Atjaunināt sīkdatņu piekrišanu

E-grāmata: Introduction to Self-Driving Vehicle Technology [Taylor & Francis e-book]

(Queens University Belfast, UK)
Citas grāmatas par šo tēmu:
  • Taylor & Francis e-book
  • Cena: 142,30 €*
  • * this price gives unlimited concurrent access for unlimited time
  • Standarta cena: 203,28 €
  • Ietaupiet 30%
Introduction to Self-Driving Vehicle TechnologyPalielināt
Citas grāmatas par šo tēmu:
Taylor & Francis e-booksMore info about Taylor & Francis e-books
Rokasgrāmatas mājas lapa: https://www.taylorfrancis.com/books/9780429316777

This book aims to teach the core concepts that make Self-driving vehicles (SDVs) possible. It is aimed at people who want to get their teeth into self-driving vehicle technology, by providing genuine technical insights where other books just skim the surface. The book tackles everything from sensors and perception to functional safety and cybersecurity. It also passes on some practical know-how and discusses concrete SDV applications, along with a discussion of where this technology is heading. It will serve as a good starting point for software developers or professional engineers who are eager to pursue a career in this exciting field and want to learn more about the basics of SDV algorithms. Likewise, academic researchers, technology enthusiasts, and journalists will also find the book useful.

Key Features:

