Advances in intelligent robotics and collaborative automation / / editors, Richard Duro, Yuriy Kondratenko.

This book provides an overview of a series of advanced research lines in robotics as well as of design and development methodologies for intelligent robots and their intelligent components. It represents a selection of extended versions of the best papers presented at the Seventh IEEE International...

Full description

Saved in:
Bibliographic Details
:
TeilnehmendeR:
Place / Publishing House:Aalborg, Denmark : : River Publishers,, 2015.
©2015
Year of Publication:2015
Edition:1st ed.
Language:English
Series:River Publishers Series in Automation, Control and Robotics ; Volume 1
Physical Description:1 online resource (363 pages) :; illustrations (some color), charts, photographs, graphs, tables.
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Cover
  • Half Title - Advances in Intelligent Roboticsand Collaborative Automation
  • Series Page - RIVER PUBLISHERS SERIES IN AUTOMATION,CONTROLAND ROBOTICS
  • Title Page - Advances in Intelligent Roboticsand Collaborative Automation
  • Copy Right Page
  • Contents
  • Preface
  • List of Figures
  • List of Tables
  • List of Abbreviations
  • Chapetr 1 - A Modular Architecture for DevelopingRobots for Industrial Applications
  • Abstract
  • 1.1 Introduction
  • 1.2 Main Characteristics for Industrial Operation andDesign Decisions
  • 1.3 Implementation of a Heterogeneous ModularArchitecture Prototype
  • 1.3.1 Actuator Modules
  • 1.3.1.1 Slider module
  • 1.3.1.2 Telescopic module
  • 1.3.1.3 Rotational module
  • 1.3.1.4 Hinge module
  • 1.3.2 Connection Mechanism
  • 1.3.3 Energy
  • 1.3.4 Sensors
  • 1.3.5 Communications
  • 1.3.6 Control
  • 1.4 Some Configurations for Practical Applications
  • 1.4.1 Manipulators
  • 1.4.2 Climber andWalker Robots
  • 1.5 Towards Industrial Applications
  • 1.6 Conclusions
  • References
  • Chapter 2 - The Dynamic Characteristics of aManipulator with Parallel KinematicStructure Based on Experimental Data
  • Abstract
  • 2.1 Introduction
  • 2.2 Purpose and Task of Research
  • 2.3 Algorithm for the Structural Identification of theMultivariable Dynamic Object with the Help of theComplete Data
  • 2.4 Algorithm for the Structural Identification of theMultivariable Dynamic Object with the Help ofIncomplete Data
  • 2.5 The Dynamics of the Mechanism with a ParallelStructure Obtained by Means of the Complete DataIdentification
  • 2.6 The Dynamics of the Mechanism with a ParallelStructure Obtained by Means of the IncompleteData Identification
  • 2.7 Verification of the Structural Identification Results
  • 2.8 Conclusions
  • References
  • Chapter 3 - An Autonomous Scale Ship Model forParametric Rolling Towing Tank Testing
  • Abstract.
