Periodic Reporting for period 1 - RE-ROUTE (integRated intElligent multi-modal tRanspOrt infrastrUcTurE: distributed localised decision-making at the network edge)
Reporting period: 2023-01-01 to 2024-12-31
Modern transport systems face growing challenges due to urbanization, increasing mobility demands, and sustainability concerns. Intelligent multi-modal transport, combining road, rail, cycling, and walking, enhances mobility but struggles with congestion, security risks, lack of infrastructure support and adaptability. The RE-ROUTE project explores potential solutions using AI, edge computing, and decentralized decision-making to improve transport resilience, security, and efficiency.
Overall Objectives of the project includes:
Enhancing transport resilience by analyzing multi-source data to identify vulnerabilities and optimize safety, security, and accessibility.
Developing an adaptive multi-modal intelligent transport system architecture (M-ITS) with real-time optimization to minimize service disruptions.
Creating a secure, edge-based data-sharing platform for decentralized, privacy-preserving transport data exchange.
Implementing a federated, decentralized decision-making model for real-time learning and network-edge adaptability.
Validating project outcomes through real-world case studies to provide data-driven policy recommendations.
RE-ROUTE will make the following impacts:
Scientific impact: Advancing AI-driven transport resilience, federated learning, and cybersecurity with research published in leading journals.
Technological impact: Developing secure, intelligent transport networks with interoperable, real-time decision-making.
Economic impact: Reducing congestion, infrastructure costs, and operational inefficiencies and improving policymaker decision-making.
Societal impact: Enhancing accessibility, sustainability, and digital security, ensuring public trust in transport networks.
To achieve its objectives, RE-ROUTE takes an interdisciplinary approach, integrating computer science, engineering, social sciences, cybersecurity, and economics to create practical, inclusive, and secure transport solutions. User behavior analysis, cybersecurity frameworks, and economic models support efficient, sustainable, and policy-driven mobility planning.
Overall Objectives of the project includes:
Enhancing transport resilience by analyzing multi-source data to identify vulnerabilities and optimize safety, security, and accessibility.
Developing an adaptive multi-modal intelligent transport system architecture (M-ITS) with real-time optimization to minimize service disruptions.
Creating a secure, edge-based data-sharing platform for decentralized, privacy-preserving transport data exchange.
Implementing a federated, decentralized decision-making model for real-time learning and network-edge adaptability.
Validating project outcomes through real-world case studies to provide data-driven policy recommendations.
RE-ROUTE will make the following impacts:
Scientific impact: Advancing AI-driven transport resilience, federated learning, and cybersecurity with research published in leading journals.
Technological impact: Developing secure, intelligent transport networks with interoperable, real-time decision-making.
Economic impact: Reducing congestion, infrastructure costs, and operational inefficiencies and improving policymaker decision-making.
Societal impact: Enhancing accessibility, sustainability, and digital security, ensuring public trust in transport networks.
To achieve its objectives, RE-ROUTE takes an interdisciplinary approach, integrating computer science, engineering, social sciences, cybersecurity, and economics to create practical, inclusive, and secure transport solutions. User behavior analysis, cybersecurity frameworks, and economic models support efficient, sustainable, and policy-driven mobility planning.
1. Identification of Resilience Dimensions in Transportation Infrastructure
The project integrated multi-source data, environmental monitoring, and traffic sensors to analyze transport infrastructure vulnerabilities. Edge computing was utilized for real-time traffic management, ensuring accessibility, safety, and serviceability.
2. Development of an Adaptive MaaS Multi-modal Intelligent Transport System (M-ITS)
A scalable computational framework leveraging cloud-to-edge computing was designed to enhance M-ITS efficiency. Modular, API-driven architectures improved interoperability, while cyber threat intelligence ensured system security.
3. Secure Data Sharing and Processing Platform for M-ITS
Methodologies for data quality assurance, ownership validation, and privacy protection were established. A blockchain-based permissioned access system was implemented to enhance secure data sharing, ensuring compliance with GDPR. Collaborations with external projects accelerated progress, leading to a journal submission on secure data governance.
The project integrated multi-source data, environmental monitoring, and traffic sensors to analyze transport infrastructure vulnerabilities. Edge computing was utilized for real-time traffic management, ensuring accessibility, safety, and serviceability.
