
Knowledge Graph-Based Methods for Automated Driving
- 1st Edition - April 11, 2025
- Imprint: Elsevier
- Editors: Rajesh Kumar Dhanaraj, M. Nalini, Malathy Sathyamoorthy, Manar Mohaisen
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 3 0 0 4 0 - 0
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 3 0 0 4 1 - 7
The global race to develop and deploy automated vehicles is still hindered by significant challenges, with the related complexities requiring multidisciplinary research ap… Read more

Purchase options

Institutional subscription on ScienceDirect
Request a sales quoteThe global race to develop and deploy automated vehicles is still hindered by significant challenges, with the related complexities requiring multidisciplinary research approaches.
Knowledge Graph-Based Methods for Automated Driving offers sought-after, specialized know-how for a wide range of readers both in academia and industry on the use of graphs as knowledge representation techniques which, compared to other relational models, provide a number of advantages for data-driven applications like automated driving tasks. The machine learning pipeline presented in this volume incorporates a variety of auxiliary information, including logic rules, ontology-informed workflows, simulation outcomes, differential equations, and human input, with the resulting operational framework being more reliable, secure, efficient as well as sustainable.
Case studies and other practical discussions exemplify these methods’ promising and exciting prospects for the maturation of scalable solutions with potential to transform transport and logistics worldwide.
- Systematically covers knowledge graphs for automated driving processes
- Includes real-life case studies, facilitating an understanding of current challenges
- Analyzes the impact of various technological aspects related to automation across a range of transport modes, networks, and infrastructures
- Knowledge Graph-Based Methods for Automated Driving
- Cover image
- Title page
- Table of Contents
- Copyright
- Contributors
- 1 Knowledge graph-based method for self-driving cars in Industry 5.0
- Abstract
- 1.1 Introduction
- 1.2 Graphs: What are they?
- 1.3 The concept of properties graphs
- 1.4 Knowledge graphs presented
- 1.5 Self-driving cars
- 1.6 Mechanisms of self-driving cars
- 1.7 Industry 5.0
- 1.8 Importance of KG for self-driving cars in Industry 5.0
- 1.9 Reinforcement learning
- 1.10 RL for KG
- 1.10.1 RL’s initial work
- 1.10.2 Initial preparations for RL-KG
- 1.10.3 MDP in KG
- 1.11 Blockchain innovation combined with intelligent computing to develop self-driving cars with KG
- 1.12 Conclusion
- References
- 2 An overview of knowledge representation learning based on ER knowledge graph
- Abstract
- 2.1 Introduction
- 2.1.1 Latest research/recent developments in knowledge graphs
- 2.1.2 Objectives of the chapter
- 2.1.3 Structure of this chapter
- 2.2 Autonomous driving in smart cities
- 2.3 Knowledge graphs: Foundation for autonomous driving
- 2.4 Knowledge graphs in autonomous driving and their applications
- 2.5 Traffic congestion prediction and mitigation in smart cities: Knowledge graphs and machine learning
- 2.6 Object detection in complex environments, sensor technologies and fusion, and deep learning approaches
- 2.7 Collision avoidance strategies: Detection and prediction
- 2.8 Machine learning for real-time decision-making
- 2.9 Conclusion and future scope
- References
- 3 Emerging technologies and tools for knowledge gathering in automated driving
- Abstract
- 3.1 Overview
- 3.1.1 Overview of knowledge gathering in automated driving
- 3.1.2 State-of-the-art technologies
- 3.1.3 Overview of automated driving systems
- 3.1.4 Challenges in knowledge acquisition
- 3.2 Sensor technologies for environmental perception
- 3.2.1 Vehicle sensors
- 3.2.2 Perception sensor
- 3.2.3 Sensor fusion
- 3.3 Data collection and frameworks
- 3.3.1 Cognition
- 3.3.2 Memory
- 3.3.3 Planning
- 3.3.4 Reflection
- 3.4 Machine learning and AI for knowledge extraction
- 3.4.1 Regression algorithms
- 3.4.2 Pattern recognition algorithms
- 3.4.3 Clustering
- 3.4.4 Decision matrix algorithms
- 3.5 Simulation and virtual testing environments
- 3.5.1 Simulation platforms
