebol de robôsé um ambiente dinâmico, versátil e de execução em tempo real, logo, o conhecimento da posição dos elementos do jogo em campo, como robôs, bola, linhas de campo, gols, entre outros, se faz essencial para se ter domínio do jogo e atingir o objetivo de fazer o gol. Nesse contexto, o rastreamento da bolaé uma importante ferramenta para se conhecer a posição da mesma no campo e previsões de posições futuras contribui na eficiência do robô na trajetória do mesmo de perseguir a bola. No presente trabalho desenvolveu-se o rastreamento da bola através do Filtro de Kalman, por meio da modelagem das equações que representam a posição e velocidade da bola, bem como, a validação das mesmas através de simulações. Os resultados mostram que o método desenvolvido neste trabalho obtém predições acuradas, ampliando as estratégias de jogo.
Lecture Notes in Electrical Engineering, 2016
2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2015
This paper explores the use of hybrid modeling and predictive control to manage the direct inject... more This paper explores the use of hybrid modeling and predictive control to manage the direct injection of herbicide into a carrier stream. The objective is to design a control law that generates the inputs for a positive displacement piston pump used to inject the herbicide into the carrier to operate in an anticipative or non-anticipative mode according to the increase or not of the rate of application, respectively. The references are generated on line at each sampling time based on the vehicle ground speed and system modes. The control configuration proposed allows the errors associated to the transport delay to be reduced.
2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), 2013
ABSTRACT Technologies such as Brain-Computer Interface (BCI) and Electromyography (EMG) allow peo... more ABSTRACT Technologies such as Brain-Computer Interface (BCI) and Electromyography (EMG) allow people with limited mobility to interact with devices such as computers, home appliances and mobile robots. However, low cost BCI and EMG have not matured yet. Moreover, these technologies present relative low signal-to-noise ratio and classification accuracy. In case of employing BCI or EMG to manually control a mobile robot, a shared control must be inserted in the loop control to compensate misinterpreted commands. This paper presents a novel shared control approach based on vector fields for the manual navigation of assistive mobile robots. Unlike other approaches which take full control of the robot in certain situations, this technique allows full control to the user. Also, this approach reduces interventions to correct the navigation route caused by wrong classification of commands issued by the user. Results show that it is a simple, fast and effective technique.
ABSTRACT The main objective of this paper is to model and simulate a controlled injection system ... more ABSTRACT The main objective of this paper is to model and simulate a controlled injection system with variable rates for herbicide spraying over infested crops by weeds. This system avoids waste of material and protects the environment against the pollution caused by the excess of the toxic products dispersed.
2014 11th IEEE/IAS International Conference on Industry Applications, 2014
There are several methods to control robot's trajectories. The potential fields technique is one ... more There are several methods to control robot's trajectories. The potential fields technique is one of the simplest algorithms that require less computational resources. This work presents a modified version of the potential fields method using variable charge and adapted attractive fields that allows the robot to achieve the goal in dynamical and complex environment which the original approach is not able to solve. The algorithm has been validated using the MobileSim simulator together with Matlab. The results prove the algorithm efficiency in schemes with multiple local minima, goal close to obstacles and less oscillation in narrow passages. This control method can be used in industrial applications such as automatic forklift operation, robotic manipulators and wheeled robots. I.
2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing, 2011
Abstract This paper presents the design, implementation, and evaluation of a cloud computing envi... more Abstract This paper presents the design, implementation, and evaluation of a cloud computing environment for networked robotics. The environment aims to support distributed robotics applications that require large shares of computing resources and very low ...
The field of Assistive Robotics is concerned with technologies for mobility aids for people who h... more The field of Assistive Robotics is concerned with technologies for mobility aids for people who have physical impairments. This work proposes a motion control system that recognizes narrow passages in unknown environments and moves a robot through them without the support of Simultaneous Localization And Mapping (SLAM) techniques. It focuses on intelligent wheelchairs, which commonly have large dimensions for typical home and office passages, proving to be a challenge to motion controllers which aim at guaranteeing both the safety and the comfort of the users. The proposed motion controller identifies the available accesses in the environment and calculates the safest route for the robot through them. A nonlinear controller navigates the robot with the help of a Kalman Filter, which locates the robot and completes the online path planning task. Simulated and experimental results are presented to validate the proposed motion control system. Keywords— Assistive mobile robots, Shared c...
