Bachelor + Master Publishing
811 Bachelorarbeiten, 533 Masterarbeiten, 10.103 Diplomarbeiten

Online-Learning in Humanoid Robots

Online-Learning in Humanoid Robots
Über dieses Buch
  • Art: Diplomarbeit
  • Autor: Jörg Conradt
  • Abgabedatum: Februar 2001
  • Umfang: 114 Seiten
  • Dateigröße: 2,1 MB
  • Note: 1,0
  • Institution / Hochschule: Technische Universität Berlin Deutschland
  • ISBN (eBook): 978-3-8324-4858-5
  • ISBN (Paperback) :
    978-3-8324-4858-5 P
  • ISBN (CD) :978-3-8324-4858-5 CD
  • Sprache: Englisch
  • Prämierung:
  • Arbeit zitieren: Conradt, Jörg Februar 2001: Online-Learning in Humanoid Robots, Hamburg: Diplomica Verlag
  • Schlagworte: Robotik, Robot-Motion-Control, Neuroinformatics

Diplomarbeit von Jörg Conradt

Abstract:

Humanoid Robotic Systems have gained an increasing significance in the research world within the last few years. Just five years ago, there were hardly any human-like robots in the world, and those available did not represent human properties at all. They neither looked nor behaved like human beings. Today, a variety of research groups around the world is starting to work on topics related to humanoid robots, and it is very likely that these robots will become important within the upcoming decades even beyond the realm of science.

Trying to determine what humanoid robots are, a first draft of a definition might read as follows: such robots are to be called humanoid robots which - to some extent - are able to live and interact with the everyday human world, and represent certain human features, like cognitive or acting abilities. The main strength of such humanoid robots lies in their ability to operate in surroundings that have been designed for humans in the first place. Humanoid robots can be imagined to become useful assistants for every-day life in areas as diverse as:

- Rescue and clearing of dangerous situations.

- Janitorial services, Housekeeping.

- Security services.

- Care-taking in hospitals, recreational facilities.

- Entertainment.

In all these fields, close human interaction is a core issue and can be regarded as the minimum common basis. The interaction happens on many different levels, from physical touch to gesture recognition and the processing of spoken language. On cognitive issues like the two last named, much research has been done in the past few years. One has, however, to keep in mind that also the physical appearance, e.g. smoothness of motions, is an important issue when designing humanoid robots.

Table of Contents:

FOREWORD 1
1. INTRODUCTION 2
1.1 INTRODUCING THE AREA OF HUMANOID ROBOTICS 2
1.2 MECHANICAL DESIGN FOR HUMANOID ROBOTS 3
1.3 CONTROLLING HUMANOID ROBOTS 4
1.4 EXAMPLES OF TODAY'S HUMANOID ROBOTS 5
1.5 THE PURPOSE OF THE THESIS 9
2. A BRIEF RECAPITULATION OF BASIC ROBOT CONTROL 10
2.1 INTRODUCTION TO ROBOT CONTROL 10
2.2 CONTROLLING THE EXECUTION OF DESIRED TRAJECTORIES 12
2.3 THE FEEDBACK CONTROL FUNCTION 14
2.4 THE FEED-FORWARD CONTROL FUNCTION 17
2.5 ESTIMATING DYNAMICS USING RIGID BODY ASSUMPTIONS 18
2.6 RECAPITULATION 22
2.7 CONTROL OF HUMANOID ROBOTS 23
3. INTRODUCTION TO ROBOT LEARNING 25
3.1 GENERAL REMARKS ON ROBOT LEARNING 25
3.2 THE BIAS / VARIANCE TRADEOFF 27
3.3 GLOBAL VERSUS LOCAL LEARNING STRATEGIES 29
3.4 THE CURSE OF DIMENSIONALITY 31
3.5 ONLINE-LEARNING 32
3.6 LEARNING INVERSE DYNAMICS 34
3.7 RESULTS 34
4. THE LEARNING ALGORITHM LWPR 36
4.1 ADVANTAGES OF LEARNING APPROACHES 36
4.2 DESIRED ALGORITHMIC PROPERTIES 38
4.3 INPUT DATA PREPROCESSING 45
4.4 PREDICTING OUTPUT DATA USING LWPR 47
4.5 LEARNING PARAMETERS 50
4.6 THE FINAL LWPR ALGORITHM 57
4.7 PROPERTIES OF LWPR 59
5. EVALUATION OF LWPR'S PERFORMANCE ON ARTIFICIAL DATA 61
5.1 INTRODUCTION 61
5.2 ONE DIMENSIONAL FUNCTION FITTING 61
5.3 TWO-DIMENSIONAL FUNCTION FITTING WITH SHIFTING INPUT DISTRIBUTIONS 65
5.4 LIMITING THE COMPUTATIONAL COMPLEXITY 68
5.5 DISCUSSION 69
6. THE HUMANOID ROBOT 71
6.1 HARDWARE FOR ROBOT CONTROL 71
6.2 SOFTWARE FOR ROBOT CONTROL 74
6.3 THE SARCOS ROBOTIC ARM 77
7. EVALUATION OF THE ARM'S MOTION 81
7.1 GENERATING TRAJECTORIES FOR LEARNING 81
7.2 LEARNING INVERSE DYNAMICS 85
7.3 LEARNING RESULTS ON SAMPLED DATA 87
7.4 VERIFYING THE RESULTS ON REAL MOTION 91
8. CONCLUSION 96
8.1 DISCUSSION 96
8.2 BRIEF INTRODUCTION TO USING LWPR FOR INVERSE KINEMATICS ESTIMATION 97
8.2 FUTURE RESEARCH 99
REFERENCES 101
SHORT GERMAN SUMMARY 104
EIDESSTATTLICHE ERKLÄRUNG 105

Arbeit zitieren:
Conradt, Jörg Februar 2001: Online-Learning in Humanoid Robots, Hamburg: Diplomica Verlag

Schlagworte:
Robotik, Robot-Motion-Control, Neuroinformatics

Entdecken Sie mehr zum Thema

FPGA Design
FPGA Design Diplomarbeit von Thomas Strutzmann | März 2003 | Note 1,0
diplom.de
Bachelor + Master Publishing

Hermannstal 119 k
22119 Hamburg

Fon: +49 (0) 40 655992-0
Fax: +49 (0) 40 655992-22

Service-Telefon

Rufen Sie uns an:
+49 (0) 40 655992-0

Mo-Fr
09.00-16.00 Uhr

diplom.de in den Medien

Folgen Sie uns bei Twitter & werden Sie diplom.de-Fan bei Facebook!
Schreibtipps unserer Lektoren, Neuigkeiten aus dem Verlagsalltag und das Expertenwissen unserer Autoren als Tweet & Post!
Wir freuen uns auf Sie!

diplom.de BACHELOR + MASTER PUBLISHING

Bachelorarbeiten, Masterarbeiten, Diplomarbeiten, Magisterarbeiten, Dissertationen und andere Abschlussarbeiten aus allen Fachbereichen und Hochschulen können Sie bei uns als eBook sofort per Download beziehen oder sich auf CD oder als Buch zusenden lassen. Seit mehr als 15 Jahren ist diplom.de der seriöse, professionelle und erfolgreiche Partner für die Veröffentlichung wissenschaftlicher Abschlussarbeiten.

© Diplomica Verlag GmbH 1996-2011, AG Hamburg HRB 80293 - GF Björn Bedey, USt-IdNr.: DE214910002 - Verkehrsnummer: 12285 - Impressum
Index der Arbeiten - Index der Autoren