- 3.5.2 Simulation benefits and challenges
- 3.6 Human-centered autonomous vehicle systems
- 3.6.1 Shared autonomy
- 3.6.2 Learn from data
- 3.6.3 Human sensing
- 3.6.4 Shared perception control
- 3.6.5 Deep personalization
- 3.6.6 Imperfect by design
- 3.6.7 System-level experience
- 3.7 Regulatory and ethical implications
- 3.7.1 Legal dimensions
- 3.7.2 Ethical considerations
- 3.7.3 Social impacts
- 3.8 Future directions and recommendations
- 3.8.1 Collaborative stakeholder engagement
- 3.8.2 Ethical AI integration and public awareness
- 3.8.3 Ethical and responsible AI research
- 3.8.4 Pilot programs and progressive implementation
- References
- 4 Safety regulations and standards for automated driving
- Abstract
- 4.1 Introduction
- 4.2 Safety regulations for automated driving
- 4.2.1 Ensuring public safety in automated driving
- 4.2.2 Ethical considerations in automated driving
- 4.2.3 Mitigating cybersecurity risks in automated driving
- 4.2.4 Encouraging responsibility and liability
- 4.2.5 Encouraging innovation and development
- 4.3 Safety standards for automated driving
- 4.3.1 ISO 26262
- 4.3.2 ISO/SAE 21434
- 4.3.3 ISO/PAS 21448
- 4.3.4 ISO 34503
- 4.3.5 SAE J3016
- 4.3.6 ANSI/UL 4600
- 4.3.7 IEEE P2846
- 4.3.8 NHTSA
- 4.3.9 UNECE WP.29
- 4.3.10 ITU-T
- 4.4 Guidelines for safety regulations and standards for automated driving
- 4.4.1 Recognize applicable regulations
- 4.4.2 Determine safety requirements
- 4.4.3 Create a safety management system
- 4.4.4 Conduct hazard analysis and risk assessment
- 4.4.5 Define the performance metrics and safety goals
- 4.4.6 Implement safety measures and controls in place
- 4.4.7 Validate and verify safety criteria
- 4.4.8 Document compliance and traceability
- 4.4.9 Stay informed and updated
- 4.4.10 Cultivate a safety culture
- 4.5 Conclusion
- References
- 5 Reliability and ethics developments in knowledge graphs for automated driving
- Abstract
- 5.1 Introduction
- 5.1.1 Understanding knowledge graphs
- 5.1.2 Importance of knowledge graphs in automated driving
- 5.1.3 Overview of reliability and ethical challenges
- 5.1.4 Fundamentals of reliability in knowledge graphs
- 5.1.5 Reliability metrics and measurements
- 5.1.6 Challenges in ensuring reliability in knowledge graphs
- 5.1.7 Techniques for improving reliability in knowledge graphs
- 5.1.8 Ethical considerations in knowledge graphs for automated driving
- 5.1.9 Ethical framework for anonymous systems
- 5.1.10 Privacy and consent
- 5.1.11 Security and integrity
- 5.1.12 Transparency and accountability
- 5.1.13 Fairness and inclusivity
- 5.1.14 Legal and regulatory compliance
- 5.1.15 Societal impact and ethical use
- 5.1.16 Moral decision-making in anonymous vehicles
- 5.1.17 Algorithmic ethics
- 5.1.18 Utilitarian vs deontological approaches
- 5.1.19 Ethical transparency
- 5.1.20 Adaptability and learning
- 5.1.21 Public input and stakeholder involvement
- 5.1.22 Legal and regulatory compliance
- 5.1.23 Addressing ethical dilemmas through knowledge graphs
- 5.1.24 Comprehensive information integration
- 5.1.25 Contextual understanding
- 5.1.26 Real-time updates and education
- 5.1.27 Explainability and transparency
- 5.1.28 Participation of multiple stakeholders
- 5.1.29 Risk evaluation and reduction
- 5.1.30 Advances in reliability assurance techniques
- 5.1.31 Machine learning approaches to reliability assurance
- 5.1.32 Formal verification methods
- 5.1.33 Testing and validation strategies
- 5.1.34 Ensuring transparency and accountability
- 5.1.35 Explainability in knowledge graphs
- 5.1.36 Auditing and monitoring systems
- 5.1.37 Legal and regulatory implications
- 5.2 Benefits, limitations, and future prospects
- 5.2.1 New developments in knowledge graphs for automated vehicles
- 5.2.2 Upcoming moral difficulties
- 5.2.3 Suggestions for additional research and development
- 5.3 Conclusion
- References
- 6 Role of knowledge graph-based methods in human—AI systems for automated driving
- Abstract
- 6.1 Introduction
- 6.2 Background
- 6.2.1 AVs at a glance
- 6.2.2 Existing issues
- 6.2.3 AVs regulations and standards
- 6.3 Explanations for autonomous driving
- 6.3.1 Potential benefits of explanations in AVs
- 6.3.2 Explanation recipients in AVs
- 6.3.3 How to deliver explanations in AVs?