— An individual’s motor ability, such as walking, can be easily compromised by a wide range of fa... more — An individual’s motor ability, such as walking, can be easily compromised by a wide range of factors, such as traumatic spinal cord injury, cerebral vascular accidents, limb amputations, multiple sclerosis, etc. Some technologies can be applied to assist these individuals improving their mobility and quality of life. Such technologies are often referred to as assistive technologies and one fitting this scenario is mobile robotics. This paper proposes a lightweight sEMG (surface Electromyography) control based approach aimed for assistive systems where all signal processing and robot’s control is embedded on a Android based cellphone. The system also provides a simple collision avoidance based on the velocity control upon obstacle detection.
The Settlement Price of Differences (SPD) is a variable used to determinate the value to be settl... more The Settlement Price of Differences (SPD) is a variable used to determinate the value to be settled in the Chamber of Electric Energy Commercialization (CEEC) relative to the difference between the amount of energy that has been supplied to a company and the amount that had been contracted. This variable changes on a weekly basis and is calculated based on statistical and mathematical models of optimization, and therefore its behavior is highly non-linear. This paper predicts the SPD value one week ahead of time using an LSTM recurrent neural network architecture and a correction filter, avoiding the most common pitfalls of using recurrent networks in time series forecasting. The results show how dealing with the right input variables leads to a trustworthy prediction of the SPD. Resumo: O Preço de Liquidação das Diferenças (PLD) é uma variável utilizada para determinar o valor a ser cobrado pelos volumes de energia que serão liquidados na CCEE (Câmara de Comercialização de Energia ...
A mobilidade e uma competencia humana extremamente valiosa, e pode ser perdida por diversas razoe... more A mobilidade e uma competencia humana extremamente valiosa, e pode ser perdida por diversas razoes, tais como traumas na coluna vertebral, acidentes vasculares cerebrais, dentre outras. Algumas tecnologias desenvolvidas para as areas medicas, como eletroencefalografia e eletromiografia, podem ser empregadas no desenvolvimento de Interfaces Humano-Maquina (Human-Machine Interface, ou, HMI) com o objetivo de permitir que pessoas com capacidades motoras severamente comprometidas possam comunicar e operar os mais diversos equipamentos. Assim, esses usuarios podem conduzir robos moveis por meio de uma HMI adaptada para suas capacidades motoras e cognitivas. Entretanto, essas interfaces apresentam erros na identificacao da acao pretendida pelo usuario, os quais comprometem sobremaneira a experiencia desse usuario na interacao com o mundo exterior. Para o caso dos robos moveis assistivos, o conceito de controle compartilhado (shared control) foi concebido para compensar as taxas de erros d...
2018 Simposio Brasileiro de Sistemas Eletricos (SBSE), 2018
This paper presents the short-term prediction of the Settlement Price of Differences, which is th... more This paper presents the short-term prediction of the Settlement Price of Differences, which is the price of electricity in the Brazilian short-term market, published weekly by the Electric Energy Trading Chamber, through an artificial intelligence tool. This strategy combines an artificial neural network with autoregressive techniques in order to provide the network with the learning capacity for dynamic stochastic systems. The recurrent neural network is used for the prediction of multiple steps in the future for the time series of the Settlement Price of Differences, which has great variability with unequal energy dispatch characteristics. The results show that the proposed network has the ability to predict upward and downward price trends, as well as the difference between sub region prices, as an attractive tool to aid in the planning and reduction of energy purchase risks.
