Muutke küpsiste eelistusi

Human-Like Decision Making and Control for Autonomous Driving [Kõva köide]

(Tongji University, China), (Nanyang Technological University, Singapore), (Nanyang Technological University, Singapore)
  • Formaat: Hardback, 186 pages, kõrgus x laius: 234x156 mm, kaal: 430 g, 16 Tables, black and white; 103 Line drawings, black and white; 103 Illustrations, black and white
  • Ilmumisaeg: 25-Jul-2022
  • Kirjastus: CRC Press
  • ISBN-10: 1032262087
  • ISBN-13: 9781032262086
Teised raamatud teemal:
Human-Like Decision Making and Control for Autonomous DrivingSuurem pilt
  • Formaat: Hardback, 186 pages, kõrgus x laius: 234x156 mm, kaal: 430 g, 16 Tables, black and white; 103 Line drawings, black and white; 103 Illustrations, black and white
  • Ilmumisaeg: 25-Jul-2022
  • Kirjastus: CRC Press
  • ISBN-10: 1032262087
  • ISBN-13: 9781032262086
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781032262086.html
Märksõnad:
This book details cutting-edge research into human-like driving technology, utilising game theory to better suit a human and machine hybrid driving environment. Covering feature identification and modelling of human driving behaviours, the book explains how to design an algorithm for decision making and control of autonomous vehicles in complex scenarios.

Beginning with a review of current research in the field, the book uses this as a springboard from which to present a new theory of human-like driving framework for autonomous vehicles. Chapters cover system models of decision making and control, driving safety, riding comfort and travel efficiency. Throughout the book, game theory is applied to human-like decision making, enabling the autonomous vehicle and the human driver interaction to be modelled using noncooperative game theory approach. It also uses game theory to model collaborative decision making between connected autonomous vehicles. This framework enables human-like decision making and control of autonomous vehicles, which leads to safer and more efficient driving in complicated traffic scenarios.

