Danilo Hernani Perico

Centro Universitário FEI · Department of Computer Science

One of the goals of humanoid robot researchers is to develop a complete – in terms of hardware and software – artificial autonomous agent able to interact with humans and to act in the contemporary world, that is built for human beings. There has been an increasing number of humanoid robots in the last years, including Aldebaran’s NAO and Romeo, In...

This paper presents a qualitative approach for updating the particles used by Monte Carlo Localization (MCL) during a mobile robot localization procedure. The combination between MCL and qualitative data will be called, in this article, Hybrid Localization. The motivation of using qualitative data is to obtain a level of abstraction closer to the h...

This paper presents a humanoid robot framework, composed of a simulator and a telemetry interface. The framework is based on the Cross Architecture, and it is developed aiming for the RoboCup Soccer Humanoid League domain. A simulator is an important tool for testing cognitive algorithms without handling issues of real robots; furthermore, a simula...

Navigation is an essential ability for mobile agents to be completely autonomous and able to perform complex actions. However, the problem of navigation for agents with limited (or no) perception of the world, or devoid of a fully defined motion model, has received little attention from research in AI and Robotics. One way to tackle this problem is...

This paper investigates the use of Deep Reinforcement Learning (DRL) applied to the humanoid robot soccer environment, where a robot must learn from basic to complex skills while it interacts with the environment through images received by its own camera. To do so, the Dueling Double DQN algorithm is used: it receives the images from the robot's ca...

Este trabalho apresenta o conceito de Aprendizado por Reforço aplicado ao problema do pêndulo invertido preso a um robô móvel (problema conhecido como Cart Pole em inglês). Nesse problema, o robô deve aprender as melhores ações para manter o pêndulo em equilíbrio. Os algoritmos de Aprendizado por Reforço utilizados nesse projeto foram o Q-Learning,...

Object detection techniques that achieve state-of-the-art detection accuracy employ convolutional neural networks, implemented to have lower latency in graphics processing units. Some hardware systems, such as mobile robots, operate under constrained hardware situations, but still benefit from object detection capabilities. Multiple network models...

Navigation is an essential ability for mobile agents to be completely autonomous and able to perform complex actions. However, the problem of navigation for agents with limited (or no) perception of the world, or devoid of a fully defined motion model, has received little attention from research in AI and Robotics. One way to tackle this problem is...

Object detection techniques that achieve state-of-the-art detection accuracy employ convolutional neural networks, implemented to have optimal performance in graphics processing units. Some hardware systems, such as mobile robots, operate under constrained hardware situations, but still benefit from object detection capabilities. Multiple network m...

Recent advances in deep learning point towards the use of computer vision systems based on Deep Neural Networks (DNNs). However, these network architectures are optimized to be executed in specialized hardware, such as in computers with Graphics Processing Units (GPU). Such hardware is rarely available in embedded computers, for instance, those use...

Este artigo apresenta o estudo e explicação detalhados, por meio de vídeos didáticos sintetizados, dos sistemas de software e hardware atuantes nos robôs do time RoboFEI. Estes softwares e hardwares foram desenvolvidos no Centro Universitário FEI e são utilizados atualmente. O principal foco deste projeto é, por meio de videoaulas, disseminar o ens...

Humanoid robots use a gait pattern generator to control the servo motors during the gait preserving its dynamic balance. There are several gait generation techniques that have been developed for humanoid robots. The Darwin-OP robot uses a method to generate the gait pattern based on coupled oscillators that perform sinusoidal trajectories. However...

This paper proposes a new Case-Based Reasoning (CBR) approach, named Q-CBR, that uses Qualitative Spatial Reasoning theory to model, retrieve and reuse cases by means of spatial relations. Qualitative relations between objects, represented in terms of the EOPRA formalism, are stored as qualitative cases that are applied in the definition of new ret...

This work proposes a new Case-Based Reasoning (CBR) approach, named Q-CBR, that uses a Qualitative Spatial Reasoning (QSR) theory to model, retrieve and reuse cases by means of spatial relations. We used the EOPRA formalism to model the qualitative relations between the objects in a case and two algorithms were proposed: a new retrieval algorithm,...

Climbing ramps is an important ability for humanoid robots: ramps exist everywhere in the world, such as in accessibility ramps and building entrances. This works proposes the use of Reinforcement Learning to learn the action policy that will make a robot walk in an upright position, in a lightly sloped terrain. The proposed architecture of our sys...

This paper presents a new 2D robot simulator based on the Cross Architecture for RoboCup Soccer Humanoid League domain. A simulator is an important tool for testing cognitive algorithms in robots without the need of handling with real robot problems, moreover, a simulator is extremely useful for allowing reproducibility of any developed algorithm,...

This paper proposes a new Case-Based Reasoning (CBR) approach, named Q-CBR, that uses a Qualitative Spatial Reasoning theory to model, retrieve and reuse cases by means of spatial relations. A qualitative distance and orientation calculus (\(\mathcal {EOPRA}\)) is used to model cases using qualitative relations between the objects in a case. A new...

The goal of this work is to develop a collaborative communication system of spatial perceptions for vision-based multi-robot systems using qualitative spatial reasoning, where the representation of the domain is built upon the perspective of the Elevated Oriented Point Algebra (EOPRA) and the reasoning itself is made by a combination between the Or...

In order to perform a walk on a real environment, humanoid robots need to adapt themselves to the environment, as humans do. One approach to achieve this goal is to use Machine Learning techniques that allow robots to improve their behavior with time. In this paper, we propose a system that uses Reinforcement Learning to learn the action policy tha...

Este trabalho busca o estudo do comportamento da Integração Numérica por Monte Carlo em um problema que tem como meta encontrar o volume e centro de massa de um objeto cuja função não é bem comportada ou definida. Realizando estes experimentos ficou comprovada a robustez do método que apresentou ótimos resultados, e que este método pode se estender...

Robôs humanoides podem ser considerados uma das melhores representações artificiais do corpo humano. Assim, competições robóticas tem sido usadas para incentivar o desenvolvimento de robôs em diferentes aplicações e domínios. Dentre as principais competições, pode-se citar a Robocup Soccer. Na Liga Humanoide da RoboCup o sistema de visão é a princi...

This paper describes the design and development of a new humanoid robot named Newton, that is intended for applications in research and also to be used in the RoboCup KidSize League World Competition. Newton robot has been designed to work without any dedicated sub-controller implemented in low level hardware, often used to control the servomotors...

This paper describes a monocular vision system for humanoid robots designed and built to compete in the RoboCup Humanoid KidSize League. The proposed vision system allows the robots to track a ball, identify goals, field lines, teammates and opponents, providing information such as distances and estimated location for the robots simultaneously, usi...

The Reinforcement Learning is a well known method for solving problems where the agent needs to learn through direct interaction with the environment. However, this technique is not efficient enough, due to its high computational cost. This work proposes and test the Reinforcement Learning accelerated by heuristics obtained through demonstrations a...

O Aprendizado por Reforço é um método bastante conhecido para resolução de problemas em que o agente precisa aprender em interação direta com o ambiente. Porém esta técnica tem o problema de não ser eficiente o bastante, devido ao seu alto custo computacional. Este trabalho tem como objetivo propor e testar o algoritmo de Aprendizado por Reforço Ac...

O Aprendizado por Reforço é um método bastante conhecido para resolução de problemas em que o agente precisa aprender em interação direta com o ambiente. Porém esta técnica tem o problema de não ser eficiente o bastante, devido ao seu alto custo computacional. Este artigo tem como objetivo propor e testar o algoritmo de Aprendizado por Reforço Acel...