Search

This Deliverable 6.2 of the TransAID project presents and evaluates the simulation results obtained for the scenarios considered during the project's first and second iterations. To this end, driver- and AV-models designed in WP3, traffic management procedures developed in WP4, and V2X communication protocols and models from WP5 were implemented within the iTETRIS simulation framework. Previous main results from Deliverable 4.2, where baseline and traffic management measures without V2X communication were compared, have been confirmed. While not all TransAID scenarios' traffic KPIs were affected, the realistic simulation of V2X communication has shown a discernible impact on some of them, which makes it an indispensable modelling aspect for a realistic performance evaluation of V2X traffic scenarios. Flaws of the first iteration's traffic management algorithms concerning wireless V2X communication and the accompanying possibility of packet loss were identified and have been addressed during the project's second iteration. Finally, lessons learned while working on these simulation results and assessments have additionally been described in the form of recommendations for the real-world prototype to be developed in WP7. We conclude that all results obtained for all scenarios when employing ideal communication confirmed the statistical trends of the results from the original TM scenarios as reported in Deliverable 4.2 where no V2X communication was considered. Furthermore, the performance evaluation of the considered scenarios and parameter combinations has shown the following, which held true in both the first and second iterations: (1) The realistic simulation of V2X communication has an impact on traffic scenarios, which makes them indispensable for a realistic performance evaluation of V2X traffic scenarios. (2) Traffic management algorithms need to account for sporadic packet loss of various message types in some way. (3) Although important, the realistic modelling and simulation of V2X communication also induces a significant computational overhead. Thus, from a general perspective, a trade-off between computation time and degree of realism should be considered.

This deliverable explains how simulations of both the baseline (WP3) and the traffic management schemes (WP4) can be ported from the SUMO simulation environment (with the help of the TraCI interface and Python scripts) to the iCS environment (using the C++ language).We first gave an explanation on how to set up the creation of a traffic management application in the context of the iCS. Details were given on how to prepare the development of an application, based on the source code in the repository. We also explained the interactions between the iCS, SUMO, ns-3, and the various applications, using subscriptions and the exchange of messages.To this end, the TransAID version of the iTETRIS platform defined in WP6 includes a basic application known as baseAppthat manages the exchange of information between the applications and the iCS modules. The application developed for the different services of the TransAID project will inherit form this baseAppand extend the functionality with the traffic management procedures defined in WP4. In order to develop these applications,a new branch (transaid-apps) is added to the git repository. Note that all TransAID applications developed share the same baseApp. Hence, commits to the baseApp should be strictly separated from thecommits to the TransAID applications in development. Changes to the baseApp as well as other iTETRIS modules like iCS or ns-3 should be integrated into the transaid-dev branch. When porting the traffic management code from the WP4 to the WP6 environments, we need to make sure that the same logic is preserved. In order to guarantee this, all applications implemented in the use cases should create test suites, similarly as described in Deliverable D6.1. We use the same testing framework, called TextTest. Tests are created in the transaid-apps branch of the repository, separated for each use case individually. All tests are stored in the transaid/TransAIDScenarios/tests/scenariosfolder. All relevant data pertaining to a specific use case (i.e. SUMO networks, configuration files, ...) are copied to the relevant scenario in the tests folder. Just as before, the testing concept employed by TextTest is to compare expected output of an entire program run with actual output (output files or stdout and stderr). However, here we need to be a bit more careful and considerate of the complexity involved with comparing the various iCS traffic management applications to their previously created SUMO counterparts.We explain this via a method of aggregate quantities, rather than explicitly comparing time-space diagrams.A more detailed comparison of simulation outputs would be to use detector measurements and/or explicit vehicle trajectories, create time-space diagrams from these (of average speeds or flows), and then compare these with each other and define whether or not the deviation is significant. However, even though this type of analysis would certainly allow us to detect deviations in the time-space plane (e.g.,congested areas that may appear/disappear as artefacts, ...), it would be out of scope. In addition, such analyses have not been done widespread before, as they are also difficult to interpret, and still require some aggregation in order to test these 'automatically'.

This present document is Deliverable D3.2 entitled "Cooperative manoeuvring in the presence of hierarchical traffic management", which was prepared in the context of the WP3 framework of the TransAID project. The scope of this document encompasses the modelling and simulation of cooperative manoeuvring in the context of the microscopic traffic simulation activities conducted within TransAID. Initially, the state of the art in the domain of cooperative manoeuvring is provided and then two different cooperative manoeuvring frameworks are introduced. The first one is a decentralized framework where cooperative manoeuvring is solely based on vehicle-to-vehicle (V2V) communications, while the second one is a centralized framework that utilizes vehicle-toanything (V2X) communications. A work zone scenario is used to elaborate on the operation of the centralized approach. The logic for simulating the decentralized approach in the microscopic traffic simulator SUMO is subsequently introduced along with the corresponding functionalities that were developed within SUMO for this purpose. Cooperative manoeuvring is coupled with hierarchical traffic management by explaining how the decentralized approach can be integrated in the traffic management plans that were developed for each use case examined in the context of TransAID. Cooperative manoeuvring is coupled with traffic separation in SUMO and a timeline of cooperative manoeuvring actions in the simulation is presented. Coupling with communications is also addressed. Moreover, adaptations to the driver-vehicle models encompassing communication requirements are proposed to enable integration in iTETRIS. Finally, recommendations for finetuning of driver-vehicle models in simulation are provided based on the findings of the real-world prototype experiments.

