Vinicius Goncalves - Academia.edu (original) (raw)

Uploads

Papers by Vinicius Goncalves

Research paper thumbnail of Motion Planning of Mobile Robots in Indoor Topological Environments using Partially Observable Markov Decision Process

IEEE Latin America Transactions, 2021

Deterministic motion planners perform well in simulated environments, where sensors and actuators... more Deterministic motion planners perform well in simulated environments, where sensors and actuators are perfect. However, these assumptions are restrictive and consequently motion planning will have poor performance if applied to real robotic systems (or a more realistic simulator), as they are inherently fraught with uncertainty. In most real robotic systems, states cannot be directly observed, and the results of the actions performed by the robots are uncertain. Thus, the robot must make use of a new class of planners that take into account system uncertainties when making a decision. In the present work, the Partially Observable Markov Decision Process is presented as an alternative to solve problems immersed in uncertainties, selecting optimal actions aiming to perform a given task. The contribution of this article is to implement the Partially Observable Markov Decision Process using greedy optimization, which has considerably simplified the decision-making problem for uncertain environments. This article also presents new ways to determine the parameters of the Partially Observable Markov Decision Process. The aforementioned tooling was applied in a system to control the actions of a real robot that navigates in a indoor topological living space with ambiguity of informations.

Research paper thumbnail of Stable-by-Design Kinematic Control Based on Optimization

IEEE Transactions on Robotics, 2020

This paper presents a new kinematic control paradigm for redundant robots based on optimization. ... more This paper presents a new kinematic control paradigm for redundant robots based on optimization. The general approach takes into account convex objective functions with inequality constraints and a specific equality constraint resulting from a Lyapunov function, which ensures closed-loop stability by design. Furthermore, we tackle an important particular case by using a convex combination of quadratic and l1-norm objective functions, making possible for the designer to choose different degrees of sparseness and smoothness in the control inputs. We provide a pseudo-analytical solution to this optimization problem and validate the approach by controlling the center of mass of the humanoid robot HOAP3.

Research paper thumbnail of Parsimonious Kinematic Control of Highly Redundant Robots

IEEE Robotics and Automation Letters, 2016

When a robot is highly redundant in comparison to the task to be executed, current control techni... more When a robot is highly redundant in comparison to the task to be executed, current control techniques are not "economic" in the sense that they demand, most of the time unnecessarily, all the joints to move. Such behavior can be undesirable for some applications. In this direction, this work proposes a new control paradigm based on linear programming that intrinsically provides a parsimonious control strategy, that is, one in which few joints move. In addition to a formal stability proof, the paper presents simulation and experimental results on the HOAP-3 humanoid robot. Finally, a comparison is made with a least-square method based on the pseudoinverse of the task Jacobian, showing that the proposed method indeed uses fewer joints than the classic one.

Research paper thumbnail of Controle de um robô móvel em um galpão de estoque utilizando Processo de Decisão de Markov Parcialmente Observável

Anais do 14º Simpósio Brasileiro de Automação Inteligente, 2019

In most robotic systems states can not be directly observed, and there is uncertainty as to the o... more In most robotic systems states can not be directly observed, and there is uncertainty as to the outcome of a robot's decision making. POMDP's are presented as an alternative to solve problems immersed in uncertainties, selecting actions to accomplish a given task. In this work, it was simulated a system of locating and controlling the actions of a robot that moves through a warehouse. The results of the experiments show that the POMDP presents robustness and efficiency to determine the control actions of the robot. Resumo: Na maioria dos sistemas robóticos os estados não podem ser diretamente observados, e há incerteza quanto ao resultado da tomada de decisão de um robô. POMDP's são apresentados como alternativa para solucionar problemas imersos em incertezas, selecionando ações com objetivo de realizar uma dada tarefa. Neste trabalho, foi simulado um sistema de localização e controle das ações de um robô que se locomove por um galpão utilizado para estocagem. Os resultados dos experimentos mostram que o POMDP apresenta robustez e eficiência para determinar as ações de controle do robô.