- 6.4 AI for autonomous driving
- 6.4.1 Convolutional neural networks
- 6.4.2 Reinforcement learning
- 6.5 Datasets, ontologies, and knowledge graphs
- 6.5.1 nuScenes
- 6.5.2 BDD
- 6.5.3 PandaSet
- 6.5.4 Adding other datasets
- 6.5.5 Global knowledge graph
- 6.6 Conclusions and future directions
- References
- 7 Knowledge-infused learning: A roadmap to autonomous vehicles
- Abstract
- 7.1 Introduction
- 7.1.1 Background and significance
- 7.1.2 Challenges faced by autonomous cars
- 7.1.3 Insufficiency of traditional machine learning in real-world scenarios
- 7.2 Knowledge-infused learning
- 7.2.1 Definition of knowledge-infused learning
- 7.2.2 Key concepts of knowledge-infused learning
- 7.2.3 Domain-specific adaptability
- 7.3 Roadmap to knowledge-infused learning
- 7.3.1 The need for integration of relevant knowledge
- 7.3.2 Sensor data integration
- 7.3.3 Semantic mapping
- 7.3.4 Knowledge representation
- 7.4 Safety and efficiency enhancement
- 7.4.1 Injection of domain-specific information
- 7.4.2 Comprehension of surroundings
- 7.4.3 Proactive anticipation and adaptation
- 7.5 Learning continuum for autonomous cars
- 7.5.1 Adaptation to changing environments
- 7.5.2 Communal learning process through real-world encounters
- 7.6 Benefits, limitations, and future prospects
- 7.6.1 Knowledge acquisition
- 7.6.2 Implications for the future
- 7.6.3 Envisioning a future of safer, smarter, and automated transportation
- References
- 8 Integrated machine learning architectures for a knowledge graph embeddings (KGEs) approach
- Abstract
- 8.1 Introduction
- 8.1.1 The connection between knowledge graphs and machine learning
- 8.2 How does knowledge graph deal with this challenge?
- 8.3 What exactly is a graph? They are EVERYWHERE!
- 8.4 How can graphs be used in ML?