This Deliverable 6.2 of the TransAID project presents and evaluates the simulation results obtained for the scenarios considered during the project's first iteration. To this end, driver- and AV-models designed in WP3, traffic management procedures developed in WP4, and V2X communication protocols and models from WP5 were implemented within the iTETRIS simulation framework. Previous main results from Deliverable 4.2, where baseline and traffic management measures without V2X communication were compared, have been confirmed. While not all scenarios' traffic KPIs were affected, the realistic simulation of V2X communication has shown a discernible impact on some of the TransAID traffic scenarios, which makes it an indispensable modelling aspect for a realistic performance evaluation of V2X traffic scenarios. Flaws of the proposed traffic management algorithms concerning wireless V2X communication and the accompanying possibility of packet loss have been identified and will be addressed during the project's second iteration. Finally, lessons learned while working on these simulation results and assessments have additionally been described in the form of recommendations for the real-world prototype to be developed in WP7.

This present document is Deliverable D3.2 entitled 'Cooperative manoeuvring in the presence of hierarchical traffic management', which was prepared in the context of the WP3 framework of the TransAID project. The scope of this document encompasses the modelling and simulation of cooperative manoeuvring in the context of the microscopic traffic simulation activities conducted within TransAID. Initially, the state of the art in the domain of cooperative manoeuvring is provided and then two different cooperative manoeuvring frameworks are introduced. The first one is a decentralized framework where cooperative manoeuvring is solely based on vehicle-to-vehicle (V2V) communications, while the second one is a centralized framework that utilizes vehicle-toanything (V2X) communications. The logic for simulating the decentralized approach in the microscopic traffic simulator SUMO is subsequently introduced along with the corresponding functionalities that were developed within SUMO for this purpose. Cooperative manoeuvring is coupled with hierarchical traffic management by explaining how the decentralized approach can be integrated in the traffic management plans that were developed for each use case examined in the context of TransAID. Cooperative manoeuvring is coupled with traffic separation in SUMO and a timeline of cooperative manoeuvring actions in the simulation is presented. Coupling with communications is also addressed. Moreover, adaptations to the vehicle/driver models, that were developed to replicate the behaviour of cooperative and automated vehicles (CAV), are proposed based on the findings of the real-world prototype experiments. Finally, focus on the centralized approach in terms of development of relevant SUMO functionalities, and integration within the TransAID traffic management plans will be placed during the second project iteration.

This deliverable focuses on an important topic within the MAVEN project - evaluation of the project impact. This is an important step that will allow us to say what the results and impact of the different technologies, functionalities as well as assumptions are. It covers different dimensions of the impact assessment as stated in the Deliverable D7.1 - Impact assessment plan [10]. The field tests proved that the technology in the vehicle works together with the infrastructure and the solution is technically feasible. This was demonstrated also during particular events and is reported in the attached test protocols. At the same time, the emulation and simulation in Dominion software proved the functionality, for example with respect to the cooperative perception or safety indicators. The tests also proved that the key performance indicator "minimum time to the collision" decreases when applying the cooperative sensing. Also, the number of human interventions needed was zero in all the tests. This deliverable also discussed selected results of a detailed user survey aiming at understanding the expected impacts and transition of automated vehicles. The overall number of respondents reached 209. The responses have revealed some interesting facts. For example, over 80% of the respondents believe that CAVs will decrease the number of traffic accidents. Similarly, about 70% of the respondents expect improvements in traffic congestions. Over 82% of respondents declared that they would accept some detour when driving if it helps the overall traffic situation. The literature review, however, indicated that autonomous vehicles will have either a positive or a negative effect on the environment, depending on the policies. For example, opening cars as a mode of transport to new user groups (seniors, children etc.) together with improvements of the traffic, flow parameters can increase the traffic volume on roads. Policy makers shall focus on the integration of the CAVs into a broader policy concept including car or ride-sharing, electromobility and others. In order to evaluate the transition, for example, the influence of different penetration rates of CAVs on the performance, a microscopic traffic simulation was performed. Here the particular MAVEN use cases, as well as their combination, was addressed. The results of the simulation are rather promising. The potential for improvements in traffic performance is clearly there. It was demonstrated that a proper integration of CAVs into city traffic management can, for example, help with respect to the environmental goals (Climate Action of the European Commission) and reduce CO2 emissions by up to 12 % (a combination of GLOSA and signal optimization). On corridors with a green wave, a capacity increase of up to 34% was achieved. The conclusions from this project can be used not only by other researchers but mainly by traffic managers and decision-makers in cities. The findings can get a better idea about the real impacts of particular use cases (such as green wave, GLOSA and others) in the cities. An important added value is also the focus on the transition phase. It was demonstrated that already for lower penetration rates (even 20% penetration of automated vehicles), there are significant improvements in traffic performance. For example, the platooning leads to a decrease of CO2 emissions of 2,6% or the impact indicator by 17,7%.

