Keywords: Urban Mobility, Latent variable models, amortized inference, normalizing flows
TL;DR: How can leverage normalizing flows to enable system operators (e.g. Uber, Lyft) to estimate a flexible probability distribution of urban mobility? In this work, we propose Recurrent Flow Networks (RFNs) to capture the evolution of urban mobility.
Abstract: Mobility-on-demand (MoD) systems represent a rapidly developing mode of transportation wherein travel requests are dynamically handled by a coordinated fleet of vehicles. Crucially, the efficiency of an MoD system highly depends on how well supply and demand distributions are aligned in spatio-temporal space (i.e., to satisfy user demand, cars have to be available in the correct place and at the desired time). When modelling urban mobility as temporal sequences, current approaches typically rely on either (i) a spatial discretization (e.g. ConvLSTMs), or (ii) a Gaussian mixture model to describe the conditional output distribution.
In this paper, we argue that both of these approaches could exhibit structural limitations when faced with highly complex data distributions such as for urban mobility densities. To address this issue, we introduce recurrent flow networks which combine deterministic and stochastic recurrent hidden states with conditional normalizing flows and show how the added flexibility allows our model to generate distributions matching potentially complex urban topologies.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 3 code implementations](https://www.catalyzex.com/paper/recurrent-flow-networks-a-recurrent-latent/code)
4 Replies
Loading