Silas Franco dos Reis Alves

Artificial Neural Network Architectures and Training Processes

The architecture of an artificial neural network defines how its several neurons are arranged, or placed, in relation to each other. These arrangements are structured essentially by directing the synaptic connections of the neurons.

Pomodoro, a mobile robot platform for hand motion exercising

According to the World Report on Disability, currently 93 million children experience some kind of moderate or severe disability. Several systems including motion capture, serious games, exoskeletons and robotics have been researched and developed for assisting them on recovering basic functionality and daily activities, thus, improving mobility and providing a better quality of life. The popularization of these tools is a challenging task due to the required technical knowledge and the high acquisition costs, yet, the field of didactic robots is growing as an alternative that can be used in education, research, entertainment and other scenarios. This project proposes the development of the Pomodoro mobile robot as a device for encouraging hand motion exercise through flexion/extension and ulnar/radial deviation movements, for teleoperating the system in users experiencing reduced hand mobility. The system is composed of a low cost non-holonomic robot controlled with an embedded smartphone for on-site interactions through speech, image recognition and touch controls, along with a complimentary hand motion tracking subsystem for teleoperating the system using both real and virtual system, while recording position and orientation data for further assessment.

Conceptual Bases of Robot Navigation Modeling, Control and Applications

The advancements of the research on Mobile Robots with high degree of autonomy is possible, on one hand, due to its broad perspective of applications and, on other hand, due to the development and reduction of costs on computer, electronic and mechanic systems. Together with the research in Artificial Intelligence and Cognitive Science, this scenario currently enables the proposition of ambitious and complex robotic projects. Most of the applications were developed outside the structured environment of industry assembly lines and have complex goals, such as planets exploration, transportation of parts in factories, manufacturing, cleaning and monitoring of households, handling of radioactive materials in nuclear power plants, inspection of volcanoes, and many other activities. This chapter presents and discusses the main topics involved on the design or adoption of a mobile robot system and focus on the control and navigation systems for autonomous mobile robots. Thus, this chapter is organized as follows: • The Section 2 introduces the main aspects of the Robot design, such as: the conceptualization of the mobile robot physical structure and its relation to the world; the state of art of navigation methods and systems; and the control architectures which enables high degree of autonomy. • The Section 3 presents the dynamic and control analysis for navigation robots with kinematic and dynamic model of the differential and omnidirectional robots. • And finally, Section 4 presents applications for a robotic platform of Automation, Simulation, Control and Supervision of Navegation Robots, with studies of dynamic and kinematic modeling, control algorithms, mechanisms for mapping and localization, trajectory planning and the platform simulator.

Proposal of educational environments with mobile robots

This paper describes an initiative which uses low-cost mobile robots to create robotics courses and learning environment to support the teaching of computing and many other related disciplines. The pursued principle is that lower cost alternatives that can meet the educational needs, since it is accompanied by an environment with friendly software interface. In this sense, the hardware interface was developed to allow the computer to process data from the sensors and actuators of the mobile robot. This architecture is adequate because of the acceptance of students in their use, since the environment is unrolled within a familiar platform to them.

A friendly mobile entertainment robot for disabled children

Disabled children, when compared to other children, have fewer opportunities for exploring and interacting with the world. Thus, they are exposed to the feeling that they are unable to do anything by themselves. In this sense, the use of mobile robots may help these children to overcome their limitation and provide means to develop social skills. This paper describes partial results of on-going research on control architectures for mobile robots concerning hardware and software aspects. We propose a behavior-based architecture for the interaction between humans and robots, particularly children with severe motor disabilities. The main goal is to create a modular, flexible and scalable development environment, which motivates children to interact with the robot and the world.

Educational Environment for Robotic Applications in Engineering

This paper describes an initiative which uses low-cost mobile robots to create both robotics courses and learning environment to support the teaching of computing and many other related disciplines. The pursued principle is that lower cost alternatives that can meet the educational needs, since it is accompanied by an environment with friendly software interface. In this sense, the hardware interface was developed to allow the computer to process data from the sensors and actuators of the mobile robot. This architecture is adequate because of the acceptance of students in their use, since the environment is developed within a familiar platform to them.

Multilayer Perceptron Networks

Multilayer Perceptron (MLP) network features, at least, one intermediate (hidden) neural layer, which is placed between the input layer and the respective output layer.

Assisted robot navigation based on speech recognition and synthesis

Interactive robots can help people with or without disabilities. In this sense, research has been made in order to help children with motor disabilities to explore the world around them, which is important for their cognitive development. However, most of these initiatives lack on natural and intuitive interfaces, or are prohibitively expensive to be adopted in a larger scale. This paper describes an experimental environment to use speech recognition and synthesis to improve human-robot interaction (HRI) with children. The proposed system main goal is to perform activities with physically disabled children, however it can be used with other children. Thus, robots that are attractive, small-sized and relatively low-cost are used to implement such environment. The system recognizes a set of simple speech commands, which allows human-assisted navigation.

Use of myoelectric signals to command mobile entertainment robot by disabled children: Design and control architecture

Severely disabled children have little chance of environmental and social exploration and discovery. This lack of interaction and independency may lead to an idea that they are unable to do anything by themselves. In an attempt to help children in this situation, educational robotics can offer and aid, once it can provide them a certain degree of independency in the exploration of environment. The system developed in this work allows the child to transmit the commands to a robot through myoelectric and movement sensors. The sensors are placed on the childs body so they can obtain information from the body inclination and muscle contraction, thus allowing commanding, through a wireless communication, the mobile entertainment robot to carry out tasks such as play with objects and draw. In this paper, the details of the robot design and control architecture are presented and discussed. With this system, disabled children get a better cognitive development and social interaction, balancing in a certain way, the negative effects of their disabilities.

Mobile robotic teleoperation using gesture-based human interfaces

In this work a natural interaction framework for programming a mobile robot with gestures is developed using two low-cost human interface devices available on the market. The use of natural motion has been growing among user interface researches and developers for offering comfortable ways of interacting with the devices around us. Some examples can be seen in how touch screens, accelerometers and image processing have influenced our interactions with cellphones, gaming devices and computers, thus, allowing us to take advantage of our body ergonomics. The objective of this work is to integrate an intuitive tool for teleoperating a mobile robot through gestures as an alternative input for encouraging non-experts to relate with robotics and ease navigation tasks. For accomplishing the objective of this work, the mobile robots programming architecture is studied and integrated with those of the user interfaces for allowing the teleoperation of the robotics device. To check how the implemented framework impacts the user interaction, a navigation scenario with obstacles is used for validating the suitability of the gesture-based navigation.