Uma proposta de slam com determinação de informações geométricas do ambiente

PEDROSA, Diogo P. F. ; MEDEIROS, Adelardo A. D. ; ALSINA, Pablo J. . Uma Proposta de SLAM com Determinação de Informações Geométricas do Ambiente. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 16, Salvador, BA, 2006. Anais... Salvador: CBA, 2006. v. 1. p. 1704-1709

Pose estimation of a humanoid robot using images from a mobile external camera

NOGUEIRA, Marcelo B. ; MEDEIROS, Adelardo A. D. ; ALSINA, Pablo J. Pose Estimation of a Humanoid Robot Using Images from an Mobile Extern Camera. In: IFAC WORKSHOP ON MULTIVEHICLE SYSTEMS, 2006, Salvador, BA. Anais... Salvador: MVS 2006, 2006.

Uma arquitetura distribuída de hardware e software para controle de um robô móvel autônomo

BRITTO, Ricardo S.; MEDEIROS, Adelardo A. D.; ALSINA, Pablo J. Uma arquitetura distribuída de hardware e software para controle de um robô móvel autônomo. In: SIMPÓSIO BRASILEIRO DE AUTOMAÇÃO INTELIGENTE,8., 2007, Florianópolis. Anais... Florianópolis: SBAI, 2007.

Representation of odometry errors on occupancy grids

SOUZA, Anderson A. S. ; SANTANA, André M. ; BRITTO, Ricardo S. ; GONÇALVES, Luiz Marcos G. ; MEDEIROS, Adelardo A. D. Representation of Odometry Errors on Occupancy Grids. In: INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, 5., 2008, Funchal, Portugal. Proceedings... Funchal, Portugal: ICINCO, 2008.

Localization of a mobile robot based on odometry and natural landmarks using extended kalman filter

SANTANA, André M.; SOUZA, Anderson A. S.; BRITTO, Ricardo S.; ALSINA, Pablo J.; MEDEIROS, Adelardo A. D. Localization of a mobile robot based on odometry and natural landmarks using extended Kalman Filter. In: INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS, 5., 2008, Funchal, Portugal. Proceedings... Funchal, Portugal: ICINCO, 2008.

Aprendizado por Reforço com Valores deInfluência em Sistemas Multi-Agente

We propose a new paradigm for collective learning in multi-agent systems (MAS) as a solution to the problem in which several agents acting over the same environment must learn how to perform tasks, simultaneously, based on feedbacks given by each one of the other agents. We introduce the proposed paradigm in the form of a reinforcement learning algorithm, nominating it as reinforcement learning with influence values. While learning by rewards, each agent evaluates the relation between the current state and/or action executed at this state (actual believe) together with the reward obtained after all agents that are interacting perform their actions. The reward is a result of the interference of others. The agent considers the opinions of all its colleagues in order to attempt to change the values of its states and/or actions. The idea is that the system, as a whole, must reach an equilibrium, where all agents get satisfied with the obtained results. This means that the values of the state/actions pairs match the reward obtained by each agent. This dynamical way of setting the values for states and/or actions makes this new reinforcement learning paradigm the first to include, naturally, the fact that the presence of other agents in the environment turns it a dynamical model. As a direct result, we implicitly include the internal state, the actions and the rewards obtained by all the other agents in the internal state of each agent. This makes our proposal the first complete solution to the conceptual problem that rises when applying reinforcement learning in multi-agent systems, which is caused by the difference existent between the environment and agent models. With basis on the proposed model, we create the IVQ-learning algorithm that is exhaustive tested in repetitive games with two, three and four agents and in stochastic games that need cooperation and in games that need collaboration. This algorithm shows to be a good option for obtaining solutions that guarantee convergence to the Nash optimum equilibrium in cooperative problems. Experiments performed clear shows that the proposed paradigm is theoretical and experimentally superior to the traditional approaches. Yet, with the creation of this new paradigm the set of reinforcement learning applications in MAS grows up. That is, besides the possibility of applying the algorithm in traditional learning problems in MAS, as for example coordination of tasks in multi-robot systems, it is possible to apply reinforcement learning in problems that are essentially collaborative