- 8.5 Background
- 8.6 The integration of large language models and knowledge graphs
- 8.6.1 Large language models
- 8.7 Several approaches facilitate this integration
- 8.7.1 Enhancing LLMs with knowledge graphs
- 8.7.2 Using language models to enrich knowledge graphs
- 8.7.3 Hybrid systems
- 8.8 An algorithm for the integration of machine learning (ML) architectures into knowledge graph embeddings
- 8.9 Different architectures and several key attributes
- 8.9.1 Case studies and practical applications
- 8.10 Conclusion
- References
- 9 Future trends and directions for knowledge graph embeddings based on visualization methodologies
- Abstract
- 9.1 Foundations and implications of knowledge graph embeddings
- 9.2 Importance of visualization methodologies in understanding complex relationships
- 9.2.1 Intuitive representation
- 9.2.2 Exploration and analysis
- 9.2.3 Identification of patterns and trends
- 9.2.4 Communication and collaboration
- 9.2.5 Integration with knowledge graph embeddings
- 9.3 Knowledge graph embedding: Foundations and techniques
- 9.3.1 Overview
- 9.3.2 Techniques for generating embeddings
- 9.3.3 Challenges and limitations
- 9.4 Visualization methodologies for knowledge graphs
- 9.4.1 Importance of visualization in knowledge graph analysis
- 9.4.2 Common visualization techniques and tools
- 9.5 Emerging trends in knowledge graph embeddings
- 9.5.1 Embedding diversity: Capturing richer contextual information
- 9.5.2 Dynamic embedding: Adapting to changing knowledge graphs
- 9.5.3 Hierarchical embedding: Modeling intricate knowledge hierarchies
- 9.5.4 Interpretable embedding and privacy-protective techniques
- 9.6 Interactive visualization tools for knowledge graphs
- 9.6.1 Role of interactive visualization in knowledge graph exploration
- 9.6.2 Overview of existing interactive visualization tools
- 9.6.3 Case studies demonstrating the effectiveness of visualization dashboard
- 9.7 Scalability challenges and solutions
- 9.7.1 Scalability issues in handling large and dynamic knowledge graphs
- 9.7.2 Techniques for improving scalability in knowledge graph embeddings and visualization
- 9.8 Cross-modal embeddings in knowledge graphs
- 9.8.1 Introduction to cross-modal embeddings
- 9.9 Case studies and applications
- 9.9.1 Real-world applications of knowledge graph embeddings and visualization methodologies
- 9.9.2 Case studies showcasing successful implementations and their impact
- 9.10 Future directions and research opportunities
- 9.10.1 Potential areas for further research and development
- 9.10.2 Anticipated advancements in knowledge graph embeddings and visualization methodologies
- 9.11 Conclusion
- 9.11.1 Summary of key findings and insights
- 9.11.2 Final remarks on the future of knowledge graph embeddings and visualization
- References
- 10 A brief study on evaluation metrics for knowledge graph embeddings
- Abstract
- 10.1 Introduction
- 10.1.1 Background and motivation
- 10.1.2 Significance of KGEs
- 10.1.3 Purpose of evaluation metrics
- 10.2 KGE: A brief overview
- 10.2.1 Models for KG embedding
- 10.2.2 Characteristics of KG embedding
- 10.3 Commonly used evaluation metrics
- 10.3.1 Importance of evaluation metrics
- 10.3.2 Challenges in evaluating KGEs
- 10.3.3 Comparison with traditional embedding models and advantages
- 10.3.4 Link prediction metrics
- 10.3.5 Importance of mean rank and mean reciprocal rank in link prediction
- 10.4 Additional evaluation metrics
- 10.4.1 Clustering metrics
- 10.4.2 Metrics specific to KGE
- 10.4.3 Significance in model-specific evaluation
- 10.5 Latest research in KGE evaluation techniques
- 10.5.1 Improving quality with new evaluation frameworks
- 10.5.2 Handling the multirelational nature of the graphs
