
Robot Intelligence Technology and Applications 5
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This book includes papers from the 5th International Conference on Robot Intelligence Technology and Applications held at KAIST, Daejeon, Korea on December 13-15, 2017. It covers the following areas: artificial intelligence, autonomous robot navigation, intelligent robot system design, intelligent sensing and control, and machine vision.
The topics included in this book are deep learning, deep neural networks, image understanding, natural language processing, speech/voice/text recognition, reasoning & inference, sensor integration/fusion/perception, multisensor data fusion, navigation/SLAM/localization, distributed intelligent algorithms and techniques, ubiquitous computing, digital creatures, intelligent agents, computer vision, virtual/augmented reality, surveillance, pattern recognition, gesture recognition, fingerprint recognition, animation and virtual characters, and emerging applications.
This book is a valuable resource for robotics scientists, computer scientists, artificial intelligence researchers and professionals in universities, research institutes and laboratories.
More details
Other editions
Additional editions

Persons
Content
- Intro
- Preface
- Contents
- Artificial Intelligence
- Artificial Intelligence Approach to the Trajectory Generation and Dynamics of a Soft Robotic Swallowing Simulator
- 1 Introduction
- 2 Generating Different Peristalsis Pattern in the Swallowing Robot
- 2.1 Matsuoka Oscillator
- 2.2 Problem Formulaton for the Parameter Estimation
- 3 Optical Motion Tracking and System Identification of the Swallowing Robot
- 3.1 Swallowing Robot's Motion Capture by Vicon
- 3.2 Processing the Captured Time-Series Data
- 3.3 State Initialisation
- 3.4 Defining Regression Problem
- 4 Results
- 4.1 Parameter Estimation Results
- 4.2 Preprocessing Results
- 4.3 Regression Results
- 5 Conclusion
- References
- Reinforcement Learning of a Memory Task Using an Echo State Network with Multi-layer Readout
- 1 Introduction
- 2 Method
- 2.1 Network
- 2.2 Learning
- 3 Experiment
- 4 Result
- 5 Conclusion
- References
- Selective Filter Transfer
- 1 Introduction
- 2 Method
- 2.1 Pretraining
- 2.2 Evaluating the Pre-trained Filters
- 2.3 Isolated Fine-Tuning and Re-initialization
- 2.4 Whole Network Fine-Tuning
- 3 Experiment
- 3.1 Database
- 3.2 Modified AlexNet
- 3.3 Transfer Learning
- 4 Discussion
- 4.1 An Ablation Study
- 5 Conclusion
- References
- Improving Deep Neural Networks by Adding Auxiliary Information
- 1 Introduction
- 2 The Effect of Additional Information
- 3 Model Architecture
- 4 Some Examples of Auxiliary Information
- 5 Experimental Results
- 6 Conclusion and Future Works
- References
- 5 Improved InfoGAN: Generating High Quality Images with Learning Disentangled Representation
- Abstract
- 1 Introduction
- 2 Motivation
- 3 Model Description
- 4 Experiments
- 4.1 Varying Code c and Fixed Noise z
- 4.2 Comparison of the Results with the Proposed Model to InfoGAN Results
- 5 Conclusion
- References
- Task-related Item-Name Discovery Using Text and Image Data from the Internet
- 1 Introduction
- 2 Related Works
- 3 Proposed Method
- 3.1 Text Data Mining
- 3.2 Images Collection
- 3.3 Item-Name Likelihood Measurement
- 4 Experimental Results
- 4.1 Text Data Mining
- 4.2 Item-Name Likelihood Measurement Experiment
- 5 Conclusion
- References
- An Exploration of the Power of Max Switch Locations in CNNs
- 1 Introduction
- 2 Related Work
- 3 The Power of Max Switch Locations
