Flavio Tonidandel

Centro Universitário FEI · Department of Computer Science

This work provides a comparison between two path planners, the coordinated Multi-Robot A Star (MRA*) and uncoordinated Dynamic Visibility Graph A Star (DVG+A*) algorithms when applied to the highly dynamic, uncertain, multi-robot environment of the RoboCup Small Size League. To consider dynamic obstacles and uncertainties, the path planners were co...

The COVID-19 global pandemic has challenged the entire academic community (and the whole world) to adopt new and creative ways of making progress. Most conferences have now organized at least one fully virtual event, often including keynote lectures, paper presentation sessions, poster sessions, and even social events. However, when the core of one...

This work provides a deeper comparison between two path planning algorithms, the Dynamic Visibility Graph A Star (DVG+A*) and Rapidly–exploring Random Trees (RRT), when applied in a high dimension and dynamic environment, which is the RoboCup Small Size League. The algorithms were compared under two different perspectives. In the first analysis, th...

The changes in the Small Size League rules have brought greater possibilities of playing. With the increased complexity of soccer matches, the positioning of the robots has become important as a defense and attack mechanism. The learning of opposing team game playing has been shown to be effective, but an SSL soccer match indicates the need for sol...

A Smart Home has different types of systems that interact with the inhabitants that are looking for more comfort and a better quality within the residence. To increase the comfort and life quality of inhabitants, it is necessary to develop a system that adapts itself to the inhabitant's behavior. This article presents a study of the GSP, SPADE, Pre...

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 article introduces the successful methodology adopted for the realization of the Brazilian Robotics Olympiad. Organizational and scientific issues are presented and discussed as well as results of statistical surveys performed with participants that verify the benefits brought by this robotics Olympiad. The Brazilian Robotics Olympiad is a nin...

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...

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 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...

There is much information of users to be analyzed to develop a personalized project. To perform an analysis, it is necessary to create clusters in order to identify features to be explored by the project designer. In general, a classical clustering algorithm called K-Means is used to group users features. However, K-Means reveals some problems duri...

Since the end of the 1990s, there has been an increasing interest in the application of artificial intelligence (AI) planning techniques to solve real-life problems. In addition to characteristics of academic problems, such as the need to reason about actions, real-life problems require detailed knowledge elicitation, engineering, and management. A...

This paper presents a Multi-Robot Task Allocation (MRTA) system, implemented on a RoboCup Small Size League team, where robots participate of auctions for the available roles, such as attacker or defender, and use Heuristically Accelerated Reinforcement Learning to evaluate their aptitude to perform these roles, given the situation of the team, in...

The Robot Soccer domain has become an important artificial intelligence test bench and a widely studied research area. It is a domain with real, dynamic, and uncertain environment, where teams of robots cooperate and face adversarial competition. To build a RoboCup Small Size League (SSL) team able to compete in the world championship requires mult...

This paper presents an overview of the RoboFEI team state for the RoboCup Brazil Small Size League competi-tion 2010. It contains descriptions of the mechanical, electrical and software modules designed to enable the robots to achieve playing soccer capabilities in the dynamic environment of the RoboCup Small Size League.

Transforming requirements of real planning applications into a sound input-ready model for planners has been one of the main challenges in the study of Knowledge Engineering within AI planning. However, few tools and methods have been developed to facilitate this transformation process. it- SIMPLE is a research project dedicated to support the de-...

The knowledge Engineering for Planning and Schedul- ing requires techniques and tools that can assist a de- signer to better understand, specify, verify and validate a domain model. There are some tools, like itSIMPLE and GIPO, that can meet the modeling process require- ments but none of them can reason about the domain in order to validate model...

The challenge of a competition has attracted attention in the academic world, first by the fact that it deals with motivation and second because it can play an impor- tant role in the research improvement as a testbed for techniques, models and applications. In this article we raise a discussion on ICKEPS competition which had two editions so far....

This chapter described the use of artificial intelligence and computer vision techniques to create a fast and robust real time vision system for a robot soccer team. To increase the system performance, this work proposes a new approach to interpret the space created by the Hough Transform, as well as a fast object recognition method based on constr...

A great effort has been made today in the area of Artifi- cial Intelligence for defining reliable automated plan- ning systems that can be applied in real life applica- tions. That leads to the need of a systematic design pro- cess, in which the initial phases are not neglected and where Knowledge and Requirement Engineering tools have a fundamenta...

