Periodic Reporting for period 1 - TANGENT (ENHANCED DATA PROCESSING TECHNIQUES FOR DYNAMIC MANAGEMENT OF MULTIMODAL TRAFFIC)
Periodo di rendicontazione: 2021-09-01 al 2023-02-28
The development of disruptive technologies, abundance of micro mobility solutions (scooters, e-bikes, skateboards, shared bicycles, etc.) and the tendency towards a more human-centric approach generate a revolution in mobility, transport network and traffic management. Transport infrastructure, vehicle technologies and digitalisation of mobility are progressively improving, while movement of people and transport of goods is expected to continuously increase dramatically. In this context, the European transport faces major challenges in terms of safety, greenhouse gas emissions, traffic congestions and its derived costs.
TANGENT aims to develop new complementary tools for optimising traffic operations in a coordinated and dynamic way from a multimodal perspective and considering automated/non-automated vehicles, passengers and freight transport. TANGENT will allow the precise knowledge and management of the mobility flows among the transport modes and will enable the implementation and integration of innovative mobility solutions, services and business models.
The results will be tested in three case studies: Rennes (FR), Lisbon (PT), Great Manchester (UK) and a virtual case study in Athens (HE).
The impact will be assessed to reach expected reduction targets of 10% in travel time, 8-10% in CO2 emissions, 5% of accidents, 5-10% increase in use public transport and use of active modes or 10% of economic costs due to a more efficient management.
TANGENT aims to develop new complementary tools for optimising traffic operations in a coordinated and dynamic way from a multimodal perspective and considering automated/non-automated vehicles, passengers and freight transport. TANGENT will allow the precise knowledge and management of the mobility flows among the transport modes and will enable the implementation and integration of innovative mobility solutions, services and business models.
The results will be tested in three case studies: Rennes (FR), Lisbon (PT), Great Manchester (UK) and a virtual case study in Athens (HE).
The impact will be assessed to reach expected reduction targets of 10% in travel time, 8-10% in CO2 emissions, 5% of accidents, 5-10% increase in use public transport and use of active modes or 10% of economic costs due to a more efficient management.
In P1, TANGENT consortium has actively worked towards the set up and development of the multi-actor co-creation process for each case studies. One of the key priorities have been the definition of the user needs and system requirements. Also, the regulatory framework in traffic management have been identified.
In parallel, the data requirements for each of the case studies have been identified, with a first map of available data sources, and the data-sharing governance model have been defined, which identifies key processes to be addressed by TANGENT stakeholders for proper data-sharing in the project with the identification of different roles and specific rules.
In the scope of “Travel behaviour modelling”, a review of the state-of-the-art regarding the factors that affect daily travel patterns and modelling perspectives of travel behaviour has been completed. A survey has been designed for collecting the preferences of travelling of the transport& mobility users for each of the case studies, including real trajectories, and modelling their behaviour.
Regarding “traffic predictions and simulations”, a review of the state-of-the-art regarding mobility forecasting on demand and supply has been done. Preliminary implementations and tests have been performed to assess the solutions of the proposed algorithms, on either open datasets often used in literature to benchmark methods for traffic supply forecasting. Furthermore, the workflow for the integration framework for real-time monitoring and forecasting has been designed to bring all elements together.
Regarding the “transport network-wide optimization” module, a review of the state-of-the-art regarding adaptive traffic control and CAVs, synchronization of on-demand with transit modes, dynamic congestion pricing, as well as negotiation and arbitration models have been done. During P1, the mathematical formulation of the optimization problems mentioned have been implemented, also the selection of the optimization methods to be used for solving the four optimization problems indicated before, and an initial implementation of the optimization framework for the problem of synchronization of public transport and traffic control.
In relation to integration tasks, a first release of the TANGENT tool architecture has been delivered, providing a functional description of the TANGENT services, detailing the technical structure of the TANGENT modular system, specially designed for both automatic and cooperative transport management.
The approach of each case studies and the framework for the testing methodology has been designed, as well as the description of the scenarios to be tested and their relation to the services that will be experimented with and the functionalities’ requirements of the TANGENT tool.
In parallel, the data requirements for each of the case studies have been identified, with a first map of available data sources, and the data-sharing governance model have been defined, which identifies key processes to be addressed by TANGENT stakeholders for proper data-sharing in the project with the identification of different roles and specific rules.
In the scope of “Travel behaviour modelling”, a review of the state-of-the-art regarding the factors that affect daily travel patterns and modelling perspectives of travel behaviour has been completed. A survey has been designed for collecting the preferences of travelling of the transport& mobility users for each of the case studies, including real trajectories, and modelling their behaviour.
Regarding “traffic predictions and simulations”, a review of the state-of-the-art regarding mobility forecasting on demand and supply has been done. Preliminary implementations and tests have been performed to assess the solutions of the proposed algorithms, on either open datasets often used in literature to benchmark methods for traffic supply forecasting. Furthermore, the workflow for the integration framework for real-time monitoring and forecasting has been designed to bring all elements together.
