This position is funded by EAISI (Eindhoven Artificial Intelligence Systems Institute) with the aim of conducting cross cut research in the area of real time traffic managmnet by leveraging on AI (Artificial Intelligence). Extremely large amount of data is available regarding real time (private and public) vehicle positions, aggregate traffic conditions, real time states of infrastructure, route planning recommendation (to drivers who use such system), position of sharing services in the network, availability of parking areas, accidents and in the future information about the presence of AVs’ in the network. In order to maximize the benefit from collecting such huge volume of data for the (built) environment, they have to be collectively and simultaneously used to optimize the usage of services and infrastructure (maximizing temporal and spatial efficiency of service and infrastructure) and increasing safety and convenience of travelers (given their preferences) by giving right travelers, right types of advice at right times and right places. The data can also be used for the traffic network management via means such as traffic lights, ramp meters and VMS (Variable Message Sign). It can be further used to help (shared) mobility service providers to manage their fleet more efficiently. In other words, the project is based on the idea of developing a system that provides information to and advise and control the action of travelers (including drivers), fleet operators and network managers. Data on traffic light, vehicle priorities, emission monitoring, various sensors (indictive loop, Magnetic sensor, cameras), state of available fleet for shared vehicles, public transportation schedule will be brought together and processed. Algorithms will be developed which would transform this data into decision aid tools in order to optimize the traffic system. Three groups would mainly benefit from the developed system.
(1) Travelers and Drivers
The information and recommendation (on mode choice, route choice, departure time) will be communicated with travelers/ drivers via app. The advices would take into account personal preferences and constraints which themselves will be recognized (using algorithms) by people’s historical travel behavior. Travelers might follow the recommendation or not. Their reaction (to the recommendation) will be stored and used to update the algorithm for providing future advices.
(2) Fleet operators
The probabilistic demand for different mobility services ((free float)car sharing, (free float) bike sharing) will be forecasted using large scale simulation models (in which our group has s trong expertise) employing the historical data, state of the traffic network (real time travel time by mode, waiting time) and travelers reactions to the recommendation (as far as travel mode choice is concerned). That would help optimizing operation of the fleet.
(3) Network Managers
Real time forecasting of traffic flow by data mining algorithms will be the third wing of the system. The choice of Travelers/ drivers (either based on their experience and/or real time recommendation (mentioned under section (1)) will impact the state of traffic flow on road networks which can then be effectively managed by traffic lights, VMS (Variable Message Sign) and ramp meters. The predictions can be adjusted by sensors’ data (indictive loop, …) and serve as part of inputs for abovementioned (1) and (2)
To enable a smooth human in teraction with such complex dynamic system, all information will be visualized on one single map to facilitate understanding of such system for parties (mobility service providers, network managers) and communication among them. Depending on each partner’s need, different layers of map with certain (temporal and spatial) resolution would be available. In the future when AV would be part of the urban fleet (mixed fleet), having such a system in place encompassing real time information of manual cars, AV and states of infrastructure would guarantee higher level of safety by communicating information to relevant parties (drivers, AV, infrastructure).
The ultimate goal of the project is therefore to develop an integrated system with the above functionalities.
We offer a stimulating and ambitious educational and research environment and are looking for candidates with the following qualifications:
Do you recognize yourself in this profile and would you like to know more? Please contact prof.dr. Soora Rasouli, s.rasouli[at]tue.nl.
For information about terms of employment, click here or contact the HR department Built Environment, po[at]bwk.tue.nl.
Are you inspired to know more about working at TU/e? Please visit www.tue.nl/jobs
This vacancy is part of the Irène Curie Fellowship and is currently only open for female candidates. Male applicants will not be considered for the position. Under European jurisdiction it is lawful to specifically recruit underrepresented groups. If no female candidate is found in the first six months of recruitment, this vacancy will be re-opened as a generic vacancy.
We invite you to submit a complete application by using the 'apply now'-button on this page. The application should include a:
We look forward to your application and will screen it as soon as we have received it. Screening will continue until the position has been filled. We are committed to the cause of gender equality and, in case of equal suitability, we give preference to female candidates.
You can upload a maximum of 5 documents of up to 2 MB each.