  • 3.1 Introduction
  • 3.2 System Architecture
  • 3.2.1 Data Acquisition
  • 3.2.2 Software Systems
  • 3.2.3 Speed Control
  • 3.2.4 Track-Keeping Control
  • 3.2.5 Other Components
  • 3.3 Testing
  • 3.3.1 Prediction System
  • 3.3.2 Prevention System
  • 3.3.3 Towing Tank Tests and Results
  • 3.3.3.1 Mathematical model validation
  • 3.3.3.2 Validation of stability diagrams
  • 3.3.3.3 Prediction system tests
  • 3.4 Conclusions and FutureWork
  • References
  • Chapter 4 - Autonomous Knowledge Discovery Basedon Artificial Curiosity-Driven Learningby Interaction
  • Abstract
  • 4.1 Introduction
  • 4.2 Proposed System and Role of Curiosity
  • 4.2.1 Interpretation from Observation
  • 4.2.2 Search for the Most Coherent Interpretation
  • 4.2.3 Human-Robot Interaction
  • 4.3 Validation Results by Simulation
  • 4.4 Implementation on Real Robot and Validation Results
  • 4.4.1 Implementation
  • 4.4.2 Validation Results
  • 4.5 Conclusions
  • References
  • Chapter 5 - Information Technology for InteractiveRobot Task Training ThroughDemonstration of Movement1
  • Abstract
  • 5.1 Introduction
  • 5.2 Conception and Principles of Motion Modeling
  • 5.2.1 Generalized Model of Motion
  • 5.2.2 Algorithm for Robot Task Training by Demonstration
  • 5.2.3 Algorithm for Motion Reproduction after Task Training byDemonstration
  • 5.2.4 Verification of Results for the Task of Training theTelecontrolled (Remote Controlled) Robot
  • 5.2.5 Major Advantages of Task Training by Demonstration
  • 5.3 Algorithms and Models for Teaching Movements
  • 5.3.1 Task Training by Demonstration of Movement amongthe Objects of the Environment
  • 5.3.2 Basic Algorithms for RobotTaskTraining by Demonstration
  • 5.3.3 Training Algorithm for the Environmental Survey Motion
  • 5.3.4 Training Algorithm for Grabbing a Single Object
  • 5.3.5 Special Features of the Algorithm for Reproduction ofMovements.
  • 5.3.6 Some Results of Experimental Studies
  • 5.3.7 Overview of the Environment for Task Training byDemonstration of the Movements of the Human Head
  • 5.3.8 Training the Robot to Grab Objects by Demonstration ofOperator Hand Movements
  • 5.4 Conclusions
  • References
  • Chapter 6 - A Multi-Agent Reinforcement LearningApproach for the Efficient Controlof Mobile Robots
  • Abstract
  • 6.1 Introduction
  • 6.2 Holonic Homogenous Multi-Agent Systems
  • 6.2.1 Holonic, Multi-Agent Systems
  • 6.2.2 Homogenous, Multi-Agent Systems
  • 6.2.3 Approach to Commitment and Coordination in H2 MAS
  • 6.2.4 Learning to Coordinate Through Interaction
  • 6.3 Vehicle Steering Module
  • 6.4 A Decomposition of Mobile Platform
  • 6.5 The Robot Control System Learning
  • 6.5.1 Learning of the Turning of a Module-Agent
  • 6.5.1.1 Simulation
  • 6.5.1.2 Verification
  • 6.5.2 Learning of the Turning of a Module-Agent
  • 6.5.2.1 Simulation
  • 6.5.2.2 Verification
  • 6.6 Conclusions
  • References
  • Chapter 7 - Underwater Robot Intelligent Control Basedon Multilayer Neural Network
  • Abstract
  • 7.1 Introduction
  • 7.2 Underwater Robot Model
  • 7.3 Intelligent NN Controller and Learning AlgorithmDerivation
  • 7.4 Simulation Results of the Intelligent NN Controller
  • 7.5 Modification of NN Control
  • 7.6 Conclusions
  • Acknowledgement
  • References
  • Chapter 8 - Advanced Trends in Design of SlipDisplacement Sensors for Intelligent Robots
  • Abstract
  • 8.1 Introduction
  • 8.2 Analysis of Robot Task Solving Based on SlipDisplacement Signals Detection
  • 8.3 Analysis of Methods for Slip Displacement SensorsDesign
  • 8.4 Mathematical Model of Magnetic Slip DisplacementSensor
  • 8.4.1 SDS Based on "Permanent Magnet/Hall Sensor" SensitiveElement and Its Mathematical Model
  • 8.4.2 Simulation Results
  • 8.5 Advanced Approaches for Increasing the Efficiencyof Slip Displacement Sensors.
