John Wiley & Sons Engineering Autonomous Vehicles and Robots Cover Offers a step-by-step guide to building autonomous vehicles and robots, with source code and accompa.. Product #: 978-1-119-57056-1 Regular price: $101.87 $101.87 Auf Lager

Engineering Autonomous Vehicles and Robots

The DragonFly Modular-based Approach

Liu, Shaoshan

Wiley - IEEE

Cover

1. Auflage März 2020
216 Seiten, Hardcover
Wiley & Sons Ltd

ISBN: 978-1-119-57056-1
John Wiley & Sons

Jetzt kaufen

Preis: 109,00 €

Preis inkl. MwSt, zzgl. Versand

Weitere Versionen

epubmobipdf

Offers a step-by-step guide to building autonomous vehicles and robots, with source code and accompanying videos

The first book of its kind on the detailed steps for creating an autonomous vehicle or robot, this book provides an overview of the technology and introduction of the key elements involved in developing autonomous vehicles, and offers an excellent introduction to the basics for someone new to the topic of autonomous vehicles and the innovative, modular-based engineering approach called DragonFly.

Engineering Autonomous Vehicles and Robots: The DragonFly Modular-based Approach covers everything that technical professionals need to know about: CAN bus, chassis, sonars, radars, GNSS, computer vision, localization, perception, motion planning, and more. Particularly, it covers Computer Vision for active perception and localization, as well as mapping and motion planning. The book offers several case studies on the building of an autonomous passenger pod, bus, and vending robot. It features a large amount of supplementary material, including the standard protocol and sample codes for chassis, sonar, and radar. GPSD protocol/NMEA protocol and GPS deployment methods are also provided. Most importantly, readers will learn the philosophy behind the DragonFly modular-based design approach, which empowers readers to design and build their own autonomous vehicles and robots with flexibility and affordability.
* Offers progressive guidance on building autonomous vehicles and robots
* Provides detailed steps and codes to create an autonomous machine, at affordable cost, and with a modular approach
* Written by one of the pioneers in the field building autonomous vehicles
* Includes case studies, source code, and state-of-the art research results
* Accompanied by a website with supplementary material, including sample code for chassis/sonar/radar; GPS deployment methods; Vision Calibration methods

Engineering Autonomous Vehicles and Robots is an excellent book for students, researchers, and practitioners in the field of autonomous vehicles and robots.