A trend in today’s mobile robotics is to perform the control of mobile robots in a distributed fa... more A trend in today’s mobile robotics is to perform the control of mobile robots in a distributed fashion. This control scheme requires a wireless communication network connecting the robot to the other existing devices in the environment. WiFi and Bluetooth are examples of such networks. Ad-hoc networks such as wireless sensor networks (WSN) can be deployed instantly and offer a wide coverage by employing a large number of communicating nodes. In addition to provide a communication link to the robots, a WSN can aid the robot’s navigation, localization, and also enhance its sensory capabilities. This paper presents a network architecture for supporting the control and communication of mobile robots through WSNs.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Computer Science and Robotics are becoming strong and consistent methods in teaching Science, Tec... more Computer Science and Robotics are becoming strong and consistent methods in teaching Science, Technology, Engineering, Arts and Mathematics (STEAM) in schools all over the world. In this sense, robots have been developed for schools and teaching, in several ways of configurations. There are many ways of locomotion for mobile robots, mainly based in wheels and mechanical legs. Unfortunately, there are few legged robots available in the market, and to the best of our knowledge there isn't a commercial model made in Brazil, which makes it more expensive to import. This paper proposes the development of a low cost fully functional hexapod, for educational purposes, describing its hardware and software, and also, showing control tests. The developed hexapod was conceived with 3D-printed legs and low-cost servomotors, that can be easily acquired and assembled. A transparent and effective API to control its movements, LEDs and other functionalities was developed to provide a quick learning curve for the user. The Hexapod's Kinematics chain and its motion strategy are discussed in depth, with a pseudo-Inverse Jacobian method to execute the legs Inverse Kinematic, allied with quintic polynomial function servo planner, successfully leading to a smooth movement to each hexapod's leg. The goal is to produce a low-cost, 3D printable robot for school education.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Anais do 14º Simpósio Brasileiro de Automação Inteligente
The Settlement Price of Differences (SPD) is one of the main variables in the Electric Energy Fre... more The Settlement Price of Differences (SPD) is one of the main variables in the Electric Energy Free Market, and is disclosed by the Electric Energy Trading Chamber. Its behavior is nonlinear and contaminated by random variables. For any market participant, knowing their behavior is imperative to define their energy strategies. This work consists in the development of a model for prediction of SPD in the Brazilian Short-Term Market. The model is based on Artificial Neural Networks delayed in time with Levenberg-Marquardt method with Momentum. As input variables, SPD and its explanatory variables were used, Subsystem Induced Natural Energy, Energy Exchange and Stored Energy. As an output, the future SPD is obtained one week ahead. The results show an efficient methodology for the prediction, with the monitoring of its tendencies. Resumo: O Preço de Liquidação das Diferenças (PLD) é uma das principais variáveis no Mercado Livre de Energia Elétrica, e é divulgada pela Câmara de Comercialização de Energia Elétrica. Seu comportamento é não-linear e contaminado por variáveis aleatórias. Para qualquer participante do mercado, conhecer seu comportamento é imperativo para definir suas estratégias energéticas. Este trabalho consiste no desenvolvimento de um modelo para predição do PLD no Mercado de Curto Prazo Brasileiro. O modelo é baseado em Redes Neurais Artificiais atrasadas no tempo com método de Levenberg-Marquardt com Momentum. Como variáveis de entrada foram utilizados o PLD e suas variáveis explanatórias, a Energia Natural Afluente por Subsistema, o Intercâmbio de Energia e a Energia Armazenada. Como saída, obtêm-se o PLD futuro uma semana afrente. Os resultados mostram uma eficiente metodologia para a predição, com o acompanhamento de suas tendências.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
The medical area in conjunction with engineering have developed techniques that can create Human-... more The medical area in conjunction with engineering have developed techniques that can create Human-Machine Interfaces, facilitating the interaction between equipment and people with disabilities. The use of mobile robots associated with assistive technologies can restore the mobility of these people. These interfaces have inherent classification errors and thus require shared controls between the machine and the human in order to supervise navigation and compensate for the classification errors inherent in those interfaces. In this article we propose the shared control of a wheelchair using fuzzy logic, capable of adapting to any type of environment, making navigation safe, accurate and free of collision risks. Resumo: A área médica em conjunto com a engenharia tem desenvolvido técnicas que podem criar Interfaces Humano-Máquina, facilitando a interação entre equipamentos e pessoas portadoras de deficiências. O uso de robôs móveis associados a tecnologias assistivas podem recuperar a mobilidade dessas pessoas. Essas interfaces possuem erros de classificação inerentes, e, assim, necessitam-se de controles compartilhados entre a máquina e o humano, de modo a supervisionar a navegação e compensar os erros de classificação inerentes a essas interfaces. Neste artigo é proposto o controle compartilhado de uma cadeira de rodas utilizando lógica fuzzy, capaz de se adaptar a quaisquer tipos de ambientes, possibilitando uma navegação, segura, acurada e livre de riscos de colisão.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Despite the rapid development of the robotics' field, overall the equipment's employed are still ... more Despite the rapid development of the robotics' field, overall the equipment's employed are still expensive or even inaccessible, therefore the ground truth and precise tests must be taken in simulation. Although several simulators are available, in most cases these tools are complicated and require a steep learning curve. This paper presents the development of a robotic simulator which is cross-platform, lightweight, language agnostic, able to simulate differential mobile robots. This simulator takes into account environmental and robot variables, such as constructive and random errors, in a simple way of configuring and accessing. Thus the effort is applied in the required task instead of simulation construction, providing a fast and accurate simulator. The simulator follows the cross-platform paradigm and is compatible with several programming languages through a external binding system. Some tests were performed using path planning algorithms to evaluate the simulator and have shown positive results. The main aim of this work is to produce a simulator ready-to-go in educational environments.
