Navegando por Autor "Flavio Tonidandel"

Agora exibindo 1 - 20 de 20

A Case Base Seeding for Case-Based Planning Systems
(2004-12-26) Flavio Tonidandel; RILLO, M.
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 important, there are no references about CBS systems in the literature even from those CBP systems that claim to use some similar systems. Therefore, this paper tries to overcome this deficiency by modeling and implementing a complete random Case Base Seeding process. © Springer-Verlag Berlin Heidelberg 2004.
A fast model-based vision system for a robot soccer team
(2006-11-17) MARTINS, M. F.; Flavio Tonidandel; Reinaldo Bianchi
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 design and implementation of a fast and robust computer vision system for a team of small size robot soccer players. The proposed system combines artificial intelligence and computer vision techniques to locate the mobile robots and the ball, based on global vision images. To increase system performance, this work proposes a new approach to interpret the space created by a well-known computer vision technique called Hough Transform, as well as a fast object recognition method based on constraint satisfaction techniques. The system was implemented entirely in software using an off-the-shelf frame grabber. Experiments using real time image capture allows to conclude that the implemented system are efficient and robust to noises and lighting variation, being capable of locating all objects in each frame, computing their position and orientation in less than 20 milliseconds. © Springer-Verlag Berlin Heidelberg 2006.
A single camera vision system for a humanoid robot
(2015-01-27) VILAO, C. O.; PERICO, D. H.; SILVA, I. J.; HOMEN, T. P. D.; Flavio Tonidandel; Reinaldo Bianchi
© 2014 IEEE.This paper describes a monocular vision system for humanoid robots designed and built to compete in the Robo Cup Humanoid Kid Size League. The proposed vision system allows the robots to track a ball, identify goals, field lines, team mates and opponents, providing information such as distances and estimated location for the robots simultaneously, using threads. With experiments using the real robots it was possible to run the vision system in real time with Full HD camera resolution, thus achieving the main goal of this work.
Analysis of the PSO Parameters for a Robots Positioning System in SSL
(2019-07-08) LAUREANO, M. A. P.; Flavio Tonidandel
© 2019, Springer Nature Switzerland AG.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 solutions that analyze the strategy of the opposing team during the game and make any necessary adaptations. This paper proposes the use of the Particle Swarm Optimization (PSO) algorithm as an option to determine the positioning during the match. A prototype has been developed to validate the configuration parameters. Experiments in a simulator, analysis of game logs and results in a real matches have demonstrated the feasibility of applying the PSO algorithm to find the robots positions.
Analysis of WiFi localization techniques for kidnapped robot problem
(2022-04-05) PEGORELLI NETO, A.; Flavio Tonidandel
© 2022 IEEE.This work proposes an analysis of the earliest indoor localization techniques based on recurrent neural networks (RNN) like Gated Recurrent Unit (GRU) and Long-Short Term Memory (LSTM), including k-Nearest Neighbors (KNN) machine learning, to process WiFi received signal strength data (RSS) for the kidnapped robot problem (KRP). The proposed solutions uses processed data generated in a Webots simulation of the iRobot Create robot, with the RSS signals simulated based on fingerprinting data from a real indoor area with 6 dedicated access points as reference. The efficiency of each system is evaluated using cumulative distribution function for several access point combinations, noise and vanishing levels for a model trained with the base test parameters from the reference material, with all 6 access points (APs) activated, ldBm Gaussian noise, 10% masking level and using 10 time steps of data as history inputs. The results show that RNN systems can achieve mean localization accuracy between $0.44\mathrm{m}\pm 0.39\mathrm{m}$ for LSTM and $0.50\mathrm{m}\pm 0.38\mathrm{m}$ for GRU and the KNN proposal reaching $0.68\mathrm{m}\pm 0.73\mathrm{m}$, proving the capability of those systems to recover from a KRP event keeping similar results obtained without any event.
Case adaptation by segment replanning for case-based planning systems
(2005-08-26) Flavio Tonidandel; RILLO, M.
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 method called CASER - Case Adaptation by Segment Replanning - is presented as an adaptation rule for case-based planning system. The method has two phases: the first one completes a retrieved case as an easy-to-generate solution method. The second phase improves the quality of the solution by using a generic heuristic in a recursive algorithm to determine segments of the plan to be replanned. The CASER method does not use any additional knowledge, and it can find as good solutions as those found by the best generative planners. © Springer-Verlag Berlin Heidelberg 2005.