1 Affordable and Reliable Autonomous Driving Through Modular Design 1

1.1 Introduction 1

1.2 High Cost of Autonomous Driving Technologies 2

1.2.1 Sensing 2

1.2.2 HD Map Creation and Maintenance 3

1.2.3 Computing Systems 3

1.3 Achieving Affordability and Reliability 4

1.3.1 Sensor Fusion 4

1.3.2 Modular Design 5

1.3.3 Extending Existing Digital Maps 5

1.4 Modular Design 6

1.4.1 Communication System 7

1.4.2 Chassis 7

1.4.3 mmWave Radar and Sonar for Passive Perception 8

1.4.4 GNSS for Localization 8

1.4.5 Computer Vision for Active Perception and Localization 8

1.4.6 Planning and Control 8

1.4.7 Mapping 9

1.5 The Rest of the Book 9

1.6 Open Source Projects Used in this Book 10

References 11

2 In-Vehicle Communication Systems 13

2.1 Introduction 13

2.2 CAN 13

2.3 FlexRay 16

2.3.1 FlexRay Topology 16

2.3.2 The FlexRay Communication Protocol 17

2.4 CANopen 18

2.4.1 Object Dictionary 19

2.4.2 Profile Family 19

2.4.3 Data Transmission and Network Management 20

2.4.4 Communication Models 21

2.4.5 CANopenNode 21

References 22

3 Chassis Technologies for Autonomous Robots and Vehicles 23

3.1 Introduction 23

3.2 Throttle-by-Wire 23

3.3 Brake-by-Wire 25

3.4 Steer-by-Wire 25

3.5 Open Source Car Control 26

3.5.1 OSCC APIs 26

3.5.2 Hardware 27

3.5.3 Firmware 28

3.6 OpenCaret 29

3.6.1 OSCC Throttle 29

3.6.2 OSCC Brake 29

3.6.3 OSCC Steering 29

3.7 PerceptIn Chassis Software Adaptation Layer 30

References 34

4 Passive Perception with Sonar and Millimeter Wave Radar 35

4.1 Introduction 35

4.2 The Fundamentals of mmWave Radar 35

4.2.1 Range Measurement 36

4.2.2 Velocity Measurement 37

4.2.3 Angle Detection 38

4.3 mmWave Radar Deployment 38

4.4 Sonar Deployment 41

References 45

5 Localization with Real-Time Kinematic Global Navigation Satellite System 47

5.1 Introduction 47

5.2 GNSS Technology Overview 47

5.3 RTK GNSS 49

5.4 RTK-GNSS NtripCaster Setup Steps 52

5.4.1 Set up NtripCaster 52

5.4.2 Start NtripCaster 54

5.5 Setting Up NtripServer and NtripClient on Raspberry Pi 55

5.5.1 Install the Raspberry Pi System 55

5.5.2 Run RTKLIB-str2str on the Raspberry Pi 57

5.5.2.1 Running NtripServer on the Base Station Side 57

5.5.2.2 Running NtripClient on the GNSS Rover 58

5.6 Setting Up a Base Station and a GNSS Rover 59

5.6.1 Base Station Hardware Setup 59

5.6.2 Base Station Software Setup 60

5.6.3 GNSS Rover Setup 67

5.6.3.1 Rover Hardware Setup 67

5.6.3.2 Rover Software Setup 68

5.7 FreeWave Radio Basic Configuration 71

References 75

6 Computer Vision for Perception and Localization 77

6.1 Introduction 77

6.2 Building Computer Vision Hardware 77

6.2.1 Seven Layers of Technologies 78

6.2.2 Hardware Synchronization 80

6.2.3 Computing 80

6.3 Calibration 81

6.3.1 Intrinsic Parameters 81

6.3.2 Extrinsic Parameters 82

6.3.3 Kalibr 82

6.3.3.1 Calibration Target 83

6.3.3.2 Multiple Camera Calibration 83

6.3.3.3 Camera IMU Calibration 84

6.3.3.4 Multi-IMU and IMU Intrinsic Calibration 84

6.4 Localization with Computer Vision 85

6.4.1 VSLAM Overview 85

6.4.2 ORB-SLAM2 86

6.4.2.1 Prerequisites 86

6.4.2.2 Building the ORB-SLAM2 Library 87

6.4.2.3 Running Stereo Datasets 87

6.5 Perception with Computer Vision 87

6.5.1 ELAS for Stereo Depth Perception 88

6.5.2 Mask R-CNN for Object Instance Segmentation 89

6.6 The DragonFly Computer Vision Module 90

6.6.1 DragonFly Localization Interface 90

6.6.2 DragonFly Perception Interface 92

6.6.3 DragonFly+ 93

References 94

7 Planning and Control 97

7.1 Introduction 97

7.2 Route Planning 97

7.2.1 Weighted Directed Graph 98

7.2.2 Dijkstra's Algorithm 99

7.2.3 A* Algorithm 100

7.3 Behavioral Planning 100

7.3.1 Markov Decision Process 101

7.3.2 Value Iteration Algorithm 102

7.3.3 Partially Observable Markov Decision Process (POMDP) 103

7.3.4 Solving POMDP 104