- 3.1 Image Reconstruction
- 3.2 Image Classification
- 4 Future Work and Discussion: Knowledge Transfer
- 4.1 The Max Transfer Pool
- 4.2 The Max Encourage Pool
- 5 Conclusion
- References
- An Empirical Study on the Optimal Batch Size for the Deep Q-Network
- 1 Introduction
- 2 Optimal Batch Size
- 3 Experiment
- 3.1 Environment
- 3.2 Result
- 4 Discussion
- 4.1 Completion Rate
- 4.2 Mean Training Time, Steps, and Time/Step
- 5 Conclusion
- References
- 9 Design and Development of Intelligent Self-driving Car Using ROS and Machine Vision Algorithm
- Abstract
- 1 Introduction
- 2 Mechanical Design
- 3 Electrical Design
- 3.1 RaspiCam Video Camera
- 3.2 Master Control Unit: Raspberry Pi B3 Microprocessor
- 3.3 Slave Control Unit: Arduino Development Platform
- 3.4 Wireless Serial Peripheral Interface Communication: nRF24L01 Module
- 3.5 Ping Sensors (Ultrasonic Sensor)
- 3.6 Adafruit Motor Drive Shield
- 3.7 Power Source: Lithium Polymer Battery
- 3.8 ROS: Robot Operating System
- 4 Algorithm Explanation
- 4.1 Resizing of Image Frame
- 4.2 Gaussian Blur Algorithm
- 4.3 Conversation from BGR (Blue, Green, Red) to HSV (Hue, Saturation, Value)
- 4.4 Removing Unwanted Area from Image Frame
- 4.5 Dynamic Threshold Parameter
- 4.6 Dynamic Threshold Setting
- 4.7 Masking Based on Dynamic Threshold Parameters
- 4.8 Applying Erosion, Opening, and Closing
- 4.9 New Regions of Interest for Turning Decisions/Taking Decisions for Motor Commands
- 4.10 Sending Commands to Arduino Through SPI
- 5 Conclusion
- Acknowledgements
- References
- 10 Intelligent Smart Glass for Visually Impaired Using Deep Learning Machine Vision Techniques and Robot Operating System (ROS)
- Abstract
- 1 Introduction
- 1.1 Related Work
- 1.2 Total Servable Market
- 1.3 Working Principle
- 2 Design and Fabrication of Smart Glass
- 3 Proposed Framework
- 3.1 Ultrasonic Hand Device
- 3.2 Computer Vision Glasses (Real-Time Object Detection Using Deep Learning)
- 3.2.1 Single Shot Detection
- 3.2.2 MobileNets
- 3.3 Emergency Situation
- 4 Result and Discussion
- 4.1 Obstacle Detection in the Environment
- 4.2 Validation from Visually Impaired People
- 5 Application
- 6 Conclusion and Future Discussion
- References
- A Proactive Robot Tutor Based on Emotional Intelligence
- 1 Introduction and Related Work
- 2 Proposed Model
- 3 Flowchart Mechanism of ECS
- 4 Scenario and Results
- 5 Conclusion
- References
- 12 Reusability Quality Metrics for Agent-Based Robot Systems
- Abstract
- 1 Introduction
- 2 Component-Based Software Engineering
- 2.1 Fenton and Melton Software Metric
- 2.2 Dharma Coupling Metric
- 3 Service-Oriented Architecture
- 3.1 Service-Oriented Device Architecture (SODA)
- 3.2 Business Commonality Metrics
- 3.3 Modularity Metrics
- 3.4 Adaptability Metrics
- 3.5 Standard Conformance Metrics
- 3.6 Discoverability Metrics
- 3.7 Reusability Metric
- 4 Case Study
- 4.1 Drone-Based Building Inspection System
- 4.2 Metric Measurement
- 5 Conclusion
- References
- Autonomous Robot Navigation
- SVM-Based Fault Type Classification Method for Navigation of Formation Control Systems
- 1 Introduction
- 2 Formation Control Algorithm
- 2.1 Networked Multi-Agent Model
- 2.2 Formation Control Law
- 3 Support Vector Machine Based Fault Classification with Fault Detection
- 3.1 Fault Detection
- 3.2 Fault Type Learning and Classification
- 4 Simulation
- 4.1 Simulation Setup
- 4.2 Simulation Results
- 5 Conclusion
- References
- Indoor Magnetic Pose Graph SLAM with Robust Back-End
- 1 Introduction
- 1.1 Basic Formulation
- 1.2 Design of Constraints