Regarding the “transport network-wide optimization” module, a review of the state-of-the-art regarding adaptive traffic control and CAVs, synchronization of on-demand with transit modes, dynamic congestion pricing, as well as negotiation and arbitration models have been done. During P1, the mathematical formulation of the optimization problems mentioned have been implemented, also the selection of the optimization methods to be used for solving the four optimization problems indicated before, and an initial implementation of the optimization framework for the problem of synchronization of public transport and traffic control.
In relation to integration tasks, a first release of the TANGENT tool architecture has been delivered, providing a functional description of the TANGENT services, detailing the technical structure of the TANGENT modular system, specially designed for both automatic and cooperative transport management.
The approach of each case studies and the framework for the testing methodology has been designed, as well as the description of the scenarios to be tested and their relation to the services that will be experimented with and the functionalities’ requirements of the TANGENT tool.
TANGENT will address several advances beyond the State of the Art in the following areas:
(i) Travel Behaviour Analysis is devoted to the modelling of the travel behaviour of transport users. It will include dynamic mechanisms to replicate users’ decisions in the presence of unexpected events and system disruptions. The goal is to describe how individual needs, preferences and sentiments affect travel related decisions and how mobility patterns change under various system conditions such as the emergence of new services and new travel mode alternatives, network interventions and road pricing policies.
(ii) Transport Prediction & Simulation to infer the future traffic state in the network by predicting multimodal travel demand and supply, and the mobility parameters for different time horizons. It will incorporate and fuse knowledge derived from travel behaviour models and exploit machine learning techniques to feed traffic simulation software to estimate the impacts of events in the traffic network.
(iii) Transport network optimization on-line and off-line optimisation of multimodal network-wide traffic management will be implemented based on Artificial Intelligence, and concretely model-based optimisation and reinforcement learning techniques. The module will use the current status of the traffic, predictions and simulations of the future evolution of traffic to determine the best possible actions to take depending on the performance targets, constraints and scenarios considered by transport managers. The potential management strategies and actions will be defined by a set of decision variables over which stakeholders of CCAM can influence transport supply, e.g. traffic control, C-ITS services, and the transport demand, e.g. public transport incentives.
TANGENT will deliver a set of applications for decision-making support creating a framework for coordinated traffic and transport management:
1. Enhanced information service for multimodal transport management – Dashboard & API. The system will deliver information on the traffic conditions on real-time visualizing on the entire transport network, integrating: cycling, PT, etc., both from public and private stakeholders. Besides, it will provide predictive information from 15 minutes up to 4 hours on the transport network regarding demand & supply, traffic congestion, events.
2. Real-time Traffic Management Services, will provide recommendations at operational/ tactical level to transport agents, with the aim of optimizing the overall transport network operations on a day to day basis.
3. Transport network optimization for Transport Authorities. This service aims to support decision-makers at the strategic and tactical level for producing policies or response plans for optimizing the performance of the transporte network. This service will simulate different scenarios suggested by the decision-maker and assess how it will affect the transport network operations. These simulations will run under What-If scenarios, showing how the transport network performance would be affected under certain hypothetical circumstances.
(i) Travel Behaviour Analysis is devoted to the modelling of the travel behaviour of transport users. It will include dynamic mechanisms to replicate users’ decisions in the presence of unexpected events and system disruptions. The goal is to describe how individual needs, preferences and sentiments affect travel related decisions and how mobility patterns change under various system conditions such as the emergence of new services and new travel mode alternatives, network interventions and road pricing policies.
(ii) Transport Prediction & Simulation to infer the future traffic state in the network by predicting multimodal travel demand and supply, and the mobility parameters for different time horizons. It will incorporate and fuse knowledge derived from travel behaviour models and exploit machine learning techniques to feed traffic simulation software to estimate the impacts of events in the traffic network.
(iii) Transport network optimization on-line and off-line optimisation of multimodal network-wide traffic management will be implemented based on Artificial Intelligence, and concretely model-based optimisation and reinforcement learning techniques. The module will use the current status of the traffic, predictions and simulations of the future evolution of traffic to determine the best possible actions to take depending on the performance targets, constraints and scenarios considered by transport managers. The potential management strategies and actions will be defined by a set of decision variables over which stakeholders of CCAM can influence transport supply, e.g. traffic control, C-ITS services, and the transport demand, e.g. public transport incentives.
TANGENT will deliver a set of applications for decision-making support creating a framework for coordinated traffic and transport management:
1. Enhanced information service for multimodal transport management – Dashboard & API. The system will deliver information on the traffic conditions on real-time visualizing on the entire transport network, integrating: cycling, PT, etc., both from public and private stakeholders. Besides, it will provide predictive information from 15 minutes up to 4 hours on the transport network regarding demand & supply, traffic congestion, events.
2. Real-time Traffic Management Services, will provide recommendations at operational/ tactical level to transport agents, with the aim of optimizing the overall transport network operations on a day to day basis.
3. Transport network optimization for Transport Authorities. This service aims to support decision-makers at the strategic and tactical level for producing policies or response plans for optimizing the performance of the transporte network. This service will simulate different scenarios suggested by the decision-maker and assess how it will affect the transport network operations. These simulations will run under What-If scenarios, showing how the transport network performance would be affected under certain hypothetical circumstances.