A5005947576- AI-based Problem Solving and Planning
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Logic, Reasoning, and Knowledge
- Robotic Locomotion and Control
- Modular Robots and Swarm Intelligence
- Model-Driven Software Engineering Techniques
- Reinforcement Learning in Robotics
- Semantic Web and Ontologies
- Multi-Agent Systems and Negotiation
- Control and Dynamics of Mobile Robots
- Education Pedagogy and Practices
- Academic Research in Diverse Fields
- Prosthetics and Rehabilitation Robotics
- Teaching and Learning Programming
- Metaheuristic Optimization Algorithms Research
- Robotic Mechanisms and Dynamics
- Software Engineering Techniques and Practices
- Advanced Vision and Imaging
- Image and Object Detection Techniques
- Constraint Satisfaction and Optimization
- Software Testing and Debugging Techniques
- Business Process Modeling and Analysis
- Biotechnology and Related Fields
- Spreadsheets and End-User Computing
Centro Universitário FEI
2015-2024
University of Coimbra
2018-2020
Universidad Católica San Pablo
2020
Fordham University
2020
Universidade do Porto
2018
Tecnológico de Monterrey
2018
Universidade de São Paulo
1998-2002
Universidade Brasil
2002
Universidade Politecnica
2000
Abstract Since the end of 1990s, there has been an increasing interest in application artificial intelligence (AI) planning techniques to solve real-life problems. In addition characteristics academic problems, such as need reason about actions, problems require detailed knowledge elicitation, engineering, and management. A systematic design process which Knowledge Requirements Engineering tools play a fundamental role is necessary applications. One main challenges process, consequently...
This paper describes a monocular vision system for humanoid robots designed and built to compete in the RoboCup Humanoid KidSize League. The proposed allows track ball, identify goals, field lines, team mates opponents, providing information such as distances estimated location simultaneously, using threads. With experiments real it was possible run time with Full HD camera resolution, thus achieving main goal of this work.
This article introduces the successful methodology adopted for realization of Brazilian Robotics Olympiad. Organizational and scientific issues are presented discussed as well results statistical surveys performed with participants that verify benefits brought by this robotics The Olympiad is a nine-year-old nation-wide initiative created mission promoting among students or without previous knowledge robotics, fostering their interest to engage in science, technology engineering studies...
This paper describes the design and development of a new humanoid robot named Newton, that is intended for applications in research also to be used Robo Cup Kid Size League World Competition. Newton has been designed work without any dedicated sub-controller implemented low level hardware, often control servomotors robot. uses only standard personal computer do all processing necessary by To able deal with tasks involved robotic soccer domain, software architecture proposed. based on hybrid...
In order to perform a walk on real environment, humanoid robots need adapt themselves the as humans do. One approach achieve this goal is use Machine Learning techniques that allow improve their behavior with time. paper, we propose system uses Reinforcement learn action policy will make robot in an upright position, lightly sloped terrain. To validate proposal, experiments were made - for RoboCup Humanoid League based DARwIn-OP. The results showed was able sloping floors, going up and down...
Abstract The Robot Soccer domain has become an important artificial intelligence test bench and a widely studied research area. It is with real, dynamic, uncertain environment, where teams of robots cooperate face adversarial competition. To build RoboCup Small Size League (SSL) team able to compete in the world championship requires multidisciplinary fields like robotic hardware development, machine learning, multi-robot systems, computer vision, control theory, mechanics, among others....
This paper provides an experimental analysis between Dynamic Visibility Graph A Star (DVG+A*) and Rapidly-exploring Random Trees (RRT) path-planners, in order to compare which one is more adequate the scenario presented Small Size League (SSL). The metrics used each algorithm were established based on characteristics of a SSL game, demand short path, low computational cost safe distance from opponent robots. For comparison, both algorithms tested static dynamic environments. After all tests,...
A Mostra Nacional de Robótica (MNR) é uma das mostras científicas caráter nacional apoiadas pelo governo federal no Brasil. Sua temática centrada na automação e robótica, representantes inatos novas tecnologias, elementos com forte capacidade para estimular o imaginário pessoas fortemente integrados processos modernos ensino-aprendizagem, dialogando diretamente diversas disciplinas dos ciclos fundamental, médio técnico. O formato adotado pela MNR busca reunir divulgação científica típicos...