Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Iterative Learning Control for Highway Traffic Control
In modern society, the problem of traffic congestion in densely populated cities is worsening due to the heavy daily commuting. This affects not only the commuters that waste many hours in traffic congestion every year, but it also creates inefficiencies and pollution that translate into additional societal costs. The role of service stations in the future years will gain importance due to, among other factors, the constant raise in electric vehicle sales. The presence of a service station on highway stretches highly affect the level of traffic congestion on the road. In this work, we aim at developing an Iterative Learning Control scheme that is able to maximize the positive effects that a service station has in terms of peak and overall traffic congestion reduction. We will validate the designed algorithm using real data and state-of-the-art micro-simulators.
Keywords: Iterative Learning Control, Traffic control, Connected and Automated Vehicles, Smart City, Smart Mobility
See the attachment for a complete description of the project.
See the attachment for a complete description of the project.
1. Learn about Iterative Learning Control;
2. Formalize the problem of traffic demand management in highways via service stations applications;
3. Develop an Iterative Learning Control scheme to compute the optimal operating conditions for
the service station. Optimality is defined with respect to the ability to diminish traffic congestion
while satisfying some users’ satisfaction constraints;
4. Validate the designed algorithm via numerical simulations and characterize its performance
in terms of traffic congestion and users’ satisfaction.
**Publications:** If the final results are promising they can potentially be turned into a publication.
1. Learn about Iterative Learning Control; 2. Formalize the problem of traffic demand management in highways via service stations applications; 3. Develop an Iterative Learning Control scheme to compute the optimal operating conditions for the service station. Optimality is defined with respect to the ability to diminish traffic congestion while satisfying some users’ satisfaction constraints; 4. Validate the designed algorithm via numerical simulations and characterize its performance in terms of traffic congestion and users’ satisfaction.
**Publications:** If the final results are promising they can potentially be turned into a publication.
**Daily supervisors:**
- Dr. Carlo Cenedese - ccenedese@ethz.ch
- Dr. Efe Balta - ebalta@ethz.ch
**Supervisor:**
- Prof. John Lygeros
**Daily supervisors:** - Dr. Carlo Cenedese - ccenedese@ethz.ch - Dr. Efe Balta - ebalta@ethz.ch
MA_Proposal_ILC_for_traffic (4).pdf
