RADELN
Bicycle infrastructure & network design – a human-centric, data-driven approach using spatio-temporal machine learning
Principle Investigators
Prof. Dr. Klaus Bogenberger,
Chair of Traffic Engineering and Control, Department of Mobility Systems Engineering
Prof. Dr. Stephan Günnemann,
Chair of Data Analytics and Machine Learning, Department of Informatics
Project contributors
Dr.-Ing. Simone Weikl,
Chair of Traffic Engineering and Control, Department of Mobility Systems Engineering
Victoria Dahmen, M.Sc.,
Chair of Traffic Engineering and Control, Department of Mobility Systems Engineering
Dominik Fuchsgruber, M.Sc.,
Chair of Data Analytics and Machine Learning, Department of Informatics
Project summary
The aim of the RADELN project is to give more incentive to travel by bike by optimally improving the cycling infrastructure within Munich and to its neighbouring regions. The type of cycle path and the cohesiveness of the cycling network play a key role in modal choice behaviour. To ensure a holistic approach we will also account for factors like the financial feasibility of proposals and existing cycling infrastructure.
We will be using novel spatio-temporal graph-based machine learning methods as the main prediction engine.
The project is split into three subprojects:
- What is the predicted bicycle mode share for a given O-D pair assuming a specific bicycle network with specific infrastructure design?
- Which bicycle network & infrastructure design maximizes bike usage for all O-D pairs in the road network of the Munich metropolitan area while fulfilling certain constraints?
- How can the local authorities prioritize, plan & implement individual infrastructure measures leading to the target picture?
Project (preliminary) results
Tasks covered so far:
- Preparation of tracking data: general assessment (validation, plausibility, correction) as well as further processing (map matching, imputation, enrichment)
- Preparation of cycle network data: data cleansing, simplification, processing, completeness
- Development of Simplicial Complex Neural Networks for traffic trajectory prediction