978-981-5285-58-1

Chapter 1 Introduction to Adaptive Gripping Technologies
       1.1 Importance of Adaptive Grippers in Modern Automation
       1.2 Evolution of Adaptive Grippers
       1.3 Overview of Grasping and Manipulation Challenges
             1.3.1 Single-drive adaptive grippers
             1.3.2 Perception and control of clamping force
             1.3.3 Intelligent grasping strategy for irregular parts
             1.3.4 Flexible precision assembly technology based on manipulator
             1.3.5 Existing problems and research topics
       1.4 Structure and Scope of the Book
       Reference
Chapter 2 Design of a Microgripper for Micro/nano Manipulation
       2.1 Introduction
       2.2 Mechanical Structure
       2.3 Modeling And Analysis
             2.3.1 Kinematics modeling
             2.3.2 Static modeling
             2.3.3 Dynamic Modeling
       2.4 Finite Element Analysis
       2.5 Experimental Tests
       2.6 Conclusions
       References
Chapter 3 Design of a Three-Finger Adaptive Robotic Gripper
       3.1 Introduction
       3.2 Mechanical System Structure
             3.2.1 Motor Driver
             3.2.2 Finger Structure
             3.2.3 Flexible Differential Mechanism
       3.3 Working Principle of Adaptive Grasping
             3.3.1 Planar Analysis of Grasping Motion
             3.3.2 Spatial Analysis of Grasping Motion
       3.4 Flexure Hinge Design
             3.4.1 Flexure Hinge Structure
             3.4.2 Finite Element Simulation
       3.5 Adaptive Grasping Experiments
       3.6 Conclusions
       References
Chapter 4 Design and Control of a Four-finger Adaptive Gripper
       4.1 Introduction
       4.2 Gripper design
             4.2.1 Design Considerations
             4.2.2 Gripper Structure
             4.2.3 Working Principle
       4.3 Modeling of the Gripper
             4.3.1 Kinematics Analysis
             4.3.2 Statics Analysis
       4.4 Gripper control
       4.5 Experimental Evaluations
             4.5.1 Prototype Development
             4.5.2 Adaptive Grasp
             4.5.3 Grasping Force Control
             4.5.4 Fixture to Fixture (F2F) Assembly
             4.5.5 Discussions
       4.6 Conclusion
       References
Chapter 5 Design and Control of a Variable-Stiffness Gripper
       5.1 Introduction
       5.2 Development of Variable-stiffness Finger (VSF)
             5.2.1 Working Principle of Stiffness Variation
             5.2.2 Stiffness Modeling
             5.2.3 Design of the VSF
       5.3 VSF Gripper and its Characteristics
             5.3.1 Prototype
             5.3.2 Grasping Control & Strategy
             5.3.3 Stiffness Estimation
             5.3.4 Robustness & Safety Characteristics
             5.3.5 Significance of Stiffness Variation
       5.4 Application Experiments of The VSF Gripper
             5.4.1 Adapt to Object’s Position & Shapes
             5.4.2 Versatile Object Grasping
       5.5 Conclusion
       References
Chapter 6 Design and Control of a Dexterous Hand
       6.1 Introduction
       6.2 Physical Prototype
             6.2.1 Mechanism Description
             6.2.2 Actuator System
             6.2.3 Design Features
       6.3 Control Scheme
       6.4 Modeling and Analysis
             6.4.1 Kinematics Analysis
             6.4.2 Joint Torque Computation
       6.5 Conclusion
       Reference
Chapter 7 Design of a Robotic Gripper for Container Twist Lock Unlocking
       7.1 Introduction
       7.2 Mechanism Characteristics
             7.2.1 Mechanism Kinematics
             7.2.2 Effects of the Design Parameters
       7.3 Mechanism Optimization
       7.4 Case study
             7.4.1 Mechanism Simulation
             7.4.2 Applied on a Robotic Gripper
       7.5 Conclusion
       References
Chapter 8 Assembly of T-Joint Frame Structures with a Fixturing Assistive Gripper (FAG)
       8.1 Introduction
       8.2 Problem description
       8.3 System Overview
             8.3.1 Fixturing Assistive Gripper Development
             8.3.2 FFA Workcell Setup
       8.4 Modeling and Algorithm development
             8.4.1 2D Vision Algorithm for Pose Recognition
             8.4.2 Dual Robot Cooperation
             8.4.3 Robot Path Planning
             8.4.4 Assembly Sequence Planning
       8.5 Experiments and Verification
             8.5.1 FAG Method vs Traditional Method
             8.5.2 FFA Workcell Verification
       8.6 Conclusion
       References
Chapter 9 Full Range Gripping Force Sensing Method for Adaptive Grippers
       9.1 Introduction
       9.2 Full-range Gripping Force Sensing Principle
             9.2.1 Gripping force sensing mechanism
             9.2.2 Gripping force sensing base
             9.2.3 Structural Stiffness Calculation
             9.2.4 force sensing principle
       9.3 Finite Element Simulation Analysis
             9.3.1 Finite element analysis method
             9.3.2 Relative error analysis
       9.4 Experimental validation
             9.4.1 Static calibration experiment