  • 8.6 Advances in Development of Smart Grippers forIntelligent Robots
  • 8.6.1 Self-Clamping Grippers of Intelligent Robots
  • 8.6.2 Slip Displacement Signal Processing in Real Time
  • 8.7 Conclusions
  • References
  • Chapter 9 - Distributed Data Acquisition and ControlSystems for a Sized Autonomous Vehicle
  • Abstract
  • 9.1 Introduction
  • 9.2 The Testing Environment
  • 9.3 Description of the System
  • 9.4 Lane Detection
  • 9.4.1 In-Range Filter
  • 9.4.2 Hough-Transformation
  • 9.4.3 Lane Marks
  • 9.4.4 Polynomial
  • 9.4.5 Driving Lane
  • 9.4.6 Stop Line
  • 9.4.7 Coordinate Transformation
  • 9.5 Control of the Vehicle
  • 9.6 Results
  • 9.7 Conclusions
  • References
  • Chapter 10 - Polymetric Sensing in Intelligent Systems
  • Abstract
  • 10.1 Topicality of Polymetric Sensing
  • 10.2 Advanced Perception Components of IntelligentSystems or Robots
  • 10.2.1 Comparison of the Basics of Classical and PolymetricSensing
  • 10.2.2 Advanced Structure of Multi-Agent Intelligent Systems
  • 10.3 Practical Example of Polymetric Sensing
  • 10.3.1 Adding the Time Scale
  • 10.3.2 Adding the Information about the Velocity of theElectromagneticWave
  • 10.4 Efficiency of Industrial Polymetric Systems
  • 10.4.1 Naval Application
  • 10.4.1.1 Sensory monitoring agency SMA
  • 10.4.1.2 Information Environment Agency INE
  • 10.4.1.3 Operator Interface Agency OPI
  • 10.4.1.4 Advantages of the polymetric sensing
  • 10.4.1.5 Floating dock operation control system
  • 10.4.1.6 Onshore applications
  • 10.4.1.7 Special applications
  • 10.5 Conclusions
  • References
  • Chapter 11 - Design and Implementation of WirelessSensor Network Based on MultilevelFemtocells for Home Monitoring
  • Abstract
  • 11.1 Introduction
  • 11.2 Network Architecture and Femtocell Structure
  • 11.2.1 Body Sensor Network
  • 11.2.2 Ambient Sensor Network
  • 11.2.3 Emergency Sensor Network.
  • 11.2.4 Higher-level Architecture and Functional Overview
  • 11.3 Data Processing
  • 11.4 Experimental Results
  • 11.5 Conclusion
  • References
  • Chapter 12 - Common Framework Modelfor Multi-Purpose Underwater DataCollection Devices Deployed with RemotelyOperated Vehicles
  • Abstract
  • 12.1 Introduction
  • 12.2 Research Challenges
  • 12.2.1 Power Supply
  • 12.2.2 Communications
  • 12.2.3 Maintenance
  • 12.2.4 Law and Finance
  • 12.2.5 Possible Applications
  • 12.3 Mathematical Model
  • 12.3.1 System Definition
  • 12.3.2 Actuator Definition
  • 12.3.3 Sensor Definition
  • 12.4 ROV
  • 12.4.1 ROV Manipulator Systems
  • 12.4.2 Types of Offshore Constructions
  • 12.5 ROV Simulator
  • 12.6 Common Modular Framework
  • 12.7 Conclusions
  • References
  • Chapter 13 - M2M in Agriculture - Business Modelsand Security Issues
  • Abstract
  • 13.1 Introduction
  • 13.2 RelatedWork
  • 13.3 Communication and Standardization
  • 13.4 Business Cases
  • 13.4.1 Process Transparency (PT)
  • 13.4.2 Operations Data Acquisition (ODA)
  • 13.4.3 Remote Software Update (RSU)
  • 13.5 Business Models
  • 13.6 Economic Analysis
  • 13.7 Communication Security
  • 13.7.1 CA
  • 13.7.2 Communicating On-the-Go
  • 13.7.3 Covering Dead Spots
  • 13.7.4 Securing WLAN Infrastructures
  • 13.7.5 Firmware Update
  • 13.8 Resume
  • 13.9 Acknowledgement
  • References
  • Index
  • Editor's Biographies
  • Author's Biographies.