Human Factors in Intelligent Vehicles

Front Cover
Human Factors in Intelligent Vehicles
Contents
Preface
List of Contributors
List of Figures
List of Tables
List of Abbreviations
01 Continuous Game Theory Pedestrian Modelling Method for Autonomous Vehicles
	1.1 Introduction
	1.2 Related Work
		1.2.1 Pedestrian Crossing Behaviour
		1.2.2 Game Theory
		1.2.3 Pedestrian Tracking
	1.3 Methods
		1.3.1 Human Experiment
		1.3.2 Pedestrian Detection and Tracking
		1.3.3 Sequential Chicken Model
		1.3.4 Gaussian Process Parameter Posterior Analysis
	1.4 Results
	1.5 Discussion
	Acknowlegdment
	References
02 The Interface Challenge for Partially Automated Vehicles: How Driver Characteristics Affect Information Usage Over Time
	2.1 Introduction
	2.2 Method
		2.2.1 Study Design
		2.2.2 Participants
		2.2.3 Interface Design
		2.2.4 Driving Scenario
		2.2.5 Procedure
		2.2.6 Data Analysis
			2.2.6.1 Trust (Parts 1 and 2)
			2.2.6.2 DBQ (Part 1 only)
			2.2.6.3 DALI (Part 2 only)
	2.3 Results
		2.3.1 Trust Results (Parts 1 and 2)
		2.3.2 DBQ Results (Part 1 only)
		2.3.3 DALI Results (Part 2 only)
		2.3.4 Fixations
			2.3.4.1 Fixations and Trust (Parts 1 and 2)
			2.3.4.2 Fixations and DBQ (Part 1 only)
			2.3.4.3 Fixations and DALI (Part 2 only)
		2.3.5 Between trust, DBQ and DALI
			2.3.5.1 Trust and DBQ (Part 1 only)
			2.3.5.2 Trust and DALI (Part 2 only)
	2.4 Discussion
		2.4.1 Fixations
			2.4.1.1 Fixations and Trust (Parts 1 and 2)
			2.4.1.2 Fixations and DBQ (Part 1 only)
		2.4.2 Fixations and DALI (Part 2 only)
		2.4.3 Between Trust, DBQ and DALI
			2.4.3.1 Trust and DBQ (Part 1 only)
			2.4.3.2 Trust and DALI (Part 2 only)
	2.5 Conclusion
	References
03 A CNN Approach for Bidirectional Brainwave Controller for Intelligent Vehicles
	3.1 Introduction
		3.1.1 Human Brain
		3.1.2 Brainwaves Features
		3.1.3 BCI Research
	3.2 Setup Overview
		3.2.1 Brainwave Sensor
		3.2.2 Vehicle Platform
	3.3 Methodology
		3.3.1 Data Reading
		3.3.2 Data Filtering
		3.3.3 Input Processing
		3.3.4 NN Classifier
		3.3.5 CNN Classifier
			3.3.5.1 MindNet_1
			3.3.5.2 MindNet_2
	3.4 Experimental Works and Results
		3.4.1 General Classifier
		3.4.2 Individual Classifier
		3.4.3 Computational Time
	3.5 Conclusion and Future Work
	References
04 A-RCRAFT Framework for Analysing Automation: Application to SAE J3016 Levels of Driving Automation
	4.1 Introduction
	4.2 A Framework for Automation Analysis: A-RCRAFT
		4.2.1 Allocation of Functions and Tasks
		4.2.2 Allocation of Resources
		4.2.3 Allocation of Control Transitions
		4.2.4 Allocation of Responsibility
		4.2.5 Allocation of Authority
	4.3 Qualitative Analysis of SAE J3016 Levels of Driving Automation with A-RCRAFT
		4.3.1 Scope of the SAE J3016 for the Human Tasks and System Functions
		4.3.2 Decomposition of Levels of Driving Automation Accordingto A-RCRAFT
		4.3.3 Results of the Analysis and Benefits from Using A-RCRAFT
	4.4 Conclusion
	References
05 Autonomous Vehicles: Vulnerable Road User Response to Visual Information Using an Analysis Framework for Shared Spaces
	5.1 Introduction
	5.2 Field Test Description
	5.3 Analyzing Algorithm
		5.3.1 Pedestrian Detection and Pose Estimation
		5.3.2 Distance Estimation via Stereo Cameras
		5.3.3 Pedestrian tracking with DeepSort
		5.3.4 Face Detection
		5.3.5 Velocity
		5.3.6 Classification
		5.3.7 Behavior Segmentation
	5.4 Data Analysis
	5.5 Results
		5.5.1 Algorithm Result
		5.5.2 Field Tests Results
	5.6 Conclusion, Discussion, and Future Work
	Acknowledgment
	References
06 Intelligent Vehicles and Older Drivers
	6.1 Introduction
	6.2 Age-related Limitations in Driving
		6.2.1 Vision and Audition
		6.2.2 Cognitive Function
		6.2.3 Physical Function
	6.3 How Can Intelligent Vehicles Help Older Drivers?
	6.4 Intelligent Vehicles and Older Driver
		6.4.1 Research Methods
		6.4.2 Age Differences in the Acceptance of Assistive Technologies
		6.4.3 Age Differences in Effectiveness of FCW
		6.4.4 Age Differences in Effectiveness of LDW
	6.5 HMI Design for Older Drivers
		6.5.1 Visual HMI Design
		6.5.2 Audible HMI Design
		6.5.3 Multiple-task Design
	6.6 Conclusions
	References
07 Integration Model of Multi-Agent Architectures for Data Fusion-Based Active Driving System
	7.1 Introduction
	7.2 Related Work
	7.3 Deployment Architecture
	7.4 Materials and Methods
		7.4.1 Materials
		7.4.2 Deployment Details
		7.4.3 Driving Trail Designing
	7.5 Results
	7.6 Discussion
	Acknowledgment
	References
Index
About the Editors
Back Cover