             9.4.2 Analysis of relative error caused by position
       9.5 Conclusion
       References
Chapter 10 Grasping Detection Based on Deep Learning
       10.1 Introduction
       10.2 Grasp detection methods overview
       10.3 Key point detection model KPDM
       10.4 Pose Solving Module
       10.5 Experiment
             10.5.1 Data acquisition and annotation
             10.5.2 Training scheme
             10.5.3 Model comparison experiment
             10.5.4 Grasping experiment
       10.6 Conclusion
       References
Chapter 11 Grasp Pose Detection Based on Regions of Interest
       11.1 Introduction
       11.2 YOLOv4 Object Detection Algorithm
       11.3 Lightweight Rotated Object Detection Algorithm R-YOLOv4
             11.3.1 Backbone Network
             11.3.2 SimAM
             11.3.3 ASFF Module
             11.3.4 Five-Parameter Representation
             11.3.5 Approximate SkewIoU Loss
       11.4 Object Grasp Pose Detection
             11.4.1 Five-Dimensional Grasp Rectangle
             11.4.2 Principles of DeepLabV3+ Algorithm
             11.4.3 Improved DeepLabV3+ Model
             11.4.4 Training Loss
       11.5 Experimental Results and Analysis
             11.5.1 Object Detection
             11.5.2 Model Parameter Analysis
             11.5.3 Ablation Experiments
             11.5.4 Performance Comparison
             11.5.5 Image Preprocessing
             11.5.6 Multi-Object Grasp Pose Estimation
       11.6 Conclusion
       References
Chapter 12 Original Stable Grasping Based on E-HRGrasp Detection
       12.1 Introduction
       12.2 Original Stable Grasping
       12.3 E-HRGrasp
             12.3.1 Coordinate Attention Module
             12.3.2 Multi-Level Feature Aggregation Module
       12.4 Experiments
             12.4.1 Datasets and Experiment Setup
             12.4.2 Experiments and Analysis on Custom Dataset
             12.4.3 Ablation Studies
       12.5 Conclusion
       References
Chapter 13 Grasping Pose Estimation Based on Semantic Segmentation and Rotating Target Detection
       13.1 Introduction
       13.2 Description of robotic arm gripping method
             13.2.1 Description of the problem
             13.2.2 Detection frame mapped to gripping position in 3D space
       13.3 Network Model
             13.3.1 Faster-RCNN model
             13.3.2 Feature Pyramid Module
             13.3.3 Semantic Segmentation Module
             13.3.4 R-Centernet Based Position Estimation Module
       13.4 Simulation and Experimentation of Autonomous Gripping
             13.4.1 Grabbing the dataset
             13.4.2 Comparative Experiments on Crawl Detection Networks
             13.4.3 Pose Estimation and Dynamic Simulation Experiment
             13.4.4 Robot actual grasping experiment
       13.5 Conclusion
       References
Chapter 14 Grasping Detection Network with Uncertainty Estimation
       14.1 Introduction
       14.2 Related work
             14.2.1 Deep Learning for Grasping Detection
             14.2.2 Semi-Supervised Learning
             14.2.3 Model Uncertainty Estimation
       14.3 Proposed Approach
             14.3.1 RGB-D Fusion Based Feature Pyramid Network
             14.3.2 LocNet: Grasping Location Heatmap
             14.3.3 PoseNet: Grasping Pose with Uncertainty Estimation
             14.3.4 Confidence-Driven Mean Teacher
       14.4 Implementation Details
             14.4.1 Grasping Dataset and Preprocessing
             14.4.2 Training of Grasping Detection Network
             14.4.3 Semi-Supervised Domain Adaptation
       14.5 Experiments and Discussions
             14.5.1 Grasping Detection Network with Certainty Estimation
             14.5.2 Confidence-Driven Mean Teacher Domain Adaptation
       14.6 Conclusions
       References
Chapter 15 Weight Imprinting Classification-Based Force Grasping with a Variable-Stiffness Robotic Gripper
       15.1 Introduction
       15.2 Universal Force Grasping Framework For Variable Stiffness Gripper
             15.2.1 Overview of the Framework
             15.2.2 Structure-Controlled Variable Stiffness Gripper
       15.3 Center-Guided Weight Imprinting For Grasping Classification
             15.3.1 Preliminaries and Analysis of Weight Imprinting
             15.3.2 Enhancing Imprinting by Center-Guided Embedding
       15.4 Vision-Based Grasping Force Sensing and Regulation
             15.4.1 Visual Marks Localization and Rectification
             15.4.2 Segmentation and Deflection Angle Detection
             15.4.3 Stiffness Adjustment and Grasping Force Regulation
       15.5 Experiments and Discussion
             15.5.1 Evaluation of Imprinting Classification Performance
             15.5.2 Evaluation of Force Sensing Resolution
             15.5.3 Evaluation of Force Grasping Performance
             15.5.4 Grasping Soft Plastic Cup of Water
             15.5.5 Grasping of Various Objects
       15.6 Conclusion
       References
Index