Future urban mobility systems

CIVIL-415 / 4 credits

Teacher(s): Barmpounakis Emmanouil, Geroliminis Nikolaos, Xu Meng

Language: English

Summary

This course introduces future urban mobility systems from a data-driven perspective, covering mobility data ecosystems, sensing technologies, information extraction, traffic state and performance analysis, forecasting, control, active sensing, digital twins, and emerging smart-mobility applications.

Content

  • Urban mobility data ecosystems: mobility observatories, sensing technologies, open data, data pipelines, cleaning, validation, aggregation and privacy-aware data management.
  • From data to mobility information: trajectory extraction, map matching, object detection and tracking, demand inference, and mobility pattern identification from heterogeneous data sources.
  • Traffic state and system performance analysis: estimation and interpretation of speed, density, flow, OD demand, congestion, safety, emissions and environmental indicators.
  • Prediction, control and active sensing for urban mobility systems: short-term traffic forecasting, demand prediction, AI/deep learning methods, reinforcement learning, mobility control, and strategies for actively acquiring information.
  • Digital twins and future mobility applications: use of integrated mobility information for simulation, decision support, drone logistics, autonomous mobility, smart-city operations and emerging urban mobility services.

 

Keywords

Smart Cities; Urban mobility; Mobility data; Traffic forecasting; Drones

 

Learning Prerequisites

Required courses

No mandatory prerequisite specified

Recommended courses

Fundamentals of traffic operations and control (CIVIL-457); Traffic engineering (CIVIL-349)

Important concepts to start the course

Traffic flow fundamentals; transport systems; probability/statistics; geospatial data; Python/data analysis; basic machine learning concepts.

Learning Outcomes

By the end of the course, the student must be able to:

  • Explain data ecosystems and sensing technologies for future urban mobility systems.
  • Apply data cleaning, validation and machine learning methods to urban mobility datasets for traffic analysis and forecasting.
  • Analyze trajectory, sensor and environmental data to estimate urban mobility related indicators.
  • Design data-driven insights and decision-support concepts for future mobility systems and digital twins.
  • Assess / Evaluate forecasting, deep learning and reinforcement learning approaches for mobility analysis and control.

Transversal skills

  • Plan and carry out activities in a way which makes optimal use of available time and other resources.
  • Set objectives and design an action plan to reach those objectives.
  • Use both general and domain specific IT resources and tools
  • Access and evaluate appropriate sources of information.
  • Make an oral presentation.

Teaching methods

Lectures with slides; invited lecture; in-class discussions and demonstrations; hands-on computational/data exercises; project work with real urban mobility datasets.

 

Expected student activities

Attend lectures, participate in exercises and discussions, analyze real mobility datasets, complete hands-on work, collaborate on the project, and present final results.

Assessment methods

Midterm assessment; hands-on project work/reports or notebooks; final project presentation. Weighting and detailed format to be confirmed.

 

Supervision

Office hours Yes
Assistant.e.s Yes
Forum No

Resources

Virtual desktop infrastructure (VDI)

No

Bibliography

  • Barmpounakis, E., & Geroliminis, N. (2020). On the new era of urban traffic monitoring with massive drone data: The pNEUMA large-scale field experiment. Transportation research part C: emerging technologies, 111, 50-71.
  • Mahajan, V., Barmpounakis, E., Alam, M. R., Geroliminis, N., & Antoniou, C. (2023). Treating Noise and Anomalies in Vehicle Trajectories From an Experiment With a Swarm of Drones. IEEE Transactions On Intelligent Transportation Systems, 24 (9), 9055-9067.
  • Espadaler-Clapés, J., Barmpounakis, E., & Geroliminis, N. (2023). Traffic congestion and noise emissions with detailed vehicle trajectories from UAVs. Transportation Research Part D: Transport and Environment, 121, 103822.
  • Barmpounakis, M., Espadaler-Clapés, J., Tsitsokas, D., Mordan, T., & Geroliminis, N. (2025). A New Perspective on Urban Mobility Through Large-Scale Drone Experiments for Smarter, Sustainable Cities. Drones, 9(9), 637.
  • Xu, M., & Geroliminis, N. (2026). Knowledge-aware path planning for UAV parcel delivery and road monitoring. Transportation Research Part C: Emerging Technologies, 190, 105780.

Moodle Link

In the programs

  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Future urban mobility systems
  • Courses: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Lab: 1 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Future urban mobility systems
  • Courses: 2 Hour(s) per week x 14 weeks
  • Exercises: 1 Hour(s) per week x 14 weeks
  • Lab: 1 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.