- 10.5.3 Evaluating the KGE model for activities related to knowledge enhancement downstream (Fei et al., 2021)
- 10.6 Applications of evaluation metrics
- 10.6.1 Quantitative evaluation metrics for KGE applications
- 10.6.2 Techniques for qualitative evaluation
- References
- 11 Design, construction, and recent advancements in temporal knowledge graphs for automated driving
- Abstract
- 11.1 Introduction
- 11.2 Background
- 11.3 Temporal knowledge graphs
- 11.3.1 Entities and relationships
- 11.3.2 Temporal annotations
- 11.3.3 Dynamic evolution
- 11.3.4 Historical, present, and predictive data
- 11.3.5 Temporal granularity and resolution
- 11.3.6 Incorporation of uncertainty
- 11.4 Designing a TKG for automated driving
- 11.4.1 Data collection
- 11.4.2 Data preprocessing
- 11.4.3 Sensor fusion
- 11.4.4 Temporal representation
- 11.4.5 Ensuring data quality and consistency
- 11.4.6 Integration into the TKG
- 11.5 Construction of the TKG
- 11.5.1 Data collection
- 11.5.2 Data preprocessing
- 11.5.3 Sensor fusion
- 11.5.4 Temporal representation
- 11.5.5 Ensuring data quality and consistency
- 11.5.6 Integration into the TKG
- 11.6 Recent advancements in TKGs
- 11.6.1 Enhanced prediction capabilities
- 11.6.2 Anomaly detection
- 11.6.3 Decision support systems
- 11.6.4 Adaptive, context-aware algorithms
- 11.7 Conclusion
- References
- 12 Knowledge graph-based question answering (KG-QA) using natural language processing
- Abstract
- 12.1 Learning and knowledge outcomes
- 12.1.1 Data preparation
- 12.1.2 Preprocessing
- 12.1.3 Feature extraction
- 12.1.4 Model training
- 12.1.5 Inference
- 12.1.6 Evaluation
- 12.1.7 Iterative improvement
- 12.1.8 Deployment
- 12.2 Introduction
- 12.2.1 Overview of KG-QA
- 12.2.2 Various aspects of knowledge graph-based question-answering framework
- 12.2.3 Challenges in current question-answering methods
- 12.2.4 Objective of the chapter
- 12.3 The role of NLP in KG-QA
- 12.4 Knowledge graphs in question answering
- 12.5 Problems faced by KG-QA
- 12.6 Knowledge graphs in NLP
- 12.7 Importance of KG-QA
- 12.8 Merging knowledge graphs with NLP
- 12.9 Mathematical representation for (KG-QA) using NLP
- 12.10 Proposed method for KG-QA using NLP
- 12.11 Data sets for KG-QA
- 12.11.1 Knowledge graph data
- 12.11.2 Question-answering datasets
- 12.11.3 Diagram datasets
- 12.12 Case reports and real-world implementations
- 12.13 Barriers and moral concerns
- 12.13.1 Data privacy and security
- 12.13.2 Bias in knowledge representation
- 12.13.3 Language understanding and ambiguity
- 12.13.4 Algorithmic fairness and transparency
- 12.13.5 User understanding and trust
- 12.14 Conclusion
- References
- 13 An integrated framework for knowledge graphs based on battery management
- Abstract
- 13.1 Introduction
- 13.2 Background
- 13.3 Knowledge graph
- 13.3.1 Representation of a directed graph as a three-way array using KG
- 13.3.2 Importance of knowledge graph
- 13.4 KGs based on battery management
- 13.4.1 Entities in the KG
- 13.4.2 Relationships
- 13.4.3 Attributes and properties
- 13.4.4 Semantic modeling
- 13.4.5 Graph-based representation
- 13.5 Popular technologies used in EV battery management
- 13.5.1 Semantic modeling
- 13.5.2 Graph-based querying mechanisms
- 13.5.3 Data integration
- 13.5.4 Telematics and IoT
- 13.5.5 Predictive analytics
- 13.6 Proposed framework for EV battery management
- 13.7 Result analysis
- 13.7.1 Identifying data sources
- 13.7.2 Centralized repository creation
- 13.7.3 Semantic modeling
- 13.7.4 Graph-based representations
- 13.7.5 Incorporating battery specifications
- 13.7.6 Including dynamic factors
- 13.7.7 Enabling holistic insights
- 13.8 Case study: Comparative analysis of Exide Industries and Amara Raja Batteries
- 13.8.1 Exide Industries implementation
