Time Series Predictive Control in Robotics, livre ebook

This book presents the latest advances for the frontier cross disciplinary field of robotics, intelligent control and learning. Seven chapters are provided to cover the key common theories and technologies of robots, including the robot mapping and navigation, robot recharging and smart power management, robot arm manipulation, unmanned vehicle control, intelligent manufacturing systems, etc. The book proposes a unique new perspective using time series prediction to control robots. Especially with the fast increasing of various data in robotics, this new robot control mode using time series prediction has become very important. The book provides the complete cases for the most popular application scenes of robot predictive control. By this first monograph on the topic of robot time series predictive control in the world, author provides important references for the engineers, scientists and students in the field of robotics and artificial intelligence.

Preface..................................................... III

Abbreviations................................................ V

CHAPTER 1

Introduction................................................. 1

1.1Robotics and Control Technology ............................ 1

1.1.1Robotics ......................................... 1

1.1.2Robotics Control Technology .......................... 4

1.2 TimeSeries Forecasting in Robotics Control .................... 5

1.2.1 TimeSeries Forecasting Objectives...................... 5

1.2.2 TimeSeries Forecasting Methods ....................... 8

1.3Predictive Control in Robotics .............................. 10

1.3.1Uncertainty Problems in Predictive Control of Robotics ...... 10

1.3.2 ModelPredictive Control ............................. 13

1.3.3Significance and Purpose of Research .................... 14

1.4 Scopeof This Book ....................................... 15

References.................................................. 18

CHAPTER 2

RobotNavigation Position Time Series Predictive Control .............. 23

2.1Introduction ............................................ 23

2.2 RobotNavigation Position Time Series Measurement ............. 24

2.3 RobotNavigation Position Time Series Uncertainty Analysis ....... 25

2.4 RobotNavigation Position Time Series Statistical Forecasting Method................................................ 25

2.4.1 ARIMAForecasting Algorithm ........................ 26

2.4.2ARIMA-GARCH Forecasting Algorithm ................. 30

2.5 RobotNavigation Position Time Series Intelligent Forecasting Method................................................ 35

2.5.1 RBFNeural Network Forecasting Algorithm .............. 35

2.5.2 ElmanNeural Network Forecasting Algorithm ............. 38

2.5.3Extreme Learning Machine Forecasting Algorithm .......... 41

2.6 RobotNavigation Position Time Series Deep Learning Forecasting Method................................................ 44

2.6.1 LSTMDeep Neural Network Forecasting Algorithm ......... 45

2.6.2 ESNDeep Neural Network Forecasting Algorithm .......... 48

2.7Comparative Analysis of Forecasting Performance ................ 51

2.8 RobotAnti-Collision Monitoring and Control Based on Navigation PositionForecasting ...................................... 52