Robot Soccer is a challenging research domain for Artificial Intelligence, which was proposed in order to provide a long-term problem in which researchers can investigate the construction of systems involving multiple agents working together in a dynamic, uncertain and probabilistic environment, to achieve a specific goal. This work focuses on the...

There is a great interest in the planning community to apply all developments already achieved in the area to real applications. Such scenario makes the community focus on Knowledge Engineering (KE) applied in modeling of planning problems and domains. In this paper, we propose the use of UML for Planning Approach, denominated UML.P, during plannin...

There are many efforts towards a combination of planning systems and real world applications. Although the PDDL is in constant evolution, which improves its capability to describe real domains, it is still a declarative language that is not so simple to be used by the non-planning community. This paper describes a translation process that reads a d...

Many advances have happened in residential automation, however little importance has been given to residential automation based in the behavior of the inhabitants. This article describes a system whose objective is to observe and to learn rules in a house according to the behavior of its inhabitants. The system uses the concept of learning with ind...

An adaptation phase is crucial for a good and reasonable Case-Based Planning (CBP) system. The adaptation phase is responsible for finding a solution in order to solve a new problem. If the phase is not well designed, the CBP system may not solve the desirable range of problems or the solutions will not have appropriate quality. In this paper, a me...

A graphical interface is presented for the modeling of planning environments where an integrated tool permits the user to export the planning model to different representation languages such as PDDL or XML. The application uses an UML model to introduce a planning domain as a first step, followed by a step where a representation in Petri Nets – aut...

This paper describes a Case Base Seeding system (CBS) that can be used to seed a case base with some random cases in order to provide minimal conditions for the empirical tests of a Case-Based Planning System (CBP). Random case bases are necessary to guarantee that the results of the tests are not manipulated. Although these kind of case bases are...

This paper is a further step in the investigation of the ADG similarity performance. The ADG similarity is a new similarity rule that was first used in the FAR-OFF case-based planning system, which presents good performance in solving planning problems. The ADG similarity is more accurate than old similarity metrics because it estimates the effort...

This paper investigates the use of the FAR-OFF system in the Manufacturing Automation field. The FAR-OFF system has the feature of heuristic search based systems, which have been presenting excellent results over the last years in the planning area. However, instead of being a generative planning system, the FAR-OFF system is a case-based planner t...

Este artigo investiga o uso do sistema FAR-OFF na área da Automação da Manufatura. O sistema FAR-OFF possui característica similar aos sistemas de planejamento baseado em busca heurística, os quais têm apresentado excelentes resultados nos últimos anos na área de planejamento. Entretanto, em vez de ser um sistema generativo, o FAR-OFF é um sistema...

This paper presents a case-based planning system, called FAR-OFF, as an alternative approach to heuristic search generative planners, like HSP and FF. The FAR-OFF system introduces the use of a new similarity metric, called ADG (Action Distance-Guided), that is more accurate than other similarity metrics, and it also incorporates techniques to decr...

In this paper, we present an adaptation-guided similarity metric based on the estimate of the number of actions between states, called ADG ( Action Distance-Guided ). It is determined by using a heuristic calculation extracted from the heuristic search planning, called FF, which was the fastest planner in the AIPS'2000 competition. This heuristic p...

The number of techniques that focuses on how to create compact casebase in case-base maintenance has been increasing over the last few years. However, while those techniques are concerned with choosing suitable cases to improve the system performance, they do not deal with the problem of a limited memory space, which may affect the performance as w...

Heuristic search planners, as FF and HSP systems, are new planning approaches which p erformance has been increasing over the last years. One way to outperform the heuristic search planners is using the case-based planning approach, but new similarity metrics must be investigated. This is because the old similarity rules used in p revious case-base...

The majority of case-based planning systems consider an infinite case memory to store their cases. However, the size of the case memory is limited and it can become a barrier for case-based systems efficiency when it is full. This paper presents a method that refines and abstracts cases in order to release memory space for a new case. However, in s...

In the planning area, the reasoning about action is important, because the plans are made by a sequence of actions. Each action has its effects that need to be treated and formalized in some logical framework.The use of Transaction Logic (TR) makes possible a perfect definition of fluents to treat the effects of ramification problems, because the T...

This work stands out the use of Transaction Logic (TR) in case-based planning. The TR provides a correct and complete logical theory based planner that can be computationally implemented keeping the formal theory semantic. The TR is efficient on states treatment besides to create a retriever and cases adaptation easier than others formalized system...