- 13.8.2 Amara Raja Batteries implementation
- 13.8.3 Analysis
- 13.8.4 Comparative results
- 13.9 Conclusion
- References
- 14 Ontology-based information integration standards for the automotive industry
- Abstract
- 14.1 Introduction
- 14.1.1 Key objectives of this research include
- 14.2 Foundation of ontology
- 14.2.1 The definitions of ontology
- 14.2.2 Ontology-based data integration
- 14.3 Ontology learning approaches
- 14.4 Learning from unstructured data
- 14.4.1 Text mining and natural language processing (NLP)
- 14.4.2 Image and video analysis
- 14.5 Ontology integration process
- 14.6 Popular technology
- 14.6.1 Semantic web technologies
- 14.6.2 Linked data
- 14.6.3 SPARQL query language
- 14.6.4 Graph databases
- 14.6.5 Natural language processing (NLP)
- 14.6.6 Blockchain for data sharing
- 14.7 Case study of ontology-based Activa two-wheeler
- 14.7.1 Ontology development
- 14.7.2 Data integration
- 14.7.3 Semantic interoperability
- 14.7.4 Standards compliance
- 14.8 Conclusion
- References
- 15 Emerging graphical data management methodologies for automated driving
- Abstract
- 15.1 Introduction
- 15.2 Fundamentals of AuD data
- 15.2.1 Environmental perception
- 15.2.2 V2X
- 15.2.3 High-definition map
- 15.2.4 Planning decision
- 15.2.5 Vehicle network bus technology
- 15.2.6 Information security and privacy protection technology
- 15.3 Graphical data representation in AuD
- 15.3.1 Data layer
- 15.3.2 Knowledge layer
- 15.3.3 Application layer
- 15.3.4 Dataset, ontology, and knowledge graphs
- 15.4 Current graph database management techniques
- 15.4.1 Neo4j (neo technology)
- 15.4.2 Infinite graph
- 15.4.3 DEX
- 15.4.4 HyperGraphDB
- 15.4.5 Infogrid
- 15.4.6 Titan
- 15.4.7 Trinity
- 15.5 Application of knowledge graph to AuD
- 15.5.1 Object detection
- 15.5.2 Semantic segmentation
- 15.5.3 Mapping
- 15.5.4 Scene understanding
- 15.5.5 Object behavior prediction
- 15.5.6 Motion planning
- 15.5.7 Validation
- 15.5.8 Future scope
- 15.6 Conclusions
- References
- 16 Knowledge graphs vs collision avoidance systems: Pros and cons
- Abstract
- 16.1 Introduction
- 16.2 Background
- 16.2.1 Knowledge graph
- 16.2.2 Evolution of knowledge graph
- 16.3 The DIKW pyramid
- 16.3.1 Data (raw, unprocessed facts)
- 16.3.2 Information (processed data)
- 16.3.3 Knowledge (recognition of patterns, relationships)
- 16.3.4 Wisdom (strategic actions and decisions)
- 16.4 Significance of knowledge graphs
- 16.4.1 Complex traffic patterns
- 16.4.2 Diverse driving rules and behavior
- 16.4.3 Linguistic nuances
- 16.4.4 Environmental and seasonal changes
- 16.5 Knowledge graph applications
- 16.5.1 Data collection and integration
- 16.5.2 Modeling regional specifics
- 16.5.3 Integration with navigation systems
- 16.6 Collision avoidance systems
- 16.6.1 History of collision avoidance systems
- 16.7 Significance of collision avoidance systems
- 16.7.1 High traffic density
- 16.7.2 Diverse traffic participants
- 16.7.3 Unpredictable driving behavior
- 16.7.4 Road safety
- 16.8 CAS in traffic conditions
- 16.8.1 Integration with ADAS
- 16.8.2 Adaptive cruise control
- 16.8.3 Lane-keeping assist
- 16.8.4 Traffic sign recognition
- 16.9 Integration of CAS with knowledge graphs
- 16.9.1 Integration works
- 16.9.2 Features of integration of CAS and KG
- 16.10 Comparative analysis of knowledge graphs and collision avoidance systems
- 16.11 Knowledge graphs and collision avoidance systems: Pros and cons
- 16.11.1 Knowledge graphs pros and cons
- 16.11.2 Knowledge graphs cons
- 16.11.3 Collision avoidance systems pros and cons
- 16.12 Conclusion
- References
- 17 Autonomous vehicle collision prediction systems: Artificial intelligence (AI) in action with knowledge graphs
- Abstract
- 17.1 Introduction