- 2 Magnetic Field Constraints
- 2.1 Magnetic Pivoting
- 2.2 Sequence-Based Loop Closing
- 3 Robust Back-End
- 3.1 Switchable Constraint
- 3.2 Max-Mixture
- 4 Experiments
- 4.1 Experimental Setup
- 4.2 Results
- 5 Conclusion
- References
- Multi-robot SLAM: An Overview and Quantitative Evaluation of MRGS ROS Framework for MR-SLAM
- 1 Introduction
- 2 Simultaneous Localization and Mapping
- 2.1 Mathematical Formulation
- 2.2 Online Versus Offline
- 2.3 SLAM Approaches
- 2.4 Map Representation
- 3 Multi-robot SLAM
- 3.1 Centralization Versus Decentralization
- 3.2 Communication and Information Sharing
- 3.3 Map Fusion
- 3.4 Mutli-robot SLAM Implementations
- 4 mrgs ROS Stack
- 4.1 SLAM Packages Used
- 4.2 Map Fusion
- 4.3 Technical Overview of ROS Implementation
- 5 Experimental Results
- 5.1 Experiment Setup
- 5.2 Evaluation Metrics
- 5.3 Results and Discussion
- 6 Conclusion
- References
- 16 A Reinforcement Learning Technique for Autonomous Back Driving Control of a Vehicle
- Abstract
- 1 Introduction
- 2 Vehicle Dynamics
- 3 Reinforcement Learning Algorithm
- 4 Simulation Results
- 5 Conclusions
- Acknowledgements
- References
- Rapid Coverage of Regions of Interest for Environmental Monitoring
- 1 Introduction
- 2 Problem Formulation
- 3 Adaptive Hierarchical Area Decomposition and Coverage
- 3.1 Adaptive Hierarchical Area Decomposition
- 3.2 Finding Subregions
- 3.3 Utility Function Design
- 4 Finding ROIs
- 5 Simulation Results
- 5.1 Finding Coverage Path that Connects the Desired Number of ROIs
- 5.2 Performance Comparison
- 6 Conclusion
- References
- Intelligent Robot System Design
- Embedded Drilling System Using Rotary-Percussion Drilling
- 1 Introduction
- 2 Locomotion Unit
- 2.1 Leg Mechanism
- 2.2 Caterpillar Gait
- 3 Drilling Unit
- 3.1 Drilling Methods
- 3.2 Mechanism of the Drilling Unit
- 4 Simulation
- 5 Conclusion
- References
- 19 Design and Development of Innovative Pet Feeding Robot
- Abstract
- 1 Introduction
- 2 Mechanical Design
- 2.1 Chassis
- 2.2 Mechanism
- 2.3 Finite Element Analysis
- 3 Pet Feeding Robot System
- 3.1 Graphical User Interface
- 3.2 Raspberry Pi-Arduino RF-SPI Communication
- 3.3 Camera Feedback
- 3.4 Mechanical Layer and Power Management
- 4 Result and Discussion
- 5 Modification with Robotic Arm
- 6 Problems and Challenges
- 7 Conclusion and Future Discussion
- Acknowledgements
- References
- 20 SignBot, Sign-Language Performing Robot, Based on Sequential Motion of Servo Motor Arrays
- Abstract
- 1 Introduction
- 2 System Design and Structure
- 2.1 Mechanical Design of SignBot
- 2.2 Servo Mechanism
- 2.3 Robot Hands' Movements
- 3 Result and Discussion
- 4 Conclusion
- References
- 21 Isolated Bio-Regenerative System for Vertical Farming Through Robots in Space Explorations
- Abstract
- 1 Introduction
- 1.1 Need for Exploring Extra-Terrestrial Life Support
- 1.2 Challenges of Extraterrestrial Life Support
- 2 Challenges in Bioregenerative System in Space
- 2.1 Effect of Gravity on Such System
- 2.2 Elevated Microbial Concentration in a Closed System
- 3 Proposed Solution for Such System
- 3.1 Isolated Chamber
- 3.2 Dimensions of the Isolated Chamber with Respect to the Dragon Spacecraft
- 3.3 Stress Analysis of the Isolation Chamber During the Launch. Physical Properties of the Material
- 3.4 Use of Robots
- 4 Control of Robots in the Absence of Human Intervention
- 5 Conclusion
- References
- 22 A Mobile Social Bar Table Based on a Retired Security Robot
- Abstract
- 1 Introduction
- 2 Before and After
- 3 How does a Bar Table Behave?