The Y04 team from the Centro Universitário da FEI has been developing a robot soccer team based on coordinates and advanced controls. The team works with path navigation and planning, passing and attack and defense strategies. The system is still under development. Resumo. A equipe Y04 do Centro Universitário da FEI vem desenvolvendo um time de fut...

The Biênio03/04 team from the Centro Universitário da FEI has been developing a robot soccer team based on the developed team for the 2003 competition during 6 º SBAI. The team works in a simple way. Instead of being driving to achieve an specific point in the x,y coordinate, the team just follows some specific directions. The results has been good...

This work presents a possible approach to color filtering applied to robot soccer images. This approach uses the HSI color space mapped into the RGB space through a tri-dimensional matrix, avoiding either the RGB to HSI conversion and color comparisons or parameter manipulation. Resumo. Este trabalho apresenta uma solução para a filtragem de cores...

Resumo: A qualidade de uma solução é crucial em muitas aplicações de Inteligência Artificial, inclusive para as solução de um sistema de planejamento. Entretanto, não existe nenhum método independente do domínio que possa melhorar a qualidade de um plano de um sistema de planejamento. Este artigo apresenta um método independente do domínio que melh...

The AI Planning field has pursued the goal of applying all developments already achieved in order to conquest real and successful cases. Considering this objective, interesting and challenging real problems are found in the software development field. This paper was elaborated based on complex problems encountered in the software development area r...

This paper presents an overview of RoboFEI team, who will participate in the Small Size League of the RoboCup 2010, to be held in Singapore. The paper contains descriptions of the mechanical, electrical and software modules, designed to enable the robots to achieve playing soccer capa-bilities in the dynamic environment of the RoboCup Small Size Le...

This article presents the techniques of computational vision, robot control and game strategy used by RoboFEI Ro-bot-Soccer team. The computational vision is based on the Hough Transformation for circles and the opponent detection is based on colors, the robot control has a Proportional-derivative control with Kalman filter, and the strategy is bas...

Resumo. Este artigo apresenta, em linhas gerais, o desenvolvimento e a implementação de um sistema de planejamento baseado em casos. Este sistema tem como característica a incorporação de técnicas de manutenção de base de casos e uma nova regra de similaridade, chamada de ADG, que garante precisão na etapa de resgate. Todas as técnicas incorporadas...

This paper addresses the problem of colour recognition in real time computer vision systems applied to the robot soccer domain. The developed work presents a novel combination between our current model-based computer vision system and neural networks to classify colours and identity the robots on an image. This combination presents an alternative t...

Many logical theories used to formalize planning systems don't allow operations with databases that represent knowledge bases, or don't have any inference rule to allow the computational implementation. Instead of that, Transaction Logic, with its restrictive version called serial-Horn, allows a computational implementation of its theory in PROLOG...

This article presents two techniques to detect and recognize mobile robots in a soccer robot field. One technique is based on model recognition and multiple colors and the other is based on one color and multiple models. The techniques are applied to detect the systemsown team and the opponent team of robots. Resumo. Este artigo apresenta duas técn...

The entire life cycle of a real planning problem design involves several procedures, each one with its importance and capacity of extracting knowledge from the given problem. One of these procedures is the analysis and management of plans, which is vital for debugging the problem model, as well as for the verification of the consistence of the gene...

A good communication among the computer and the mobile robots is essential for real-time controlling. There are many communication protocols in the literature and they have several and specific features. However, features like reliability and flexibility are not fully present in these protocols although they are very important for an effective and...

Resumo. Muitos avanços têm acontecido em automação residencial, entretanto pouco destaque é dado à automação residencial baseada no comportamento dos habitantes. Este artigo descreve o estudo de um sistema cujo objetivo é observar e aprender regras em uma casa de acordo com o comportamento de seus habitantes. O sistema proposto, Sistema ABC+ (Autom...

This paper presents a case study and some preliminary results of a practical implementation of a Computer Vision system coupled to a steering system. The study is part of an unmanned vehicle project, which encompasses hardware and software modules. The system prototype hardware is composed of a modified vehicle, an electronic control module, a digi...

In this paper we present the RoboFEI Small League 2009 team description. Along this text we will introduce how we got to the Small Size League, where we stand as of February of 2009 and what goals we expect to reach until the Robocup 2009.