In light of the increasing trend towards vehicle connectivity and automation, there will be areas and situations on the roads where high automation can be granted, and others where it is not allowed or not possible. These are termed "Transition Areas". Without proper traffic management, such areas may lead to vehicles issuing take-over requests (TORs), which in turn can trigger transitions of control (ToCs), or even minimum-risk manoeuvres (MRMs). In this respect, the TransAID Horizon 2020 project develops and demonstrates traffic management procedures and protocols to enable smooth coexistence of automated, connected, and conventional vehicles, with the goal of avoiding ToCs and MRMs, or at least postponing/accommodating them. Our baseline simulations confirmed that a coordinated distribution of takeover events can prevent a drop in traffic efficiency, which in turn leads to a more performant, safer, and cleaner traffic system, when taking the capabilities of connected and autonomous vehicles into account.

In D2.1 five services have been described encompassing multiple use cases and scenarios. In this Deliverable 2.2, 5 scenarios are selected, one for each service, and worked out in more detail. The detailed timelines of the scenarios are provided describing what exactly is the sequence of events in the scenario and what the effect of the measures, which being developed in WP4, should be. Also, the simulation networks for each of the scenarios have been created and their specification is documented in this deliverable. Furthermore, the requirements for the simulations have been specified, ranging from several vehicle (type) models to the traffic composition, demand and vehicle mixes. For the second iteration of the project, 5 new or extended scenarios have been selected based on findings from the first iteration. Those findings are also used to update the overall simulation requirements and parameters (i.e. definition of actors, traffic composition, demand and vehicle/driver models). Finally, based on insights from the first iteration, several questions have been formulated which will be used during several surveys (e.g. digital polls or paper surveys during events; interviews with experts). The goal is to gain insights into legal implications, (expected) driver and/or automated vehicle behaviour and infrastructure specific aspects with respect to automated vehicles.

This report describes the organisation and outcome of the TransAID Symposium, held in Paris, France, on 9 June 2019, in conjunction with the IEEE Intelligent Vehicles Symposium (IV 2019), one of the major annual conferences of the IEEE Intelligent Transportation Systems Society (ITSS). In light of dissemination and obtaining stakeholder knowledge, TransAID bundled its resources with a large existing IV 2019 event to ensure a higher probability of attracting people to the workshop. As the audience of our workshop (which targeted technologies for cooperative and automated road transport) constituted a mix of academia, researchers, and industry, we were able to foster the interactive exchange between all these parties. The contents of the workshop comprised survey questions posed via the Mentimeter platform, invited speakers, and oral-paper presentations (which were thematically put into the two categories, of Connected and Automated driving, as well as security-related aspects of Cooperative ITS). Each time, an interactive discussion with the audience ensued, providing further insights into the authors' points of view. The survey results revealed that about half of the participants came from academia. Interestingly, a large group was in favour of foreseeing areas where automated driving should not be allowed, thereby directly confirming that TransAID's research questions and approach are sound and sensible. A very high proportion of the participants also spoke out towards OEMs, asking them to explain the limitations of their automated vehicles. In addition, connectivity was perceived as a mandatory requirement for Level 3 or higher automated vehicles. To conclude, a discussion followed some of the results related to the question whether (connected) automated vehicles would be allowed to break the law. This was seen as moderately acceptable when optimisation of the traffic stream was called for, but definitely for the purpose of increasing traffic safety.

Aerial images potentially contain a wealth of information relevant to the prediction of road safety if they could be thoroughly analyzed in great numbers. Coincident with the widespread availability of satellite and aerial images, machine learning algorithms for image processing and automatic object detection and classification are maturing. This allows the automated processing of huge amounts of image data by artificial neural networks (ANNs) or related machine learning systems - an area in which convolutional neural networks have shown a significant improvement over conventional methods. In the submitted work initial results on the application of machine learning on aerial images are presented. The goal is to determine an estimation of road safety levels. ANNs were trained to predict crash frequencies for road intersections relying merely on aerial images of the intersections. The used data consists of police recorded crashes in the city of Berlin and aerial images provided by the Berlin Senate Department for Urban Development. The performance of the ANN suggests that the line of research is worth further pursuit. For instance, the trained ANN was able to predict the presence of crashes on intersections in a Berlin district excluded from the training process with an accuracy of approximately 74%.