2. Development of an Adaptive MaaS Multi-modal Intelligent Transport System (M-ITS)
A scalable computational framework leveraging cloud-to-edge computing was designed to enhance M-ITS efficiency. Modular, API-driven architectures improved interoperability, while cyber threat intelligence ensured system security.
3. Secure Data Sharing and Processing Platform for M-ITS
Methodologies for data quality assurance, ownership validation, and privacy protection were established. A blockchain-based permissioned access system was implemented to enhance secure data sharing, ensuring compliance with GDPR. Collaborations with external projects accelerated progress, leading to a journal submission on secure data governance.
The RE-ROUTE project has advanced multi-modal transport resilience, AI-driven optimization, edge computing, federated learning, and data governance, delivering scalable, secure, and adaptive solutions for improved transport efficiency and sustainability.
Key Scientific and Technological Advancements
AI-Driven Security in Transport Networks
Developed methodologies for securing wireless vehicular communication and reducing cyber threats (Farooq et al.).
Impact: Strengthens privacy and resilience in connected transport systems.
Optimizing Open RAN for Transport Networks
Introduced a game-theoretic approach to resolving network conflicts, improving QoS in intelligent transport systems (M-ITS) (Wadud et al.).
Impact: Enables real-time traffic optimization and predictive routing.
Edge Computing Performance Benchmarking
Provided a comprehensive evaluation of edge-based traffic simulation models (Mechalikh et al.).
Impact: Helps transport operators select low-latency computing solutions.
AI-Based Traffic Flow Optimization
Developed AI models to predict and prevent urban traffic congestion (Geraghty et al.).
Impact: Reduces congestion, enhancing urban mobility.
Gamification for Sustainable Transport Choices
Designed engagement models to encourage eco-friendly commuting behavior (Tynan et al.).
Impact: Supports carbon reduction and congestion management.
Federated Learning for Transport AI
Addressed AI deployment challenges in heterogeneous transport networks (Oz et al.).
Impact: Enables real-time, decentralized decision-making.
AI-Optimized Traffic Signals & VRU Safety
Applied AI-driven orchestration to improve traffic signal efficiency and pedestrian safety (Safavifar et al., Guo et al.).
Impact: Enhances traffic flow and safety for vulnerable road users.
Seamless Multi-Modal Transport Data Sharing
Developed an edge-based data-sharing framework to improve MaaS interoperability (Mikolasek et al.).
Impact: Strengthens public-private transport integration.
Key Scientific and Technological Advancements
AI-Driven Security in Transport Networks
Developed methodologies for securing wireless vehicular communication and reducing cyber threats (Farooq et al.).
Impact: Strengthens privacy and resilience in connected transport systems.
Optimizing Open RAN for Transport Networks
Introduced a game-theoretic approach to resolving network conflicts, improving QoS in intelligent transport systems (M-ITS) (Wadud et al.).
Impact: Enables real-time traffic optimization and predictive routing.
Edge Computing Performance Benchmarking
Provided a comprehensive evaluation of edge-based traffic simulation models (Mechalikh et al.).
Impact: Helps transport operators select low-latency computing solutions.
AI-Based Traffic Flow Optimization
Developed AI models to predict and prevent urban traffic congestion (Geraghty et al.).
Impact: Reduces congestion, enhancing urban mobility.
Gamification for Sustainable Transport Choices
Designed engagement models to encourage eco-friendly commuting behavior (Tynan et al.).
Impact: Supports carbon reduction and congestion management.
Federated Learning for Transport AI
Addressed AI deployment challenges in heterogeneous transport networks (Oz et al.).
Impact: Enables real-time, decentralized decision-making.
AI-Optimized Traffic Signals & VRU Safety
Applied AI-driven orchestration to improve traffic signal efficiency and pedestrian safety (Safavifar et al., Guo et al.).
Impact: Enhances traffic flow and safety for vulnerable road users.
Seamless Multi-Modal Transport Data Sharing
Developed an edge-based data-sharing framework to improve MaaS interoperability (Mikolasek et al.).
Impact: Strengthens public-private transport integration.