LEADER 12947nam 22007575 450 001 9910506375803321 005 20251113174729.0 010 $a3-030-89098-8 024 7 $a10.1007/978-3-030-89098-8 035 $a(CKB)4950000000281766 035 $a(MiAaPQ)EBC6784756 035 $a(Au-PeEL)EBL6784756 035 $a(OCoLC)1277148885 035 $a(PPN)258296259 035 $a(DE-He213)978-3-030-89098-8 035 $a(EXLCZ)994950000000281766 100 $a20211017d2021 u| 0 101 0 $aeng 135 $aurcnu|||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aIntelligent Robotics and Applications $e14th International Conference, ICIRA 2021, Yantai, China, October 22?25, 2021, Proceedings, Part II /$fedited by Xin-Jun Liu, Zhenguo Nie, Jingjun Yu, Fugui Xie, Rui Song 205 $a1st ed. 2021. 210 1$aCham :$cSpringer International Publishing :$cImprint: Springer,$d2021. 215 $a1 online resource (853 pages) 225 1 $aLecture Notes in Artificial Intelligence,$x2945-9141 ;$v13014 311 08$a3-030-89097-X 320 $aIncludes bibliographical references and index. 327 $aIntro -- Preface -- Organization -- Contents - Part II -- Hybrid System Modeling and Human-Machine Interface -- Generation of Collision-Free Five-Axis Sweep Scanning Path Using Graphics Engine -- 1 Introduction -- 2 Preliminary -- 3 Collision-Free Scanning Path Planning -- 3.1 Image-Based Representation of Collision-Free Conditions -- 3.2 Collision Detection by Graphics Engine -- 3.3 Incremental Algorithm for Generating Admissible Areas -- 4 Experiment -- 5 Conclusion -- References -- Multi-robot Cooperative System Modeling and Control Software Development -- 1 Introduction -- 2 Multi-robot Collaborative System Modeling -- 2.1 Coordinated Operation Model -- 2.2 Kinematic Modeling -- 2.3 Dynamics Modeling -- 3 Collaborative Control System Frame and Methods -- 3.1 Control Frame Design -- 3.2 Position and Force Distribution -- 3.3 Motor Control and Motion Planning -- 3.4 Multi-arm Compliance Control Method -- 4 Control System Software -- 4.1 Demand Analysis -- 4.2 Overall Design -- 4.3 Design of Each Layer -- 4.4 Main Modules -- 4.5 Software Interface -- 5 Experiment Verification -- 5.1 Experimental System -- 5.2 Motion Planning Experiment -- 5.3 Compliance Control Experiment -- 6 Conclusion -- References -- Gesture Recognition and Conductivity Reconstruction Parameters Analysis with an Electrical-Impedance-Tomography (EIT) Based Interface: Preliminary Results -- 1 Introduction -- 2 The Hardware and Algorithm of Measurement System -- 2.1 Hardware -- 2.2 Construction Algorithms -- 3 Methods -- 3.1 Gesture Recognition Based on EIT -- 3.2 Conductivity Reconstruction Parameters Analysis -- 4 Results -- 4.1 Recognition Accuracy -- 4.2 The Effect of EIT Parameters -- 5 Discussions and Conclusions -- References -- Robot Manipulation Skills Learning -- Depth from Shading Based on Online Illumination Estimation Under RAMIS Environment -- 1 Introduction. 327 $a2 Shape from Shading -- 3 Method -- 4 Experiment and Result -- 5 Conclusion -- References -- Self-learning Visual Servoing for Robot Manipulation in Unstructured Environments -- 1 Introduction -- 2 Descriptions on Visual Servoing -- 3 Robust MCSIS Learning Estimator -- 4 Nonparametric Visual Servoing Framework -- 5 Results and Discussions -- 6 Conclusion -- References -- Obstacle Avoidance Methods Based on Geometric Information Under the DMPs Framework -- 1 Introduction -- 2 Obstacle Avoidance Based on Geometric Information -- 2.1 The Fundamental Principle of DMPs Framework -- 2.2 Obstacle Avoidance Based on Ellipsoidal Offset of Static Obstacles -- 2.3 Obstacle Avoidance Based on Dangerous Zone Offset of a Moving Obstacle -- 3 Simulation and Analysis -- 3.1 Simulation -- 3.2 Trajectory Evaluation in Static Obstacle Avoidance -- 4 Real Experiments in Static and Dynamic Environment -- 5 Conclusion -- References -- Integrated Classical Planning and Motion Planning for Complex Robot Tasks -- 1 Introduction -- 2 Literture Review -- 3 Methods -- 3.1 High-Level Task Planning -- 3.2 Low-Level Motion Planning -- 4 Experimental Results -- 5 Conclusion -- References -- Deep Reinforcement Learning for an Anthropomorphic Robotic Arm Under Sparse Reward Tasks -- 1 Introduction -- 2 Related Work -- 2.1 Curiosity Module -- 2.2 Curriculum Learning -- 2.3 Hierarchy Reinforcement Learning -- 3 Background -- 3.1 Reinforcement Learning -- 3.2 Policy Gradient Optimization -- 4 Method -- 4.1 Base Algorithm: Deep Deterministic Policy Gradient -- 4.2 Techniques for Sparse Rewards -- 5 Experiments and Results -- 5.1 Environments -- 5.2 Experimental Details and Results -- 6 Conclusion -- References -- Design and Experiment of Actuator for Semi-automatic Human-Machine Collaboration Percutaneous Surgery -- 1 Introduction -- 2 Actuator Design -- 2.1 Actuator Structure. 