  • Offers a comprehensive technological walk-through of what really matters in SDV development: from hardware, software, to functional safety and cybersecurity
  • Written by an active practitioner with extensive experience in series development and research in the fields of Advanced Driver Assistance Systems (ADAS) and Autonomous Driving
  • Covers theoretical fundamentals of state-of-the-art SLAM, multi-sensor data fusion, and other SDV algorithms.
  • Includes practical information and hands-on material with Robot Operating System (ROS) and Open Source Car Control (OSCC).
  • Provides an overview of the strategies, trends, and applications which companies are pursuing in this field at present as well as other technical insights from the industry.
Preface xiii
Author xv
Acknowledgment xvii
1 Introduction
1(10)
1.1 Brief history of SDV technology
2(1)
1.2 What is an SDV?
3(1)
1.3 What benefits does SDV technology offer?
4(1)
1.4 Why do we need another book about autonomous cars?
5(1)
1.5 Whom is this book aimed at?
6(1)
1.6 How is this book structured?
6(1)
1.7 Disclaimer
7(4)
References
9(2)
2 Hardware
11(38)
2.1 Sensors
11(26)
2.1.1 Key considerations
13(1)
2.1.2 Types of sensors
14(1)
2.1.2.1 Radars
15(2)
2.1.2.2 Lidars
17(4)
2.1.2.3 Ultrasonic sensors
21(3)
2.1.2.4 Cameras
24(3)
2.1.2.5 Global Navigation Satellite Systems
27(3)
2.1.2.6 Inertial Measurement Units
30(4)
2.1.2.7 Odometry sensors
34(3)
2.2 Computing platform
37(3)
2.2.1 Key considerations
37(1)
2.2.2 Examples of computing platforms
38(2)
2.3 Actuator Interface
40(4)
2.3.1 Components of an actuator interface
40(3)
2.3.2 Enabling drive-by-wire systems
43(1)
2.4 In-vehicle networks
44(1)
2.5 Summary
45(4)
References
47(2)
3 Perception
49(58)
3.1 Localization
50(8)
3.1.1 Localization based on GNSS
51(1)
3.1.2 Localization based on wheel odometry
51(1)
3.1.3 Localization based on INS
51(1)
3.1.4 Localization with external references
51(1)
3.1.5 Localization based on lidar
52(1)
3.1.6 Localization based on cameras
53(5)
3.1.7 Localization based on multi-sensor data fusion
58(1)
3.2 Mapping
58(3)
3.2.1 Occupancy grid maps
58(1)
3.2.2 Feature maps
59(1)
3.2.3 Relational maps
60(1)
3.2.4 Other types of maps
61(1)
3.3 SLAM
61(16)
3.3.1 Filtering approach
63(1)
3.3.1.1 Kalman filter
63(2)
3.3.1.2 Particle filter
65(3)
3.3.2 Optimization approach
68(2)
3.3.2.1 Graph-based SLAM
70(4)
3.3.2.2 Bundle adjustment
74(3)
3.4 Object detection
77(11)
3.4.1 Feature extraction
80(1)
3.4.1.1 Histogram of oriented gradients
81(1)
3.4.1.2 Scale-invariant feature transform
82(2)
3.4.1.3 Maximally stable extremal regions
84(1)
3.4.2 Classification
85(1)
3.4.2.1 Support vector machine
85(1)
3.4.2.2 Random forest
86(1)
3.4.2.3 Artificial neural network
87(1)
3.5 Multi-sensor data fusion
88(9)
3.5.1 Classifications
88(4)
3.5.2 Techniques
92(1)
3.5.2.1 Probabilistic approach
92(2)
3.5.2.2 Evidential approach
94(3)
3.5.2.3 Other approaches
97(1)
3.6 Summary
97(10)
References
99(8)
4 Architecture
107(28)
4.1 Functional architecture
107(13)
4.1.1 Perception
108(1)
4.1.2 Planning
109(1)
4.1.2.1 Route planning
109(1)
4.1.2.2 Behavioral planning
110(2)
4.1.2.3 Motion planning
112(4)
4.1.3 Vehicle control
116(1)
4.1.3.1 Lane keeping
117(1)
4.1.3.2 Adaptive cruise control
118(1)
4.1.3.3 Lane changing
119(1)
4.2 System architecture
120(2)
4.2.1 Hardware layer
121(1)
4.2.2 Middleware layer
121(1)
4.2.3 Application layer
122(1)
4.3 SDV middleware examples
122(8)
4.3.1 Robot operating system
122(2)
4.3.2 Automotive data and time-triggered framework
124(2)
4.3.3 Automotive open system architecture
126(4)
4.4 Summary
130(5)
References
133(2)
5 Putting it all together
135(26)
5.1 Preparation
136(2)
5.1.1 Choosing your vehicle
136(1)
5.1.2 Vehicle network
136(1)
5.1.3 Sensor selection and calibration
137(1)
5.2 Development
138(14)
5.2.1 Open source car control
139(1)
5.2.1.1 OSCC controllers
140(1)
5.2.1.2 X-by-wire systems
141(1)
5.2.1.3 OSCC software
141(2)
5.2.2 Installing middleware and device drivers
143(1)
5.2.2.1 ROS
143(1)
5.2.2.2 Sensor drivers
143(1)
5.2.2.3 CAN driver
144(1)
5.2.3 Implementing the software
145(1)
5.2.3.1 Hand-coded development
145(1)
5.2.3.2 Model-based development
146(1)
5.2.4 Map building and localization
147(2)
5.2.5 Reading vehicle data
149(1)
5.2.6 Sending vehicle commands
150(1)
5.2.7 Recording and visualization
151(1)
5.2.7.1 Recording and playing back data
151(1)
5.2.7.2 Visualization using the RViz tool
152(1)
5.3 Testing
152(5)
5.3.1 Unit testing
153(1)
5.3.2 Integration testing
153(1)
5.3.3 System testing
154(2)
5.3.4 Acceptance testing
156(1)
5.4 Summary
157(4)
References
159(2)
6 Other technology aspects
161(46)
6.1 Functional safety
161(8)
6.1.1 Why is functional safety important?
162(1)
6.1.2 ISO 26262
162(2)
6.1.2.1 Safety management
164(1)
6.1.2.2 Engineering processes and requirements
165(1)
6.1.2.3 Automotive safety integrity level
166(1)
6.1.2.4 Product development
167(1)
6.1.2.5 Production and the safety lifecycle
167(1)
6.1.2.6 Supporting processes
168(1)
6.1.3 Challenges
168(1)
6.2 Cybersecurity
169(16)
6.2.1 Why is cybersecurity important?
169(1)
6.2.2 Automotive cybersecurity standards
170(2)
6.2.3 Secure SDV design
172(1)
6.2.3.1 Secure hardware
172(2)
6.2.3.2 Secure software
174(2)
6.2.3.3 Secure in-vehicle network communication
176(5)
6.2.3.4 Secure external communication
181(3)
6.2.4 Challenges
184(1)
6.3 Vehicle-to-everything communication
185(9)
6.3.1 Why is V2X important?
185(1)
6.3.2 V2X standards
186(2)
6.3.3 V2I use cases
188(1)
6.3.3.1 Road work warning
188(1)
6.3.3.2 Road hazard and accident warning
189(1)
6.3.3.3 Traffic light phase event
190(1)
6.3.4 V2V use cases
190(1)
6.3.4.1 Intersection movement assist warning
191(1)
6.3.4.2 Wrong way driver warning
191(1)
6.3.4.3 Do-not-pass warning
192(1)
6.3.5 V2P use case
193(1)
6.3.5.1 Vulnerable road user warning
193(1)
6.3.6 Challenges
194(1)
6.4 Back-end systems
194(4)
6.4.1 Why are back-end systems important?
195(1)
6.4.2 Back-end system functions
195(1)
6.4.2.1 Software over-the-air update
195(1)
6.4.2.2 High-definition maps
196(1)
6.4.2.3 Fleet management
197(1)
6.4.3 Challenges
197(1)
6.5 Summary
198(9)
References
201(6)
7 Applications and outlook
207(20)
7.1 SDV technology applications
208(8)
7.1.1 Transportation use cases
208(1)
7.1.1.1 Private passenger cars
208(1)
7.1.1.2 Public shuttles
209(1)
7.1.1.3 Last mile delivery
210(1)
7.1.1.4 Road freight
211(1)
7.1.2 Non-transportation use cases
212(1)
7.1.2.1 Driverless tractors
213(1)
7.1.2.2 Emergency-response robots
214(1)
7.1.2.3 Security robots
215(1)
7.2 Trends in SDV development strategy
216(3)
7.2.1 Evolutionary
217(1)
7.2.2 Revolutionary
218(1)
7.2.3 Transformative
218(1)
7.3 Trends in deep learning for SDVs
219(7)
7.3.1 Applying deep learning for SDVs
224(1)
7.3.1.1 Semantic abstraction learning
224(1)
7.3.1.2 End-to-end learning
225(1)
7.3.2 Open questions
225(1)
7.4 Summary
226(1)
References 227(4)
Final words 231(2)
Index 233
Hanky Sjafrie is the CEO of SGEC, an independent engineering consulting firm specializing in automotive software engineering for Advanced Driver Assistance (ADAS) and Autonomous Driving (AD.) Much of his experience was acquired through his deep involvement in these fields while working on various R&D projects for car manufacturers and automotive technology suppliers, ranging from sensor technologies (radars, lidars, ultrasonics, etc.) to automotive cybersecurity.

Prior to SGEC, he was actively involved in diverse series development and research projects within the domains of ADAS/AD and infotainment systems at BMW and Audi, as well as at a Silicon Valley-based autonomous driving start-up. Besides working with clients from the automotive industry, he also provides insights into the realm of automotive technology to Siemens, Boston Consulting Group, PricewaterhouseCoopers, and Roland Berger, among others.
Permanent link: https://www.kriso.lv/db/9780429316777_pe.html
Keywords: