Periodic Reporting for period 1 - CONDUCTOR (Fleet and traffic management systems for conducting future cooperative mobility)
Okres sprawozdawczy: 2022-11-01 do 2024-04-30
The CONDUCTOR project’s main goal is to design, integrate and demonstrate advanced, high#level traffic and fleet management that will allow efficient and globally optimal transport of passengers and goods, while ensuring seamless multi#modality and interoperability. Using innovative dynamic balancing and priority-based management of vehicles (automated and conventional) CONDUCTOR will build upon state-of-the-art fleet and traffic management solutions in the CCAM ecosystem and develop next generation simulation models and tools enabled by machine learning and data fusion, enhancing the capabilities of transport authorities and operators, allowing them to become “conductors” of future mobility networks. We will upgrade existing technologies to place autonomous vehicles at the centre of future cities, allowing heightened safety and flexible, responsive, centralized control able to conduct traffic and fleets at a high level. These innovations will lead to less urban traffic and congestion, lowered pollution, and a higher quality of life. Project innovations will be integrated into a common, open platform, and validated in three use cases, testing the interoperability of traffic management systems and integration of different transportation means for both people and goods. Use case UC1 integrates traffic management with inter-modality, UC2 tests demand-response transport, and UC3 urban logistics. In each use case and its demonstrations, simulations will be validated through real life data.
The project's objectives rely on the upgrading of existing tools based on driver-centred approaches towards a mobility-user oriented approach, they are realistically achievable, as they will be grounded on tight collaboration with relevant stakeholders on the operator/city/authority level, where user needs are identified and valorised. The CONDUCTOR project's objectives have been defined as follow:
* Objective 1: To demonstrate traffic and fleet management to integrate CCAM for people and goods
* Objective 2:To address intermodal interfaces and interoperability between traffic management systems
* Objective 3:To test and demonstrate advanced simulation models in real-life traffic conditions considering different priorities
* Objective 4:To demonstrate optimised mobility network load balancing
* Objective 5:To consider governance of the traffic management system considering user needs
The project's objectives rely on the upgrading of existing tools based on driver-centred approaches towards a mobility-user oriented approach, they are realistically achievable, as they will be grounded on tight collaboration with relevant stakeholders on the operator/city/authority level, where user needs are identified and valorised. The CONDUCTOR project's objectives have been defined as follow:
* Objective 1: To demonstrate traffic and fleet management to integrate CCAM for people and goods
* Objective 2:To address intermodal interfaces and interoperability between traffic management systems
* Objective 3:To test and demonstrate advanced simulation models in real-life traffic conditions considering different priorities
* Objective 4:To demonstrate optimised mobility network load balancing
* Objective 5:To consider governance of the traffic management system considering user needs
The CONDUCTOR is designing, integrating and demonstrating innovative traffic and fleet management concepts for an improved transport of passengers and goods, while considering the integration of CCAM vehicles into the mobility ecosystem. The foreseen solution consists in a variety of advanced traffic management models and several relevant scenarios ensure seamless multimodality and interoperability. The dynamic balancing and priority‐based management of vehicles will be implemented using next generation simulation tools enhanced by machine learning and data fusion techniques. All the innovative models and technologies developed within CONDUCTOR project fit future mobility needs thanks to a continuous discussion with the stakeholders, including transport authorities and operators. Moreover, these models are being integrated and will be deployed within a tailor-made platform that will generate advanced simulation and compare the results with the current systems and solutions in place within three Uses cases and five pilots.
The main achievements are the results of an extensive recommendation gathering by double funnel methodology in WP1, where needs of various users and stakeholders were gathered and aligned with the current regulatory requirements, related to CCAM. The recommendations led to the design of a CONDUCTOR conceptual design, comprising of several components and their functionalities. Next, the architecture for each pilot was defined and detailed, comprising of clear relationships and dependencies among data sources, models and algorithms. Within WP2, several models were developed and updated. These models include, among others: Traffic management (e.g. Cooperative Traffic Management System (CTMS) and Real-time traffic information for multi-purpose CCAM services), Fleet management (e.g. Pickup and Delivery Problem with Cross-dock for Perishable Goods and Real-time Fleet Management System (FMS) with incident management), Multimodality (e.g. A demand prediction method using a novel probabilistic transit assignment model and A multi-modal journey planning solution), Inter-operability (e.g. Agent-based interoperability framework) and Multi-resolution simulation (e.g. Simplified mesoscopic simulation model, Aimsun-FleetPy bridge for co-simulation and A calibrated traffic simulation model using real-world data to allow testing coordinated traffic signal controls). In WP3, various data handling solutions were designed and developed for Data gathering (e.g. CONDUCTOR Data space , Data harmonization, Big data architecture ) and Data fusion and analysis (e.g. Space-time context graph as a data source, ML-based fusion pipeline for the identification of unusual traffic patterns caused by large-scale events), as well as various optimization-related techniques, like Network load balancing (e.g. A centralized and decentralized CAV routing algorithm for better network load balancing , Social rerouting framework as a travel demand management measure, respecting individual and situation-specific needs), Dynamic optimization (e.g. Optimization model for DRT) and Anomaly detection (e.g. For transport supply and demand, based on various ML approaches). These models and algorithms were integrated within WP4 and the validation phase in WP5 just started towards the end of reporting period 1, setting the validation plan with KPIs for each use case.
The main achievements are the results of an extensive recommendation gathering by double funnel methodology in WP1, where needs of various users and stakeholders were gathered and aligned with the current regulatory requirements, related to CCAM. The recommendations led to the design of a CONDUCTOR conceptual design, comprising of several components and their functionalities. Next, the architecture for each pilot was defined and detailed, comprising of clear relationships and dependencies among data sources, models and algorithms. Within WP2, several models were developed and updated. These models include, among others: Traffic management (e.g. Cooperative Traffic Management System (CTMS) and Real-time traffic information for multi-purpose CCAM services), Fleet management (e.g. Pickup and Delivery Problem with Cross-dock for Perishable Goods and Real-time Fleet Management System (FMS) with incident management), Multimodality (e.g. A demand prediction method using a novel probabilistic transit assignment model and A multi-modal journey planning solution), Inter-operability (e.g. Agent-based interoperability framework) and Multi-resolution simulation (e.g. Simplified mesoscopic simulation model, Aimsun-FleetPy bridge for co-simulation and A calibrated traffic simulation model using real-world data to allow testing coordinated traffic signal controls). In WP3, various data handling solutions were designed and developed for Data gathering (e.g. CONDUCTOR Data space , Data harmonization, Big data architecture ) and Data fusion and analysis (e.g. Space-time context graph as a data source, ML-based fusion pipeline for the identification of unusual traffic patterns caused by large-scale events), as well as various optimization-related techniques, like Network load balancing (e.g. A centralized and decentralized CAV routing algorithm for better network load balancing , Social rerouting framework as a travel demand management measure, respecting individual and situation-specific needs), Dynamic optimization (e.g. Optimization model for DRT) and Anomaly detection (e.g. For transport supply and demand, based on various ML approaches). These models and algorithms were integrated within WP4 and the validation phase in WP5 just started towards the end of reporting period 1, setting the validation plan with KPIs for each use case.
The validation process of the proposed solution just started at the end of the reporting period 1, so the specific validation results are not available yet. The first partial testing of models and algorithms already show their potential to contribute to the project’s overall goal, and its specific KPIs. That is, several models already show that they will very probably be successful, either improving the traffic flows, or decreasing travelling times and reducing emissions.
No additional needs are identified at the moment to ensure further uptake and success.
No additional needs are identified at the moment to ensure further uptake and success.