Comparison and analysis of the DVG+A∗ and rapidly-exploring random trees path-planners for the robocup-small size league
(2019-10-23) DA SILVA COSTA, L.; Flavio Tonidandel
© 2019 IEEE.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 to the scenario presented in the Small Size League (SSL). The metrics used to compare each algorithm were established based on the characteristics of a SSL game, which demand a short path, low computational cost and a safe distance from the opponent robots. For the comparison, both algorithms were tested in static and dynamic environments. After all the tests, DVG+A∗ has shown the best results.
DETECÇÃO AUTOMÁTICA DE DISLEXIA BASEADA EM LEITURA DIGITAL
(2020-12-09) IAGO RODRIGUES WANDEUR; JOSÉ DJALMA DA CUNHA JÚNIOR
O processo de investigação diagnóstica da dislexia é relativamente demorado e envolve o trabalho de uma equipe multiprofissional de saúde em seu âmbito, muitas vezes o tornando caro e impossibilitando o acesso de uma grande quantidade de pessoas com menos recursos financeiros e de pessoas com rotinas agitadas e pequena quantidade de tempo livre pessoal, seja por cotidiano atarefado profissionalmente ou estudantil. Em consideração a essas pessoas e aos obstáculos encontrados no diagnóstico dessa condição, esse trabalho objetiva identificar a dislexia de uma forma mais rápida e acessível às diferentes camadas socioeconômicas da sociedade. O experimento consiste na análise visual da leitura de um texto no computador, sendo o padrão de leitura interpretado por uma rede neural do tipo deep learning e, em questão de minutos, é emitido um relatório com a probabilidade da pessoa possuir dislexia, incentivando a procura de atendimento adequado para o caso.
DVG+A* and RRT Path-Planners: A Comparison in a Highly Dynamic Environment
(2021) DA SILVA, COSTA, L.; Flavio Tonidandel
© 2021, The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature.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, the algorithms were evaluated according to its computational time, path length and path safety in a static environment. Afterwards, they were evaluated regarding the accumulated computational time, number of recalculated paths, total navigation time and number of collisions in a dynamic environment. The static environment results have shown that the DVG+A* has a better overall performance than RRT, except for the path safety, however, some ideas on how to improve this were discussed. In the dynamic environment the algorithms performed similarly and with a high number of collisions during the experiments. Thus, showing the importance of using an obstacle avoidance algorithm combined with the path planner. In conclusion, the results obtained showed that both algorithms aren’t suitable for highly dynamic and cluttered environments, however, due how sparse the obstacles are in the SSL, they can still be used with some care. Regarding static environments, the DVG+A* has shown the best results.
ESTUDO DE MODELOS DE PREDIÇÃO DE CANCELAMENTO DE SERVIÇOS DE TELEFONIA UTILIZANDO TÉCNICAS DE APRENDIZADO DE MÁQUINA
(2020-12-09) GUILHERME MARTINS GONÇALVES DE OLIVEIRA; JOÃO VICTOR SERRALHA
Um dos pontos mais críticos, para empresas de telefonia, é a alta taxa de rotatividade dos clientes, e para atender às necessidades de sobrevivência no ambiente competitivo, a retenção de clientes existentes tornou-se um grande desafio. O estudo feito por Hanif (2019) mostra que devido ao avanço da tecnologia nos últimos anos, o ramo de telecomunicação foi uma das primeiras indústrias a investir em técnicas de aprendizado de máquina e de análise de dados para a prevenção da rotatividade de clientes. Porém, mesmo com os investimentos, a questão da rotatividade de clientes ainda é um grande problema nesse setor. Na pesquisa realizada por Saraswat e Tiwari (2018) no setor de telecomunicações, afirma-se que o custo de aquisição de um novo cliente é muito maior do que reter o existente. Nesse trabalho, foram comparados os desempenhos de três algoritmos distintos de aprendizado de máquina no contexto de predição de cancelamento de serviços em empresas de Telecom. Os algoritmos foram aplicados em uma base de dados com registros reais de uma empresa de telecomunicação. Os resultados foram utilizados para a construção de suas determinadas métricas, tendo como objetivo, avaliar o desempenho dos classificadores. Após o treinamento e validação dos modelos, foi possível chegar em uma conclusão de qual algoritmo produziu o melhor modelo nesse contexto e as possíveis razões para tal resultado
Humanoid robot gait on sloping floors using reinforcement learning
(2016-01-05) SILVA, I. J.; PERICO, D. H.; HOMEM, T. P. D.; VILAO, C. O.; Reinaldo Bianchi; Flavio Tonidandel
© Springer International Publishing AG 2016.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 system is a two-layer combination of the traditional gait generation control loop with a reinforcement learning component. This allows the use of an accelerometer to generate a correction for the gait, when the slope of the floor where the robot is walking changes. Experiments performed on a real robot showed that the proposed architecture is a good solution for the stability problem.