- 4 Designed to Wait
- 5 Preliminary Testing
- 6 Conclusion
- References
- I Remember What You Did: A Behavioural Guide-Robot
- 1 Introduction
- 2 Background and Motivation
- 3 Memory and Experience in EEGS
- 4 Evaluation
- 4.1 Experiment Design
- 5 Conclusion
- References
- 24 Robot Supporting for Deaf and Less Hearing People
- Abstract
- 1 Introduction
- 2 Structures of Robot
- 3 Communication of Robot for the Deaf People
- 4 Technical Solution of Gesture Recognition
- 5 Conclusions
- Acknowledgements
- References
- 25 The Use of Machine Learning for Correlation Analysis of Sentiment and Weather Data
- Abstract
- 1 Introduction
- 2 Big Data
- 3 Sentiment Analysis on Social Media Data
- 4 The Sentimental Analysis with Weather Data
- 5 Twitter Dataset
- 6 Sentiment Pattern Analysis
- 7 Experimental Results
- 8 Conclusion
- Acknowledgements
- References
- Design and Analysis of a Novel Sucked-Type Underactuated Hand with Multiple Grasping Modes
- 1 Introduction
- 2 Sucked-Type Underactuacted Hand
- 2.1 Mechanical Structure
- 2.2 Vacuum System
- 2.3 Three Grasping Modes
- 3 Modeling and Analysis
- 3.1 Kinematic Model
- 3.2 Mechanical Equilibrium
- 4 Experiment
- 4.1 Model Validation
- 4.2 Effective Suction Cups
- 4.3 Grasping Modes Test
- 5 Conclusion
- References
- 27 Robotizing the Bio-inspiration
- Abstract
- 1 Introduction
- 1.1 The Maiden Companionship
- 1.2 The Contemporary Apprehension
- 1.3 Outfit of a Soft Robot
- 1.4 Paper Organization
- 2 Soft Robotics Design Techniques and Materials
- 3 Sensors and Actuators in Soft Robotics
- 4 Discussion
- 5 Conclusion, Key Challenges and the Future Work
- References
- Intelligent Sensing and Control
- 28 An Observer Design Technique for Improving Velocity Estimation of a Gimbal System
- Abstract
- 1 Introduction
- 2 Configuration of a CMG
- 3 Review of a Velocity Observer
- 4 Experiment
- 4.1 Experimental Setup
- 4.2 Experimental Results
- 5 Conclusion
- Acknowledgements
- References
- 29 Voice Controlled Multi-robot System for Collaborative Task Achievement
- Abstract
- 1 Introduction
- 2 Framework for Machine Cooperation and Interaction
- 2.1 System Overview
- 2.2 Voice User Interaction
- 2.2.1 Voice Interaction Overview
- 2.2.2 Voice Interaction Design
- 2.3 Robot Navigation
- 2.3.1 Map Construction
- 2.3.2 Localization
- 2.3.3 Path Planning
- 2.4 Task Achievement
- 3 Experiments
- 3.1 Map Generation
- 3.2 Navigation
- 3.3 Task Achievement
- 4 Conclusion
- References
- 30 The Control of an Upper Extremity Exoskeleton for Stroke Rehabilitation by Means of a Hybrid Active Force Control
- Abstract
- 1 Introduction
- 2 Control Architecture
- 3 Results and Discussion
- 4 Conclusion
- Acknowledgements
- References
- 31 Intellectual Multi Agent Control of Tripod
- Abstract
- 1 Introduction
- 2 Statement of the Problem
- 3 Decupling of the Model Tripod
- 4 Solution of the Design Task
- 5 Control Algorithm of Tripod
- 6 Conclusion
- Acknowledgements
- References
- 32 Estimation and Recognition of Motion Segmentation and Pose IMU-Based Human Motion Capture