- 17.1.1 Overview of autonomous vehicles
- 17.2 Importance of collision prediction in AVs
- 17.3 Challenges in current collision prediction methods
- 17.4 Objective of the chapter
- 17.5 The role of AI in AVs
- 17.6 Limitations and challenges faced by AVs
- 17.7 Advanced collision prediction: The need
- 17.8 Importance of real-time decision-making
- 17.9 Knowledge graphs in AVs
- 17.9.1 Introduction to knowledge graph
- 17.10 Integration of knowledge graphs into AV systems
- 17.11 Quantum computing in AVs
- 17.12 Integrating AI, knowledge graphs, and quantum computing
- 17.13 Datasets
- 17.14 Case studies and practical applications
- 17.14.1 Real-world implementations
- 17.15 Challenges and ethical considerations
- 17.15.1 Technical challenges and limitations
- 17.15.2 Ethical and regulatory issues
- 17.15.3 Safety and privacy concerns
- 17.16 Conclusion
- References
- 18 Risk assessment based on dynamic behavior for autonomous systems using knowledge graphs
- Abstract
- 18.1 Introduction
- 18.2 Background and motivation
- 18.2.1 Current status of autonomous vehicles for two-wheeler
- 18.2.2 Risk management
- 18.3 Knowledge graph
- 18.3.1 Importance of knowledge graph for two-wheelers
- 18.4 Proposed methodology of autonomous systems
- 18.4.1 Data preprocessing
- 18.4.2 Knowledge graph integration
- 18.4.3 Dynamic behavior modeling
- 18.4.4 Machine learning algorithms
- 18.4.5 Physics-based simulation
- 18.4.6 Decision support system
- 18.4.7 Using knowledge graph
- 18.4.8 Adaptive responses
- 18.4.9 Recommendation
- 18.5 Result analysis
- 18.5.1 Data collection
- 18.5.2 Collect real-time data
- 18.5.3 External sources
- 18.5.4 Data preprocessing
- 18.5.5 Knowledge graph integration
- 18.5.6 Dynamic behavior modeling
- 18.5.7 Decision support system
- 18.6 Case study: Comparative study of Hero and Honda two-wheeler Company
- 18.7 Conclusion
- References
- 19 Case studies on knowledge graphs in automated driving
- Abstract
- 19.1 Introduction
- 19.1.1 Key characteristics of knowledge graph
- 19.1.2 Challenges of KG-based approaches
- 19.2 The role of knowledge graphs in automated driving
- 19.3 Knowledge graph use cases in automated driving
- 19.3.1 Predicting traffic flow with KG-based route planning
- 19.3.2 Enhancing scene understanding with KG-based object recognition
- 19.3.3 Autonomous navigation in urban environments
- 19.3.4 Personalized driving assistance with KG-based driver modeling
- 19.3.5 Dynamic route planning with KGs
- 19.3.6 Safe interaction with vulnerable road users
- 19.4 Conclusion
- References
- Index
- Edition: 1
- Published: April 11, 2025
- Imprint: Elsevier
- No. of pages: 428
- Language: English
- Paperback ISBN: 9780443300400
- eBook ISBN: 9780443300417
RD
Rajesh Kumar Dhanaraj
MN
M. Nalini
Dr. Nalini holds a PhD in Electronics and Communication Engineering from Sri Chandrasekarendra Saraswathi Viswa Maha Vidyalaya, Kanchipuram, India. Her research and publication interests include Artificial Intelligence, biomedical engineering, wireless sensor networks, and Internet of Things. She holds two patents in India and has received a grant to submit another application through the AICTE Quality Improvement Schemes supported by the Gvt. of India.
MS
Malathy Sathyamoorthy
Dr. Malathy holds a PhD in Information and Communication Engineering from Anna University, Chennai, India. Her research areas include wireless sensor networks, Internet of Things, and applied machine learning. She is a life member of the Indian Society for Technical Education (ISTE) and the International Association of Engineers (IAENG). She is an active author/editor for Springer, CRC Press, and Elsevier. She is also a reviewer for Wireless Networks (Springer) and on the editorial board at many international conferences.
MM