itSIMPLE2.0: An integrated tool for designing planning domains
(2007-09-26) VAQUERO, T. S.; ROMERO, V.; Flavio Tonidandel; SILVA, J. R.
A great effort has been made today in the area of Artificial Intelligence for defining reliable automated planning systems that can be applied in real life applications. That leads to the need of a systematic design process, in which the initial phases are not neglected and where Knowledge and Requirement Engineering tools have a fundamental role for supporting designers. Following this principle, this paper presents the evolution of the tool itSIMPLE which implements a KE integrated environment where designers can perform knowledge acquisition, domain modeling, domain model analysis, model testing, maintenance and plan analysis processes by using different well-known languages such as UML, Petri Nets, PDDL and XML, each one of them with its best contribution. The tool supports users in an organized object-oriented domain design process with a friendly and easy-to-use interface. Copyright © 2007, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Market-based dynamic task allocation using heuristically accelerated reinforcement learning
(2011-10-10) GURZONI JUNIOR, J. A.; Flavio Tonidandel; Reinaldo Bianchi
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 real-time. The performance of the task allocation mechanism is evaluated and compared in different implementation variants, and results show that the proposed MRTA system significantly increases the team performance, when compared to pre-programmed team behavior algorithms. © 2011 Springer-Verlag.
Newton: A high level control humanoid robot for the robocup soccer kidsize league
(2015-01-05) PERICO, D. H.; SILVA, I. J.; VILAO JUNIOR, C. O.; HOMEM, T. P. D.; DESTRO, R. C.; Flavio Tonidandel; Reinaldo Bianchi
© Springer-Verlag Berlin Heidelberg 2015.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, Intel’s Jimmy and Robotis’ DARwIn-OP. This research article describes the project and development of a new humanoid robot named Newton, made for research purposes and also to be used in the RoboCup Soccer KidSize League Competition. Newton robot’s contributions include that it has been developed to work without a dedicated microcontroller board, using an four-by-four-inch Intel NUC board, that is a fully functioning PC. To work with this high level hardware, a new software architecture comprised of completely independent processes was proposed. This architecture, called Cross Architecture, is comprised of completely independent processes, one for each intelligent system required by a soccer player: Vision, Localization, Decision, Communication, Planning, Sense and Acting, besides having a process used for managing the others. The experiments showed that the robot could walk, find the ball in an unknown position, recover itself from a fall and kicking the ball autonomously with a good performance.
On the construction of a RoboCup small size league team
(2011-01-05) Gurzoni Jr. J.A.; Martins M.F.; Flavio Tonidandel; Reinaldo Bianchi
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 multidisciplinary research in fields like robotic hardware development, machine learning, multi-robot systems, computer vision, control theory, and mechanics, among others. This paper intends to provide insights about the aspects involved on the development of the RoboFEI RoboCup SSL robot soccer team and to present the contributions produced over its course. Among these contributions, a computer vision system employing an artificial neural network (ANN) to recognize colors, a heuristic algorithm to recognize partially detected objects, an implementation of the known rapidly-exploring random trees (RRT) path planning algorithm with additional rules, enabling the angle of approach of the robot to be controlled, and a layered strategy software system. Experimental results on real robots demonstrate the high performance of the vision system and the efficiency of the RRT algorithm implementation. Some strategy functions are also experimented, with empirical results showing their effectiveness. © 2011 The Brazilian Computer Society.
On the use of UML.P for modeling a real application as a planning problem
(2006) VAQUERO, T. S.; Flavio Tonidandel; BARROS, L. N. DE; SILVA, J. R.