Localização e mapeamento simultâneos de ambientes planos usando visão monocular e representação híbrida do ambiente

The goal of this work is to propose a SLAM (Simultaneous Localization and Mapping) solution based on Extended Kalman Filter (EKF) in order to make possible a robot navigates along the environment using information from odometry and pre-existing lines on the floor. Initially, a segmentation step is necessary to classify parts of the image in floor or non floor . Then the image processing identifies floor lines and the parameters of these lines are mapped to world using a homography matrix. Finally, the identified lines are used in SLAM as landmarks in order to build a feature map. In parallel, using the corrected robot pose, the uncertainty about the pose and also the part non floor of the image, it is possible to build an occupancy grid map and generate a metric map with the obstacle s description. A greater autonomy for the robot is attained by using the two types of obtained map (the metric map and the features map). Thus, it is possible to run path planning tasks in parallel with localization and mapping. Practical results are presented to validate the proposal

Um sistema de visão para navegação robusta de uma plataforma robótica semi-autônoma

Large efforts have been maden by the scientific community on tasks involving locomotion of mobile robots. To execute this kind of task, we must develop to the robot the ability of navigation through the environment in a safe way, that is, without collisions with the objects. In order to perform this, it is necessary to implement strategies that makes possible to detect obstacles. In this work, we deal with this problem by proposing a system that is able to collect sensory information and to estimate the possibility for obstacles to occur in the mobile robot path. Stereo cameras positioned in parallel to each other in a structure coupled to the robot are employed as the main sensory device, making possible the generation of a disparity map. Code optimizations and a strategy for data reduction and abstraction are applied to the images, resulting in a substantial gain in the execution time. This makes possible to the high level decision processes to execute obstacle deviation in real time. This system can be employed in situations where the robot is remotely operated, as well as in situations where it depends only on itself to generate trajectories (the autonomous case)

Uma arquitetura distribuída de hardware e software para controle de um robô móvel autônomo

In this work, we present a hardware-software architecture for controlling the autonomous mobile robot Kapeck. The hardware of the robot is composed of a set of sensors and actuators organized in a CAN bus. Two embedded computers and eigth microcontroller based boards are used in the system. One of the computers hosts the vision system, due to the significant processing needs of this kind of system. The other computer is used to coordinate and access the CAN bus and to accomplish the other activities of the robot. The microcontroller-based boards are used with the sensors and actuators. The robot has this distributed configuration in order to exhibit a good real-time behavior, where the response time and the temporal predictability of the system is important. We adopted the hybrid deliberative-reactive paradigm in the proposed architecture to conciliate the reactive behavior of the sensors-actuators net and the deliberative activities required to accomplish more complex tasks

Mapeamento robótico 2,5-D com representação em grade de ocupação-elevação

This work introduces a new method for environment mapping with three-dimensional information from visual information for robotic accurate navigation. Many approaches of 3D mapping using occupancy grid typically requires high computacional effort to both build and store the map. We introduce an 2.5-D occupancy-elevation grid mapping, which is a discrete mapping approach, where each cell stores the occupancy probability, the height of the terrain at current place in the environment and the variance of this height. This 2.5-dimensional representation allows that a mobile robot to know whether a place in the environment is occupied by an obstacle and the height of this obstacle, thus, it can decide if is possible to traverse the obstacle. Sensorial informations necessary to construct the map is provided by a stereo vision system, which has been modeled with a robust probabilistic approach, considering the noise present in the stereo processing. The resulting maps favors the execution of tasks like decision making in the autonomous navigation, exploration, localization and path planning. Experiments carried out with a real mobile robots demonstrates that this proposed approach yields useful maps for robot autonomous navigation

Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.