The article presents selected results of research on the modeling of humanoid robots, including the results of neural modeling of human gait and its implementation in the environment MATLAB and Simulink with the use of Deep Learning Toolbox. The subject of the research was placed within the scope of the available literature on the subject. Then, appropriate research experiments on human movement along a given trajectory were developed. First, the method of measuring the parameters present in the experiment was established, i.e. input quantities (displacement of the left heel, displacement of the right heel) and output quantities (displacement of the measurement point of the human body in space). Then, research experiments were carried out, as a result of which numerical data were measured in order to use them for teaching and testing the Artificial Neural Network. The Perceptron Artificial Neural Network architecture was used to build a model of a neural human walk along a given trajectory. The obtained results were discussed and interpreted, drawing a number of important conclusions.
As part of this article, research work aimed at acquiring new knowledge regarding the analysis and assessment of arbitrarily selected gerontechnology: personal care robots for older adults. The results planned to be achieved under the article have not been reflected in previous scientific studies. Until now, no research has been carried out to assess this technology regarding heterogeneous criteria. The existing research results only concern the study of the acceptability of the technologies used by older people to improve their quality of life. The opinions of prospective potential users were not considered as well as their age and place of posting or education. Neither were marketing, social and ethical aspects, competitiveness or innovation. The author will use the proprietary methodology of prospective technology analysis (PAT) to analyse and evaluate the technology. This methodology allows assessing the current state of technology. It enables providing knowledge on characteristic features of the technology, current and potential applications of a given technology and necessary for the development of analysed resource technologies, as well as the impact of technology on the environment and the environment on technology.
The paper presents the gait framework for a biped robot on the Atlas robot example. The method utilizes inverted pendulum model and static stability controller with correction from IMU sensor. A straight-forward balance control strategy based on ankle joints control is proposed. The controller which stabilizes the robot during execution of the planned path is described. To show the efficiency of the proposed method the results obtained in the Virtual Robotics Challenge environment (Gazebo) are provided.
PL
Artykuł przedstawia system generowania chodu dla robotów dwunożnych na przykładzie robota Atlas. Metoda wykorzystuje model odwróconego wahadła oraz statyczny kontroler stabilności wraz z korekcją z sensora IMU. Zaproponowano prostą metodę utrzymywania równowagi w oparciu o sterowanie ruchami stóp robota. Opisano też kontroler stabilizujący robota podczas pokonywania zaplanowanej ścieżki. Zweryfikowano działanie zaproponowanych metod na robocie Atlas w symulatorze Virtual Robotics Challenge (Gazebo).
Artykuł prezentuje program rozwijający komunikację między robotami humanoidalnymi a ludźmi. Cel badań został osiągnięty za pomocą algorytmów pozwalających na odczytywanie wydrukowanych tekstów i wykonywanie na ich podstawie założonych czynności. Wiąże się to z wykorzystaniem konkretnych technik przetwarzania obrazów, jak: wyodrębnianie cech, rozpoznawanie wzorców i ich klasyfikacja oraz z komunikacją między robotem a zewnętrzną bazą danych.
EN
This article presents the program which expands the robot-human communication level. The aim of research was achieved by usage of the algorithms for reading printed information and performing actions based on the read text. It is connected to particular image processing fields like feature extraction, pattern recognition and classification as well as to the communication between robot and external database.
This paper presents a control system for a humanoid robot based on human body movement tracking. The system uses the popular Kinect sensor to capture the mo- tion of the operator and allows the small, low-cost, and proprietary robot to mimic full body motion in real time. Tracking controller is based on optimization-free algorithms and uses a full set of data provided by Kinect SDK, in order to make movements feasible for the considerably different kinematics of the humanoid robot compared to the human body kinematics. To maintain robot stability we implemented the balancing algorithm based on a simple geometrical model, which adjusts only the configuration of the robot’s feet joints, maintaining an unchanged imitated posture. Experimental results demonstrate that the system can successfully allow the robot to mimic captured human motion sequences.