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 planning domain modeling process. We also discuss the exposure of UML.P to a real application, e.g., the sequencing car problems in an assembly line. This modeling experience, using a classical manufacturing problem, provides some insights and considerations that can contribute to a general KE process for planning. Copyright © 2006, American Association for Artificial Intelligence (www.aaai.org). All rights reserved.
Performing and blocking passes in small size league
(2019-10-25) LAUREANO, M. A. P.; Flavio Tonidandel
© 2019 IEEE.The changes in the Small Size League rules, like increasing the field size and inclusion of more robots in the game have brought greater possibilities of playing and strategies. With the increased complexity of soccer matches, the positioning of the robots has become important as the defense and attack mechanisms. The learning of opposing team game playing has been shown to be effective, but an SSL soccer match indicates the need for solutions that analyze the strategy of the opposing team during the game and make necessary adaptations. This paper proposes the use of the Particle Swarm Optimization (PSO) algorithm as an option to determine the positioning for making and blocking passes during the match. A prototype has been developed to validate the configuration parameters. Experiments in a simulator and analysis of game logs have demonstrated the feasibility of applying the PSO algorithm to find the robots positions.
Reading PDDL, writing an object-oriented model
(2006-10-27) Flavio Tonidandel; VAQUERO, T. S.; SILVA, J. R.
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 domain specification in PDDL and transforms it into an object-oriented model, more specifically into a version of UML for planning approaches. This translation process can let a designer read PDDL domains and verify it with some powerful tool like itSIMPLE or GIPO, or it can allow a planning system that only reads object-oriented models to run in domains described in PDDL originally. © Springer-Verlag Berlin Heidelberg 2006.
SOFTWARE DE PRÉ-DIAGNÓSTICO MÉDICO PARA CLASSIFICAÇÃO DE RISCO
(2023-06-12) DOUGLAS IINO RINALDI; GUILHERME CUCIO LAGO; LUCAS LOPES; MARCELO NOBRE
Atualmente a classificação de risco é um processo realizado por um profissional de saúde (na maioria dos casos por um enfermeiro) assim que o paciente chega ao hospital, a fim de determinar a gravidade dos sintomas que o mesmo apresenta, além de encaixá-lo na fila com um tempo de espera condizente a tais sintomas para que todos possam ser atendidos de forma conveniente e eficiente. A falha em classificar o paciente de forma precisa pode acarretar em consequências tanto para ele quanto para todos os outros que tiveram seu tempo de espera influenciado por sua classificação. Para realizar a classificação de risco, é utilizado o Protocolo de Manchester que estipula que os profissionais de saúde realizem uma avaliação sobre o quadro clínico do paciente e o classifiquem com uma cor, representada por uma pulseira. No Brasil, o processo é realizado sem o auxílio de qualquer software ou hardware que possa acelerar ou tornar o procedimento mais eficaz: todos os sinais vitais colhidos do paciente, como frequência cardíaca e pressão arterial, são preenchidos com papel e caneta, e qualquer consulta que o funcionário precise fazer é feita em um manual físico referente ao Protocolo. Assim, este trabalho tem como objetivo propor um software capaz de armazenar todas as informações necessárias do paciente durante o pré-diagnóstico e classificá-lo de acordo com o Protocolo de Manchester. Além disso, será implementada uma Inteligência Artificial (IA) que funcionará com base no algoritmo de Random Forest para que o software seja capaz de aumentar sua precisão de acordo com seu uso.
The Inclusive Potential of Educational Robotics
(2022-10-18) CANET, A. M. D.; Flavio Tonidandel
© 2022 IEEE.Educational Robotics favors the development of reasoning, teamwork and the socialization of knowledge. In this work, using this educational technology as a learning mediator, its inclusive potential for students with disabilities in elementary school questioned. The objective of this study is verify the inclusive potential of educational robotics and what are the difficulties the robotics teachers present in the inclusion of students with disabilities. This research is qualitative and quantitative. It involves a bibliographic research and a questionnaire answered by the Professor of Support to Pedagogical Projects of Educational Technologies (PAPP TEC) of the Municipal Schools of São Bernardo do Campo. The questionnaire used the free Google Forms tool. The multiple-choice answers received statistical treatment and the open question analyzed using Bardin's content analysis. In the questionnaire and in the semi-structured interview, the teachers pointed out the need for training actions, collaborative action by support professionals (Technical Guidance Team and specialist teachers in the areas of disabilities) and access to assistive technology for the development of the inclusive potential of robotics.