Rafał Kucharski – TU Delft

Rafał Kucharski (TU Delft): Two sided-mobility platforms: supply-demand interactions and ride-pooling shareability networks

Abstract | In this talk I want to introduce you to two of our recent works in TU Delft.

First one is the study on virus spreading in the ride-pooling networks, where we first model how single infector may trigger spreading among travelers sharing a vehicles together. The key challenge is dynamically changing contact network. While the so-called shareability network is highly connected, with hubs and giant component, the daily realization of matching travelers to vehicles is sparse and disconnected. This offers us a nice control measure that we exploit in the study recently published in Scientific Reports: https://doi.org/10.1038/s41598-021-86704-2 .

Second one is our open source lightweight python framework for two-sided mobility platforms. MaaSSim, is an agent-based simulator reproducing the transport system used by two kind of agents: (i) travellers, requesting to travel from their origin to destination at a given time, and (ii) drivers supplying their travel needs by offering them rides. It allows to model complex, non-linear interactions between heterogeneous agents, who may learn and adaptively improve their actions. Report available here https://arxiv.org/abs/2011.12827 with a public repo on https://github.com/RafalKucharskiPK/MaaSSim

Bio | I research complex social systems: urban mobility. Congested, urban multimodal networks used by millions of agents to reach their destinations and leaving huge sets of mobility traces ready to be applied for modelling, optimization, understanding and control.

I work with Oded Cats at TU Delft in his ERC Starting Grant Critical MaaS. I model two-sided mobility platforms, specifcally focusing on ride-pooling (making people share their Uber with co-travellers). I did PhD with Guido Gentile in non-equilibrium dynamic traffic assignment. In the interdisciplinary field of urban mobility I did research which can be classified as:

- model estimation, optimization, system control, network design;
- agent-based simulation, game-theory, network science, stochastic simulation, epidemic modelling;
- machine learning, spatial analysis, big data analysis, pattern recognition, unsupervised learning;
- behavioural modelling, economic discrete choice models, policy, sustainability.

Outside of academia I was:

- Data Scientist at NorthGravity developing AWS-based protfolio or real-time production ready ML solutions
- R&D Developer at PTV SISTeMA implementing algorithms into PTV Optima real-time traffic forecasting models.
- Transport Modeller at Department of Transportation Systems using travel-diaries to estimate demand models and create strategic planning tools, e.g. for Warsaw and Kraków