2.9Conclusions............................................. 53

References.................................................. 53

CHAPTER 3

MobileRobot Power Time Series Predictive Control ................... 57

3.1Introduction ............................................ 57

3.2 MobileRobot Power Time Series Measurement .................. 58

3.3 MobileRobot Power Time Series Uncertainty Analysis ............ 59

3.4 MobileRobot Power Time Series Statistical Forecasting Method ..... 60

3.4.1Experimental Design ................................ 60

3.4.2Modeling Steps .................................... 61

3.4.3Forecasting Results ................................. 63

3.5 MobileRobot Power Time Series Intelligent Forecasting Method ..... 64

3.5.1Experimental Design ................................ 65

3.5.2Modeling Steps .................................... 68

3.5.3Forecasting Results ................................. 70

3.6 MobileRobot Power Time Series Deep Learning Forecasting Method . 71

3.6.1Experimental Design ................................ 71

3.6.2Modeling Steps .................................... 73

3.6.3Forecasting Results ................................. 76

3.7Comparative Analysis of Forecasting Performance ................ 78

3.7.1Analysis of Statistical Methods ........................ 78

3.7.2Analysis of Intelligent Methods ........................ 78

3.7.3Analysis of Deep Learning Methods ..................... 79

3.8 MobileRobot Delivery Process Control Based on Power Forecasting . . 80

3.9Conclusions............................................. 80

References.................................................. 81

CHAPTER 4

Robot ArmTime Series Predictive Control .......................... 83

4.1Introduction ............................................ 83

4.2 RobotArm Time Series Measurement ......................... 84

4.3 RobotArm Time Series Uncertainty Analysis ................... 85

4.4 RobotArm Time Series Statistical Forecasting Method ............ 85

4.4.1Pandit–Wu Forecasting Algorithm ...................... 86

4.4.2KF-ARMA Forecasting Algorithm ...................... 88

4.5 RobotArm Time Series Intelligent Forecasting Method............ 93

4.5.1 RELMForecasting Algorithm ......................... 93

4.5.2XGBoost Forecasting Algorithm........................ 97

4.5.3 GRNNForecasting Algorithm ......................... 101

4.6 RobotArm Time-Series Deep Learning Forecasting Method ........ 104

4.6.1Autoencoder Deep Neural Network Forecasting Algorithm .... 104

4.6.2 DeepBelief Network Forecasting Algorithm ............... 107

4.7Comparative Analysis of Forecasting Performance ................ 110

4.7.1Analysis of Statistical Methods ........................ 110

4.7.2Analysis of Intelligent Methods ........................ 111

4.7.3Analysis of Deep Learning Methods ..................... 111

4.8 RobotArm Positioning Control Based on Arm Forecasting ......... 112

4.9Conclusions............................................. 113

References.................................................. 113

CHAPTER 5

UnmannedVehicle Time Series Predictive Control .................... 115

5.1Introduction ............................................ 115

5.2Unmanned Vehicle Time Series Measurement ................... 118

5.3Unmanned Vehicle Time Series Uncertainty Analysis ............. 119

5.4Unmanned Vehicle Time Series Statistical Forecasting Method ...... 119

5.4.1Kalman Filter Forecasting Algorithm .................... 119

5.4.2 FuzzyTime Series Forecasting Algorithm ................. 122

5.5Unmanned Vehicle Time Series Intelligent Forecasting Method ...... 124

5.5.1 ElmanNeural Network Forecasting Algorithm ............. 125

5.5.2 NARNeural Network Forecasting Algorithm .............. 128

5.5.3 ANFISNeural Network Forecasting Algorithm ............. 130

5.6Unmanned Vehicle Time Series Deep Learning Forecasting Method ... 134

5.6.1 RNNDeep Neural Network Forecasting Algorithm .......... 134

5.6.2 LSTMDeep Neural Network Forecasting Algorithm ......... 137

5.6.3 GRUDeep Neural Network Forecasting Algorithm .......... 139

5.7Comparative Analysis of Forecasting Performance ................ 141

5.7.1Analysis of Statistical Methods ........................ 141

5.7.2Analysis of Intelligent Methods ........................ 142

5.7.3Analysis of Deep Learning Methods ..................... 142

5.8Unmanned Vehicle Navigation Control Based on Multi-Source PositionTime Series Fusion ................................ 142

5.8.1Unmanned Vehicle Fusion Positioning ................... 142

5.8.2Unmanned Vehicle Navigation Control ................... 144

5.9Unmanned Vehicle Charging Control Based on Multi-Source Power Time Series Fusion ....................................... 145

5.10Conclusions............................................. 146

References.................................................. 147

CHAPTER 6

WearableAssistive Robot Time Series Predictive Control ............... 151

6.1Introduction ............................................ 151

6.2Wearable Assistive Robot Time Series Measurement .............. 152

6.3Wearable Assistive Robot Time Series Uncertainty Analysis ........ 154

6.4Wearable Assistive Robot Time Series Statistical Forecasting Method . 155

6.4.1Experimental Design ................................ 155

6.4.2Modeling Step ..................................... 160

6.4.3Forecasting Results ................................. 162

6.5Wearable Assistive Robot Time Series Intelligent Forecasting Method . 165

6.5.1Experimental Design ................................ 165

6.5.2Modeling Step ..................................... 167

6.5.3Forecasting Results ................................. 171

6.6Wearable Assistive Robot Time-Series Deep Learning Forecasting Method................................................ 174

6.6.1Experimental Design ................................ 174

6.6.2Modeling Step ..................................... 176

6.6.3Forecasting Results ................................. 179

6.7Comparative Analysis of Forecasting Performance ................ 180

6.8Wearable Assistive Robot Motion Control Based on Forecasting ..... 181

6.9Conclusions............................................. 182

References.................................................. 183

CHAPTER 7

IntelligentManufacturing Performance Prediction and Application ........ 187

7.1Introduction ............................................ 187

7.2 DataAcquisition ......................................... 189

7.2.1Data-Driven Method ................................ 190

7.2.2Model-Driven Method ............................... 190

7.3Prediction Modeling ...................................... 193

7.3.1Regression Algorithms ............................... 193

7.3.2Artificial Neural Network (ANN) ....................... 199

7.3.3Comparison Analysis ................................ 202

7.4Application ............................................. 204

7.4.1System Configuration ................................ 204

7.4.2 TheOther Application ............................... 216

7.5Conclusions............................................. 217

References.................................................. 218