327 $a2.2 Guide Hole -- 3 Minimize Damage Insertion -- 4 Human-Machine Collaboration Workflow -- 5 Experiment and Results -- 6 Discussion -- References -- A Robot Learning from Demonstration Platform Based on Optical Motion Capture -- 1 Introduction -- 2 System Setup -- 2.1 The Optical MoCap System -- 2.2 Human-Machine Interface -- 3 Robot Learning from Demonstration -- 3.1 Data Pre-process -- 3.2 Policy Learning -- 4 Robot Assembly Experiment -- 4.1 Experiment Settings -- 4.2 Experimental Results and Discussion -- 5 Conclusion -- References -- Real-Time Collision Avoidance in a Dynamic Environment for an Industrial Robotic Arm -- 1 Introduction -- 2 Methods -- 2.1 Learning Dynamic Movement Primitives -- 2.2 Cost Function Formulation -- 2.3 Obstacle Position Estimation -- 2.4 Experimental Results -- 2.5 Conclusion -- References -- DOREP 2.0: An Upgraded Version of Robot Control Teaching Experimental Platform with Reinforcement Learning and Visual Analysis -- 1 Introduction -- 2 Overview of the DOREP 2.0 -- 2.1 DOREP 2.0 Components and Operational Procedures -- 2.2 Synchronization Between MATLAB and Bus Server -- 2.3 SIA Robot Toolbox -- 3 Visual Robot Inverted Pendulum Control Based on Reinforcement Learning -- 3.1 Introduction of Reinforcement Learning Algorithm -- 3.2 Introduction of Visual Analysis -- 3.3 Results of Experiment -- 4 Conclusion -- References -- An Improved TCN-Based Network Combining RLS for Bearings-Only Target Tracking -- 1 Introduction -- 2 Dynamic Model of Bearings-Only Target Tracking -- 3 TCN-Based Network Combining RLS -- 3.1 TCN-Based Network -- 3.2 Recursive Least Squares -- 4 Simulation -- 4.1 Initial Conditions -- 4.2 Simulation Results -- 5 Conclusions -- References -- Learning Robot Grasping from a Random Pile with Deep Q-Learning -- 1 Introduction -- 2 Background -- 2.1 Reinforcement Learning -- 2.2 Deep Q-learning Network. 327 $a3 Design of Grasping Strategy with DQN -- 3.1 Representations of the Target State -- 3.2 Representations of the Grasping Action -- 3.3 Design of the Rewards -- 3.4 Design of the Q-networks -- 3.5 Training of the Grasping DQN -- 4 Simulation and Experiment -- 4.1 Simulations -- 4.2 Strategy Transferring from Simulation to Real -- 5 Conclusion -- References -- Surplus Force Control Strategy of an Active Body-Weight Support Training System -- 1 Introduction -- 2 Mechanical Structure of BWSTS -- 3 Active Loading Compound Control Strategy -- 4 Surplus Force Compensation Control Strategy -- 5 Conclusion -- References -- Process Learning of Robot Fabric Manipulation Based on Composite Reward Functions -- 1 Introduction -- 2 Problem Description -- 3 Proposed Method -- 3.1 Compound Reward Function -- 3.2 Network Structure -- 4 Experiments -- 4.1 Single Task -- 4.2 Process Task -- 4.3 Compound Reward Function -- 5 Conclusions -- References -- Surface Crack Detection of Rubber Insulator Based on Machine Vision -- 1 Introduction -- 2 Surface Crack Detection System of Rubber Insulator -- 3 Surface Crack Detection Algorithm of Rubber Insulator -- 3.1 Dimension-Increased Bilateral Filtering -- 3.2 Image Segmentation -- 3.3 Crack Detection and Localization -- 4 Experiment and Analysis -- 5 Conclusion -- References -- A Hierarchical Force Guided Robot Assembly Method Using Contact State Model -- 1 Introduction -- 2 The Description of Robot Assembly -- 3 Hierarchical Force Guided Assembly Strategy -- 3.1 Assembly Process Modeling -- 3.2 Assembly Process -- 3.3 Phased Guidance Stage -- 4 Experiments -- 4.1 Experimental Platform -- 4.2 Results -- 5 Conclusion -- References -- A BAS-Based Strategy for Redundant Manipulator Tracking Continuous Moving Object in 3D Relative Velocity Coordinate -- 1 Introduction -- 2 Problem Formulation -- 2.1 Tracking Moving Object. 