W niniejszym artykule przedstawiono algorytmy sterowania robotem humanoidalnym firmy Futaba. Zaprezentowano wykorzystanie sztucznych sieci neuronowych, jako alternatywnego sposobu obliczenia kinematyki odwrotnej oraz wykorzystanie środowiska Microsoft Robotics Developer Studio do tworzenia złożonych, wielowątkowych aplikacji szeroko stosowanych w robotyce. Ponadto pokazano zastosowanie środowiska symulacyjnego VSE (Visual Simulation Environment) w procesie prototypowania algorytmów sterujących.
EN
This paper presents a control system for a Futaba humanoid robot [1]. It is equipped with a controller board based on a microcontroller with an ARM7TDMI core, a full set of inertial sensors and a 2.4 GHz wireless communication module. The controller uses the wireless communication module to send information about the robot state to a PC on which the controlling application is run. This paper focuses on the software part of the presented system (the hardware part has been presented in the first part of this paper). In order to develop a controlling algorithm, an analysis of robot kinematics was made and equations for direct kinematics were derived in consistency with the Denavit-Hartenberg convention. To eliminate the necessity of designating equations for inverse kinematics, which can be very complex due to the kinematic redundancy of the robot, an artificial neural network was used (Fig. 2). The application was written using the Microsoft Robotics Developer Studio designed for creating complex, multithread, distributed and scalable applications used in robotics. The application uses the data acquired by radio to implement the walking and balance-keeping algorithms. For visualization of the robot movement, testing and development of the algorithms without the risk of damaging the robot, a simulation in the Visual Simulation Environment, a part of the Microsoft Robotics Developer Studio, was created. A 3D model of the robot was used in this simulation (Fig. 4).
For a long time people have been interested in the similarity between living organisms and the engineering devices built by them. Recent developments in the area of service robotics show an increasing interest in personal robots. Those personal robots can help to handle daily work and to entertain people. Future service robots will more and more be able to communicate with humans in a natural way. The communication between humans is not only based on speech in fact movements and emotions are very important. The expression of those emotions is a combination of neck, eyes and skin movements. Therefore this paper presents the construction of the humanoid robot head ROMAN with artificial eyes and neck. The head includes actuators, sensors and mechanical parts which are all integrated into the head. The currents design enable the robot to include a complex sensors system and a complete emotional system.
PL
Od bardzo dawna ludzie są zainteresowani w podobieństwie budowanych przez siebie urządzeń technicznych i organizmów żywych. Aktualnie rozwój robotów usługowych pokazuje znaczny wzrost zainteresowania robotami osobistymi. Roboty osobiste mogą ułatwić i umilić codzienne życie. W przyszłości roboty usługowe będą mogły porozumiewać się z ludźmi w bardziej naturalny sposób. Komunikacja między ludźmi opiera się nie tylko na komunikacji werbalnej (słownej) lecz również w znacznej mierze na mimice ciała (wymowie ruchów) i emocjach wyrażanych przez mimikę twarzy. Emocje te są kombinacją ruchów szyi, oczu, i mięśni/skóry twarzy. W niniejszym artykule zaprezentowano rozwiązania konstrukcyjne robota humanoidalnego ROMAN, w szczególności głowy ze sztucznymi oczami i szyi. Głowa zawiera siłowniki, czujniki i układy mechaniczne zintegrowane w złożoną konstrukcję mechatroniczną naśladującą kształty i wybrane funkcje głowy człowieka. Aktualny stan projektu pozwala na włączenie skomplikowanego układu sensorycznego i wykonawczego do wyrażania emocji w sposób bardzo podobny jak to robią ludzie.
W artykule opisano zagadnienie budowy i sterowania manipulatora naśladującego ruch ramienia człowieka. Projekt konstrukcyjny wykonano w systemie Catia. Do napędu wykorzystano serwonapędy sterowane za pomocą mikrokontrolera. Interfejs użytkownika napisano w programie Visual Basic.
EN
In the paper an idea of making artificial arm imitating human's arm move is described. Mechanical part of manipulator is designed with the use of Catia system. As manipulator's drive units servomechanisms with microchip based controller are used. To control the arm a computer software, which serves as user interface, is built.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.