7.4 Motion Planning 105

7.4.1 Rapidly Exploring Random Tree 105

7.4.2 RRT* 106

7.5 Feedback Control 107

7.5.1 Proportional-Integral-Derivative Controller 108

7.5.2 Model Predictive Control 108

7.6 Iterative EM Plannning System in Apollo 110

7.6.1 Terminologies 110

7.6.1.1 Path and Trajectory 110

7.6.1.2 SL Coordinate System and Reference Line 110

7.6.1.3 ST Graph 111

7.6.2 Iterative EM Planning Algorithm 112

7.6.2.1 Traffic Decider 113

7.6.2.2 QP Path and QP Speed 114

7.7 PerceptIn's Planning and Control Framework 116

References 118

8 Mapping 119

8.1 Introduction 119

8.2 Digital Maps 119

8.2.1 Open Street Map 120

8.2.1.1 OSM Data Structures 120

8.2.1.2 OSM Software Stack 121

8.2.2 Java OpenStreetMap Editor 121

8.2.2.1 Adding a Node or a Way 123

8.2.2.2 Adding Tags 123

8.2.2.3 Uploading to OSM 124

8.2.3 Nominatim 124

8.2.3.1 Nominatim Architecture 124

8.2.3.2 Place Ranking in Nominatim 125

8.3 High-Definition Maps 125

8.3.1 Characteristics of HD Maps 126

8.3.1.1 High Precision 126

8.3.1.2 Rich Geometric Information and Semantics 126

8.3.1.3 Fresh Data 126

8.3.2 Layers of HD Maps 126

8.3.2.1 2D Orthographic Reflectivity Map 127

8.3.2.2 Digital Elevation Model 127

8.3.2.3 Lane/Road Model 127

8.3.2.4 Stationary Map 127

8.3.3 HD Map Creation 127

8.3.3.1 Data Collection 127

8.3.3.2 Offline Generation of HD Maps 128

8.3.3.2.1 Sensor Fusion and Pose Estimation 128

8.3.3.2.2 Map Data Fusion and Data Processing 129

8.3.3.2.3 3D Object Location Detection 129

8.3.3.2.4 Semantics/Attributes Extraction 129

8.3.3.3 Quality Control and Validation 129

8.3.3.4 Update and Maintenance 129

8.3.3.5 Problems of HD Maps 130

8.4 PerceptIn's pi-Map 130

8.4.1 Topological Map 130

8.4.2 pi-Map Creation 131

References 133

9 Building the DragonFly Pod and Bus 135

9.1 Introduction 135

9.2 Chassis Hardware Specifications 135

9.3 Sensor Configurations 136

9.4 Software Architecture 138

9.5 Mechanism 142

9.6 Data Structures 144

9.6.1 Common Data Structures 144

9.6.2 Chassis Data 146

9.6.3 Localization Data 149

9.6.4 Perception Data 150

9.6.5 Planning Data 153

9.7 User Interface 158

References 160

10 Enabling Commercial Autonomous Space Robotic Explorers 161

10.1 Introduction 161

10.2 Destination Mars 162

10.3 Mars Explorer Autonomy 163

10.3.1 Localization 163

10.3.2 Perception 164

10.3.3 Path Planning 165

10.3.4 The Curiosity Rover and Mars 2020 Explorer 165

10.4 Challenge: Onboard Computing Capability 168

10.5 Conclusion 169

References 170

11 Edge Computing for Autonomous Vehicles 171

11.1 Introduction 171

11.2 Benchmarks 172

11.3 Computing System Architectures 173

11.4 Runtime 175

11.5 Middleware 177

11.6 Case Studies 178

References 179

12 Innovations on the Vehicle-to-Everything Infrastructure 183

12.1 Introduction 183

12.2 Evolution of V2X Technology 183

12.3 Cooperative Autonomous Driving 186

12.4 Challenges 188

References 189

13 Vehicular Edge Security 191

13.1 Introduction 191

13.2 Sensor Security 191

13.3 Operating System Security 192

13.4 Control System Security 193

13.5 V2X Security 193

13.6 Security for Edge Computing 194

References 196

Index 199
SHAOSHAN LIU, PHD, is Founder and CEO of PerceptIn, a full-stack visual intelligence company aimed at making scalable hardware/software integrated solutions for autonomous robotics systems. Liu holds a Ph.D. in Computer Engineering from University of California, Irvine and his research focuses on Edge Computing Systems, Robotics, and Autonomous Driving. Liu has over 40 publications and over 100 patents in autonomous systems. Liu is currently a Senior Member of IEEE, an ACM Distinguished Speaker, an IEEE Computer Society Distinguished Visitor, and a co-founder of the IEEE Computer Society Special Technical Community on Autonomous Driving Technologies.