MoS Lab

Mobility Science Lab at Tsinghua University

MoS Lab studies how optimization theory and machine learning can support transportation systems, with research in system resilience, AI for Transportation, travel behavior and demand modeling, and sustainable urban systems.

Explore Research View Publications Join Us

46 publications and working papers

31 journal articles

4 research directions

Featured Research

From passenger-level behavior to city-scale resilience.

Schematic of the individual path recommendation problem on a disrupted rail and bus network (Figure 1, Transportation Science)

Public Transit Resilience

Individual path recommendation under transit disruptions

Models passenger behavior uncertainty and recommends resilient paths during service disruptions.

Read paper

Commuting patterns in Beijing, Munich, and Singapore before and after housing exchange (Figure 2, Nature Sustainability)

Sustainable Urban Systems

Housing exchange to reduce commuting emissions

Uses household-level housing exchange strategies to reduce excess commuting emissions.

Read paper

Pair-wise attention-based pointer neural network architecture (Figure 2, Transportation Research Part E)

Mobility AI

Last-mile delivery route prediction

A pair-wise attention-based pointer neural network that predicts drivers' route trajectories in last-mile delivery.

Read paper

Physical network and time-space hypernetwork representation (Figure 1, Transportation Science)

Public Transit Resilience

Ex post path choice estimation

Estimates urban rail passenger path choices from smart card data via an aggregated time-space hypernetwork.

Read paper

Research Areas

Mobility science for systems that can adapt.

Transportation system resilience When incidents disrupt transportation systems, we develop efficient optimization and machine learning algorithms to adjust operations, guide passengers, and help systems recover quickly.

AI for Transportation: We study real-time decision-making with reinforcement learning, time-series foundation models, and transportation management agents across public transit, shared mobility, and supply-chain logistics.

Travel behavior and demand modeling We combine policy analysis, surveys, econometric models, machine learning, and optimization to improve traditional behavioral and demand models.

Sustainable urban systems We study commuting carbon emissions, public health risk, housing mobility, and urban cyber-physical-social system resilience for top interdisciplinary venues.

Research Support