The book will be of interest to students and professionals alike, in the field of automotive engineering, computer engineering and control engineering.
Preface xi
Authors xiii
1 Introduction
1(18)
1.1 Overview of Human-Like Autonomous Driving
1(1)
1.2 Human-Like Decision Making for Autonomous Vehicles
2(6)
1.2.1 Model-Based Decision Making
2(2)
1.2.2 Data-Driven Decision Making
4(1)
1.2.3 Game Theoretic Decision Making
5(3)
1.3 Motion Prediction, Planning and Control for Autonomous Vehicles
8(8)
1.3.1 Motion Prediction
8(2)
1.3.2 Motion Planning
10(2)
1.3.3 Motion Control
12(4)
1.4 Framework of Human-Like Autonomous Driving with Game Theoretic Approaches
16(3)
2 Human-Like Driving Feature Identification and Representation
19(12)
2.1 Background
19(1)
2.2 Driving Style Classification and Recognition
20(4)
2.2.1 Classification of Driving Styles
20(1)
2.2.2 Recognition Approaches for Driving Style
21(2)
2.2.3 Characteristic Analysis of Different Driving Styles for Human-Like Driving
23(1)
2.3 Driving Aggressiveness of Vehicles
24(4)
2.3.1 Definition of Driving Aggressiveness
24(1)
2.3.2 Estimation Approaches of Driving Aggressiveness
25(1)
2.3.3 Aggressiveness Estimation Model for Human-Like Driving
26(2)
2.4 Conclusion
28(3)
3 System Modeling for Decision Making and Control of Autonomous Vehicles
31(10)
3.1 Background
31(1)
3.2 Vehicle Model for Decision Making and Control
32(5)
3.2.1 Vehicle Kinematic Model
32(1)
3.2.1.1 Mass Point Kinematic Model
32(1)
3.2.1.2 Bicycle Kinematic Model
33(1)
3.2.2 Vehicle Dynamic Model
34(1)
3.2.2.1 Nonlinear Vehicle Dynamic Model
34(2)
3.2.2.2 Linear Single-Track Model
36(1)
3.3 Driver Model
37(2)
3.4 Integrated Model for Human-Like Driving
39(1)
3.5 Conclusion
40(1)
4 Motion Planning and Tracking Control of Autonomous Vehicles
41(42)
4.1 Background
42(1)
4.2 Human-Like Trajectory Planning for AVs on Highways
43(12)
4.2.1 Artificial Potential Field Model
43(1)
4.2.1.1 APF Model for Vehicles
43(1)
4.2.1.2 APF Model for Road
44(1)
4.2.1.3 Integrated APF Model for Trajectory Planning
45(1)
4.2.2 Trajectory Planning Considering Different Social Behaviors of Obstacle Vehicles
45(1)
4.2.3 Trajectory Planning with APF Considering Trajectory Prediction
46(2)
4.2.4 Simulation and Discussion
48(1)
4.2.4.1 Testing Case 1
48(2)
4.2.4.2 Testing Case 2
50(2)
4.2.4.3 Testing Case 3
52(2)
4.2.5 Summary
54(1)
4.3 Path Planning of AVs on Unstructured Roads
55(13)
4.3.1 Problem Statement
55(1)
4.3.2 Path Planning for Static Obstacles
56(1)
4.3.2.1 Pretreatment of Driving Scenario
56(1)
4.3.2.2 Path Planning with the Visibility Graph Method
57(1)
4.3.2.3 Path Optimization Using NMPC
58(3)
4.3.3 Path Planning for Moving Obstacles
61(1)
4.3.3.1 Trajectory Prediction for Moving Obstacles
61(2)
4.3.3.2 NMPC for Path Optimization
63(1)
4.3.4 Simulation and Validation
64(1)
4.3.4.1 Case Study 1
64(1)
4.3.4.2 Case Study 2
65(2)
4.3.4.3 Case Study 3
67(1)
4.3.5 Summary
67(1)
4.4 Path Tracking Control of AVs
68(13)
4.4.1 Linearized and Discretized Model for Path Tracking Control
68(1)
4.4.2 Integrated Controller Design
69(1)
4.4.2.1 Control System Framework
69(1)
4.4.2.2 Handling Stability Improvement
70(1)
4.4.2.3 Rollover Prevention
71(1)
4.4.2.4 Path Tracking Performance
72(1)
4.4.2.5 LTV-MPC for Integrated Control
72(3)
4.4.2.6 Weighting Matrices for Control Objectives
75(1)
4.4.3 Simulation and Analysis
75(1)
4.4.3.1 Double-Lane Change Maneuver
76(1)
4.4.3.2 Sinusoidal Path Maneuver
76(3)
4.4.4 Summary
79(2)
4.5 Conclusion
81(2)
5 Human-Like Decision Making for Autonomous Vehicles with Noncooperative Game Theoretic Method
83(38)
5.1 Background
84(1)
5.2 Human-Like Lane Change for AVs
85(14)
5.2.1 Problem Description and Human-Like Decision-Making Framework
85(1)
5.2.1.1 Human-Like Lane Change Issue
85(1)
5.2.1.2 System Framework for Human-Like Decision Making
86(1)
5.2.2 Human-like Decision Making Based on Noncooperative Game Theory
87(1)
5.2.2.1 Cost Function for Lane-Change Decision Making
88(2)
5.2.2.2 Noncooperative Decision Making Based on Nash Equilibrium
90(1)
5.2.2.3 Noncooperative Decision Making Based on Stackelberg Equilibrium
