Generating people flow from architecture of real unseen environments

Mapping people dynamics is a crucial skill, because it enables robots to coexist in human-inhabited environments. However, learning a model of people dynamics is a time consuming process which requires observation of large amount of people moving in an environment. Moreover, approaches for mapping dynamics are unable to transfer the learned models across environments: each model only able to describe the dynamics of the environment it has been built in. However, the effect of architectural geometry on people movement can be used to estimate their dynamics, and recent work has looked into learning maps of dynamics from geometry. So far however, these methods have evaluated their performance only on small-size synthetic data, leaving the actual ability of these approaches to generalize to real conditions unexplored. In this work we propose a novel approach to learn people dynamics from geometry, where a model is trained and evaluated on real human trajectories in large-scale environments. We then show the ability of our method to generalize to unseen environments, which is unprecedented for maps of dynamics.