Anais do 14º Simpósio Brasileiro de Automação Inteligente
Robot soccer is a dynamic, versatile and real-time execution environment, so the knowledge of the... more Robot soccer is a dynamic, versatile and real-time execution environment, so the knowledge of the position of the elements of the game in the field, such as robots, ball, field lines, goals, among others, becomes essential to have play and reach the goal goal. In this context, tracking the ball is an important tool to know the position of the ball in the field and predictions of future positions contributes to the efficiency of the robot in its trajectory of chasing the ball. In the present work the tracking of the ball was developed through the Kalman Filter, by means of the modeling of the equations that represent the position and speed of the ball, as well as its validation. The results show that the method developed in this work obtains accurate predictions, amplifying the strategies for the game. Resumo: O futebol de robôsé um ambiente dinâmico, versátil e de execução em tempo real, logo, o conhecimento da posição dos elementos do jogo em campo, como robôs, bola, linhas de campo, gols, entre outros, se faz essencial para se ter domínio do jogo e atingir o objetivo de fazer o gol. Nesse contexto, o rastreamento da bolaé uma importante ferramenta para se conhecer a posição da mesma no campo e previsões de posições futuras contribui na eficiência do robô na trajetória do mesmo de perseguir a bola. No presente trabalho desenvolveu-se o rastreamento da bola através do Filtro de Kalman, por meio da modelagem das equações que representam a posição e velocidade da bola, bem como, a validação das mesmas através de simulações. Os resultados mostram que o método desenvolvido neste trabalho obtém predições acuradas, ampliando as estratégias de jogo.
Lecture Notes in Electrical Engineering, 2016
2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), 2015
This paper explores the use of hybrid modeling and predictive control to manage the direct inject... more This paper explores the use of hybrid modeling and predictive control to manage the direct injection of herbicide into a carrier stream. The objective is to design a control law that generates the inputs for a positive displacement piston pump used to inject the herbicide into the carrier to operate in an anticipative or non-anticipative mode according to the increase or not of the rate of application, respectively. The references are generated on line at each sampling time based on the vehicle ground speed and system modes. The control configuration proposed allows the errors associated to the transport delay to be reduced.
2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI), 2013
ABSTRACT Technologies such as Brain-Computer Interface (BCI) and Electromyography (EMG) allow peo... more ABSTRACT Technologies such as Brain-Computer Interface (BCI) and Electromyography (EMG) allow people with limited mobility to interact with devices such as computers, home appliances and mobile robots. However, low cost BCI and EMG have not matured yet. Moreover, these technologies present relative low signal-to-noise ratio and classification accuracy. In case of employing BCI or EMG to manually control a mobile robot, a shared control must be inserted in the loop control to compensate misinterpreted commands. This paper presents a novel shared control approach based on vector fields for the manual navigation of assistive mobile robots. Unlike other approaches which take full control of the robot in certain situations, this technique allows full control to the user. Also, this approach reduces interventions to correct the navigation route caused by wrong classification of commands issued by the user. Results show that it is a simple, fast and effective technique.
ABSTRACT The main objective of this paper is to model and simulate a controlled injection system ... more ABSTRACT The main objective of this paper is to model and simulate a controlled injection system with variable rates for herbicide spraying over infested crops by weeds. This system avoids waste of material and protects the environment against the pollution caused by the excess of the toxic products dispersed.