Map-conditioned model generates human movement adapting to map edits
Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation
Machine LearningComputers and Society
Summary
Simulating how people move through cities is useful for planning roads and infrastructure. The researchers created a computer model that can generate realistic human movement paths based on maps, and it can react when those maps are edited, like when a bridge is removed. Their model divides the area into small cells and predicts movement step-by-step while looking at the map’s layout. Tests show the model produces more accurate movement patterns when given the correct map compared to randomized maps, supporting its ability to simulate movement changes without retraining.
What this means in practice
- •For urban planning teams: Generate human movement patterns that update automatically when city maps are changed to evaluate infrastructure modifications.
- •For transportation simulation developers: Create mobility simulators that dynamically respond to edited road maps without retraining, improving scenario testing flexibility.
Authors
Takayuki Mizuno, Shouji Fujimoto, Mikito Hiruki, Atushi Ishikawa
Abstract
Geospatial simulation of infrastructure interventions requires mobility generators that respond directly to edited maps, yet many data-driven generators do not expose the map as an editable condition. We formulate this task as map-conditioned autoregressive generation of human mobility: a road raster conditions a decoder that emits nominal 31.25 m mesh-cell tokens at one-minute intervals. The mesh-local vocabulary supports held-out and locally edited maps without retraining or vocabulary changes. We instantiate a ResNet-50 visual-prefix configuration and a Vision Transformer (ViT) cross-attention configuration, trained from scratch on 87,400 smartphone-derived trajectories from 874 meshes in Ishikawa Prefecture, Japan; 219 meshes are held out. We evaluate map sensitivity by comparing correct-map and within-split shuffled-map generations with held-out real trajectories. On the 110-mesh test split, for the ResNet-50 configuration, correct-map generations are closer than shuffled-map generations on 60% of meshes under Hausdorff-based energy distance (p = 0.021), while DTW is directional but inconclusive (57%, p = 0.074); correlation with real density is 0.38 with the correct map versus 0.01 with shuffled maps. The ViT configuration shows weaker trajectory-level sensitivity and smaller density gains. An illustrative bridge-removal edit changes generated continuations without retraining. Together, these results support the feasibility of editable-map human-mobility simulation.