Smart Cities Center

Mobiliti is introduced as a foundation for a Digital Twin for managing transportation systemsTransportation systems across metropolitan regions and for planning and designing urban networks. Regional transportation systemsTransportation systems consist of interconnected subnetworks, each governed by different municipalities. Although localization simplifies analysis, transportation projects must be evaluated within the context of the larger regional network due to their potential impacts on overall network performance. The computational challenges of simulating metropolitan networks are...

Traffic assignment methods are some of the key approaches used to model flow patterns that arise in transportation networks. Since static traffic assignment does not have a notion of time, it is not designed to represent temporal dynamics that arise as vehicles flow through the network and demand varies through the day. Dynamic traffic assignment methods attempt to resolve these issues, but require significant computational resources if modeling urban-scale regions (on the order of millions of links and vehicles) and often take days of compute time to complete. The focus of this work is...

In this paper, we address the problem of recovering traveled geospatial paths on a transportation network from time sampled location traces. Determining the proper sampling rate for path reconstruction has not traditionally been addressed ahead of the collection process. Instead various uncertainty models have been created and tuned to estimate possible geospatial paths from an existing set of location measurements. This paper suggests that the geospatial road density sets a fundamental constraint on the sampling frequency. The result shows that a sufficient sampling rate is determined by...

Large-scale highway traffic forecasting approaches are critical for intelligent transportation systems. Recently, deep- learning-based traffic forecasting methods have emerged as promising approaches for a wide range of traffic forecasting tasks. These methods are specific to a given traffic network, however, and consequently they cannot be used for forecasting traffic on an unseen traffic network. Previous work has identified diffusion convolutional recurrent neural networks, (DCRNN), as a state-of- the-art method for highway traffic forecasting. It models the complex spatial and temporal...