Research paper thumbnail of Motion Planning of Mobile Robots in Indoor Topological Environments using Partially Observable Markov Decision Process

IEEE Latin America Transactions, 2021

Deterministic motion planners perform well in simulated environments, where sensors and actuators... more Deterministic motion planners perform well in simulated environments, where sensors and actuators are perfect. However, these assumptions are restrictive and consequently motion planning will have poor performance if applied to real robotic systems (or a more realistic simulator), as they are inherently fraught with uncertainty. In most real robotic systems, states cannot be directly observed, and the results of the actions performed by the robots are uncertain. Thus, the robot must make use of a new class of planners that take into account system uncertainties when making a decision. In the present work, the Partially Observable Markov Decision Process is presented as an alternative to solve problems immersed in uncertainties, selecting optimal actions aiming to perform a given task. The contribution of this article is to implement the Partially Observable Markov Decision Process using greedy optimization, which has considerably simplified the decision-making problem for uncertain environments. This article also presents new ways to determine the parameters of the Partially Observable Markov Decision Process. The aforementioned tooling was applied in a system to control the actions of a real robot that navigates in a indoor topological living space with ambiguity of informations.

Research paper thumbnail of Stable-by-Design Kinematic Control Based on Optimization

IEEE Transactions on Robotics, 2020

This paper presents a new kinematic control paradigm for redundant robots based on optimization. ... more This paper presents a new kinematic control paradigm for redundant robots based on optimization. The general approach takes into account convex objective functions with inequality constraints and a specific equality constraint resulting from a Lyapunov function, which ensures closed-loop stability by design. Furthermore, we tackle an important particular case by using a convex combination of quadratic and l1-norm objective functions, making possible for the designer to choose different degrees of sparseness and smoothness in the control inputs. We provide a pseudo-analytical solution to this optimization problem and validate the approach by controlling the center of mass of the humanoid robot HOAP3.

Research paper thumbnail of Parsimonious Kinematic Control of Highly Redundant Robots

IEEE Robotics and Automation Letters, 2016

When a robot is highly redundant in comparison to the task to be executed, current control techni... more When a robot is highly redundant in comparison to the task to be executed, current control techniques are not "economic" in the sense that they demand, most of the time unnecessarily, all the joints to move. Such behavior can be undesirable for some applications. In this direction, this work proposes a new control paradigm based on linear programming that intrinsically provides a parsimonious control strategy, that is, one in which few joints move. In addition to a formal stability proof, the paper presents simulation and experimental results on the HOAP-3 humanoid robot. Finally, a comparison is made with a least-square method based on the pseudoinverse of the task Jacobian, showing that the proposed method indeed uses fewer joints than the classic one.

Research paper thumbnail of Controle de um robô móvel em um galpão de estoque utilizando Processo de Decisão de Markov Parcialmente Observável

Anais do 14º Simpósio Brasileiro de Automação Inteligente, 2019

In most robotic systems states can not be directly observed, and there is uncertainty as to the o... more In most robotic systems states can not be directly observed, and there is uncertainty as to the outcome of a robot's decision making. POMDP's are presented as an alternative to solve problems immersed in uncertainties, selecting actions to accomplish a given task. In this work, it was simulated a system of locating and controlling the actions of a robot that moves through a warehouse. The results of the experiments show that the POMDP presents robustness and efficiency to determine the control actions of the robot. Resumo: Na maioria dos sistemas robóticos os estados não podem ser diretamente observados, e há incerteza quanto ao resultado da tomada de decisão de um robô. POMDP's são apresentados como alternativa para solucionar problemas imersos em incertezas, selecionando ações com objetivo de realizar uma dada tarefa. Neste trabalho, foi simulado um sistema de localização e controle das ações de um robô que se locomove por um galpão utilizado para estocagem. Os resultados dos experimentos mostram que o POMDP apresenta robustez e eficiência para determinar as ações de controle do robô.