327 $a2.2 3D Relative Velocity Coordinate -- 2.3 The Principle for Tracking Moving Object -- 3 Control System Design -- 4 Simulation Results -- 4.1 Simulation Methodology -- 4.2 The Results of Tracking Moving Target -- 5 Conclusions -- References -- Leveraging Expert Demonstrations in Robot Cooperation with Multi-Agent Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 2.1 Multi-Agent Reinforcement Learning -- 2.2 Imitation Learning -- 3 Methods -- 3.1 Reinforcement Learning Setup -- 3.2 Multiple Hindsight Experience Replay -- 3.3 Robot Teams Learning from Demonstrations -- 3.4 Imperfect Demonstrations -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Robot Training -- 4.3 Imperfect Demonstrations -- 5 Conclusions -- References -- Fault Diagnosis Method Based on Control Performance of Single-Leg Robot -- 1 Introduction -- 2 Robot Model Description -- 2.1 Physical Model -- 2.2 Feedback Linearization of Nonlinear Dynamic Model -- 3 LQ Controller Design -- 4 Fault Detection Based on LQ Control Performance -- 5 Verified Result -- 6 Conclusion -- References -- Robot Bolt Skill Learning Based on GMM-GMR -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Dynamic Time Warping (DTW) -- 3.2 GMM-GMR -- 4 Experimernts Results -- 4.1 The Setting of the Experimental Environment -- 4.2 The Results of the Experiment -- 5 Conclusion -- References -- Traversability Analysis for Quadruped Robots Navigation in Outdoor Environment -- 1 Instruction -- 2 Related Works -- 3 Terrain Traversability Analysis -- 3.1 Geometric Features Extraction -- 3.2 Visual Features from CNN -- 3.3 Fusing of Geometric and Visual Features -- 4 Experiment Rusults -- 4.1 CNN Training Results -- 4.2 Traversability Analysis -- 5 Conclusions -- References -- MicroNano Materials, Devices, and Systems for Biomedical Applications. 327 $aA Calibration Method of Compliant Planar Parallel Manipulator. 330 $aThe 4-volume set LNAI 13013 ? 13016 constitutes the proceedings of the 14th International Conference on Intelligent Robotics and Applications, ICIRA 2021, which took place in Yantai, China, during October 22-25, 2021. The 299 papers included in these proceedings were carefully reviewed and selected from 386 submissions. They were organized in topical sections as follows: Robotics dexterous manipulation; sensors, actuators, and controllers for soft and hybrid robots; cable-driven parallel robot; human-centered wearable robotics; hybrid system modeling and human-machine interface; robot manipulation skills learning; micro_nano materials, devices, and systems for biomedical applications; actuating, sensing, control, and instrumentation for ultra-precision engineering; human-robot collaboration; robotic machining; medical robot; machine intelligence for human motion analytics; human-robot interaction for service robots; novel mechanisms, robots and applications; space robot and on-orbit service; neural learning enhanced motion planning and control for human robot interaction; medical engineering. 410 0$aLecture Notes in Artificial Intelligence,$x2945-9141 ;$v13014 606 $aArtificial intelligence 606 $aComputer vision 606 $aComputer engineering 606 $aComputer networks 606 $aNumerical analysis 606 $aArtificial Intelligence 606 $aComputer Vision 606 $aComputer Engineering and Networks 606 $aNumerical Analysis 606 $aComputer Engineering and Networks 615 0$aArtificial intelligence. 615 0$aComputer vision. 615 0$aComputer engineering. 615 0$aComputer networks. 615 0$aNumerical analysis. 615 14$aArtificial Intelligence. 615 24$aComputer Vision. 615 24$aComputer Engineering and Networks. 615 24$aNumerical Analysis. 615 24$aComputer Engineering and Networks. 676 $a629.892 702 $aLiu$b Xin-Jun 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910506375803321 996 $aIntelligent Robotics and Applications$9773722 997 $aUNINA