- Abstract
- 1 Introduction
- 2 Node Architecture
- 3 Kinematics
- 4 Communications
- 5 Experiments and Discussions
- 6 Conclusion
- Acknowledgements
- References
- 33 Fault Diagnosis of a Robot Manipulator Based on an ARX-Laguerre Fuzzy PID Observer
- Abstract
- 1 Introduction
- 2 Problem Statements
- 3 ARX-Laguerre Fuzzy PID Observation Method
- 3.1 Dynamic Modeling Based on ARX-Laguerre
- 3.2 Fault Diagnosis
- 4 Results and Discussion
- 4.1 Case 1 (Normal Condition)
- 4.2 Case 2 (Actuator Fault Condition)
- 4.3 Case 3 (Sensor Fault Condition)
- 4.4 Case 4 (Actuator and Sensor Fault Condition)
- 5 Conclusions
- Acknowledgements
- References
- A Two-Level Approach to Motion Planning of Soft Variable-Length Manipulators
- 1 Introduction
- 2 Motion Planning Algorithm
- 2.1 Problem Formulation
- 2.2 Algorithm Overview
- 2.3 Interim Target Generator
- 2.4 Configuration Generator
- 2.5 Heuristic Motion Selection in Task Space
- 3 Simulation Results
- 3.1 Setup
- 3.2 Comparison Experiments
- 3.3 Performance Evaluation
- 3.4 Extensional Experiments
- 4 Discussions
- 5 Conclusion
- References
- A Grasp Strategy for Polygonal Objects Using a Honeycomb Pneumatic Network Soft Gripper
- 1 Introduction
- 2 Honeycomb Pneumatic Network Soft Gripper
- 3 Grasp Planning of Soft Gripper
- 3.1 Grasp Planning
- 3.2 Feasible Grasping Solution
- 3.3 Evaluation Function
- 3.4 Solution Procedure of Grasping
- 3.5 Relative Form Closure Theory
- 4 Experimental Verification
- 4.1 Simulated Environment
- 4.2 Experimental Result and Discussion
- 5 Conclusion
- References
- A Parameterized Description of Force Output of Soft Arms in Full Workspace
- 1 Introduction
- 2 Load Ability and Workspace
- 2.1 Workspace-Load Cloud
- 3 Simulation Result
- 3.1 Setup
- 3.2 Fitting and Prognosis Experiments
- 4 Conclusion
- References
- 37 Intelligent Multi-fingered Dexterous Hand Using Virtual Reality (VR) and Robot Operating System (ROS)
- Abstract
- 1 Introduction
- 2 Design and Manufacturing of Hand/Forearm
- 3 Working Principle
- 4 Electrical System and Control of the Robotic Arm
- 4.1 Master Control Unit
- 4.2 Slave Control Unit
- 5 Result and Discussion
- 5.1 Application
- 5.2 Conclusion and Future Discussion
- Acknowledgements
- References
- FEA Evaluation of Ring-Shaped Soft-Actuators for a Stomach Robot
- 1 Introduction
- 2 FEA Design and Experimental Methods
- 2.1 Basic Structure and Working Principle
- 2.2 FEA Method
- 3 Results
- 3.1 Experiment with a Fixed Pressure for the Four Models
- 3.2 Experiment with a Maximum Applied Pressure Without a Distortion on the Actuators
- 4 Discussion
- 5 Conclusion
- References
- Machine Vision
- 39 Detection and Classification of Vehicle Types from Moving Backgrounds
- Abstract
- 1 Introduction
- 2 VRDI Dataset
- 3 Offline Learning
- 3.1 Training Sample Selections
- 3.2 HOG Feature Extraction and Classification
- 4 Online Training
- 4.1 Initial ROIs Detection
- 4.1.1 Object Extraction Using Background Subtraction
- 4.1.2 Background Updating
- 4.1.3 Object Localisation