91(1)
5.2.3 Testing Results and Performance Evaluation
92(1)
5.2.3.1 Scenario A
92(2)
5.2.3.2 Scenario B
94(4)
5.2.3.3 Discussion of the Testing Results
98(1)
5.2.4 Summary
98(1)
5.3 Human-Like Decision Making of AVs at Unsignalized Roundabouts
99(21)
5.3.1 Problem Formulation and System Framework
99(1)
5.3.1.1 Decision Making of AVs at Unsignalized Roundabouts
99(3)
5.3.1.2 Decision-Making Framework for AVs
102(1)
5.3.2 Motion Prediction of AVs for Decision Making
102(2)
5.3.3 Algorithm Design of Decision Making Using the Game Theoretic Approach
104(1)
5.3.3.1 Payoff Function of Decision Making Considering One Opponent
104(2)
5.3.3.2 Payoff Function of Decision Making Considering Multiple Opponents
106(1)
5.3.3.3 Constraints of Decision Making
107(1)
5.3.3.4 Decision Making with the Game Theory and MPC Optimization
108(2)
5.3.4 Testing Results and Analysis
110(1)
5.3.4.1 Testing Case 1
110(4)
5.3.4.2 Testing Case 2
114(1)
5.3.4.3 Testing Case 3
114(5)
5.3.5 Summary
119(1)
5.4 Conclusion
120(1)
6 Decision Making for CAVs with Cooperative Game Theoretic Method
121(36)
6.1 Background
122(1)
6.2 Cooperative Lane-Change and Merging of CAVs on Highways
122(21)
6.2.1 Problem Formulation and System Framework
123(1)
6.2.1.1 Problem Formulation
123(1)
6.2.1.2 Cooperative Decision-Making Framework for CAVs
124(1)
6.2.2 Motion Prediction of CAVs
124(2)
6.2.3 Decision Making Using the Coalitional Game Approach
126(1)
6.2.3.1 Formulation of the Coalitional Game for CAVs
127(2)
6.2.3.2 Cost Function for the Decision Making of an Individual CAV
129(2)
6.2.3.3 Constraints of the Decision Making
131(1)
6.2.3.4 Decision Making with the Coalitional Game Approach
132(3)
6.2.4 Testing, Validation and Discussion
135(1)
6.2.4.1 Case Study 1
136(3)
6.2.4.2 Case Study 2
139(4)
6.2.5 Summary
143(1)
6.3 Cooperative Decision Making of CAVs at Unsignalized Roundabouts
143(12)
6.3.1 Decision Making with the Cooperative Game Theory
144(1)
6.3.2 Testing Results and Analysis
145(1)
6.3.2.1 Testing Case 1
145(4)
6.3.2.2 Testing Case 2
149(1)
6.3.2.3 Testing Case 3
150(4)
6.3.2.4 Discussion
154(1)
6.3.3 Summary
155(1)
6.4 Conclusion
155(2)
7 Conclusion, Discussion and Prospects
157(4)
7.1 Human-Like Modeling for AVs
157(1)
7.2 Human-Like Decision-Making Algorithm
158(1)
7.3 Cooperative Decision Making Considering Personalized Driving
159(2)
Bibliography 161(24)
Index 185
Dr. Peng Hang is at Nanyang Technological University, Singapore. His research interests include decision making, motion planning and control for connected autonomous vehicles. He received a Ph.D. degree in the School of Automotive Studies, Tongji University, and was a Visiting Researcher at the National University of Singapore, and a Software Engineer at SAIC Motor, China. He has written over 50 academic papers in the field of autonomous driving, as well as applying for more than 20 patents. He serves as an Associate Editor of SAE International Journal of Vehicle Dynamics, Stability, and NVH, and Guest Editors of Actuators, IET Intelligent Transport Systems, and Journal of Advanced Transportation.

Dr. Chen Lv is Professor at Nanyang Technology University, Singapore. He received his Ph.D. at the Department of Automotive Engineering, Tsinghua University, China, and researched at EECS Dept., University of California, Berkeley. His research interests are in advanced vehicle control and intelligence, where he has written over 100 papers and obtained 12 granted patents. He is also Academic Editor for IEEE Transactions on Intelligent Transportation Systems, SAE International Journal of Electrified Vehicles, etc, and Guest Editor for IEEE/ASME Transactions on Mechatronics and IEEE Intelligent Transportation Systems Magazine.

Professor Xinbo Chen studied at Zhejiang University, Tongji University and Tohoku University. He is now Professor in the school of Automotive Studies, Tongji University. He is the author of more than 200 articles and more than 70 patents. His research interests include dynamic control of electric vehicles, design and control of active/semi-active suspension system.