- 4.2 ROI Tracking and Updating
- 5 Experiment and Discussion
- 5.1 Performance Metrics
- 5.2 Experimental Results
- 6 Conclusion
- References
- Multi-object Tracking with Pre-classified Detection
- 1 Introduction
- 2 Proposed Method
- 2.1 Detection Classification
- 2.2 Track Tree Updating
- 2.3 High Uncertainty Tree Pruning
- 3 Experimental Evaluation
- 3.1 Comparison of Our Tracker with Two or Three Categories
- 3.2 MOT16 Result Comparison
- 4 Conclusion
- References
- Autonomous 3D Model Generation of Unknown Objects for Dual-Manipulator Humanoid Robots
- 1 Introduction
- 1.1 Related Work
- 1.2 Basic Methodology
- 2 Tracking the Gripper's Movements
- 3 Model Creation
- 3.1 Disabling Collision Checking
- 3.2 Selecting Poses
- 3.3 Filtering of Sensor Data and Robot Links
- 3.4 Transforming Points to the Gripper Frame
- 3.5 Normal Iterative Closest Point (NICP) Registration
- 3.6 Changing Hands
- 3.7 Merging Both Partial Models
- 3.8 Building the Mesh of Model
- 4 Experimental Results
- 5 Conclusions
- 6 Future Work
- References
- 42 Adaptive Planar Vision Marker Composed of LED Arrays for Sensing Under Low Visibility
- Abstract
- 1 Introduction
- 2 Materials and Methods
- 2.1 Image Processing Algorithms for the LED Marker Detection
- 2.2 Experiments Under the Low Visibility Conditions
- 3 Result and Discussion
- 3.1 Reconstruction of LED Matrix Displayed Markers
- 3.2 Detection Under the Low Visibility Environments
- 4 Conclusions and Future Work
- Acknowledgements
- References
- Development of Robust Recogintion Algorithm of Retro-reflective Marker Based on Visual Odometry for Underwater Environment
- 1 Introduction
- 2 Methodology
- 2.1 Retro-reflective Marker
- 2.2 Marker Recognition Algorithm
- 3 Result
- 3.1 Experiment
- 3.2 Conclusion
- References
- 44 A Robust Estimation of 2D Human Upper-Body Poses Using Fully Convolutional Network
- Abstract
- 1 Introduction
- 2 Related Research Trends
- 2.1 Skeleton Extraction Using Depth Information
- 2.2 Skeleton Extraction Using RGB Image Information
- 3 Pose Estimation Algorithm
- 3.1 Fully Convolutional Network
- 3.2 Pose Estimation Using Joint Confidence Map
- 4 Evaluation
- 4.1 Datasets for Experiments
- 4.2 Training and Testing Method
- 4.3 Experimental Results
- 5 Conclusion
- Acknowledgements
- References
- 45 Surface Crack Detection in Concrete Structures Using Image Processing
- Abstract
- 1 Introduction
- 2 Proposed Crack Detection Algorithm
- 2.1 Image Preprocessing
- 2.2 Noise Filtering
- 3 Discussion and Conclusions
- References
- 46 Evaluation of High-Speed Image Processing for Low Latency Control of a Mechatronic System
- Abstract
- 1 Introduction
- 2 Background
- 2.1 Semi-automated Foosball Table Control System
- 2.2 Latency in Control Systems
- 2.3 Related Work
- 3 Experiment Design
- 3.1 Aim
- 3.2 Methodology
- 3.3 Test Platforms
- 3.4 Data Analysis
- 4 Results
- 5 Discussion
- 5.1 Immediate Usefulness of Results
- 5.2 Comparison of Performance
- 5.3 Automated Foosball
- 6 Conclusions
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.