# Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation

arXiv: https://arxiv.org/abs/2609.32360 · HTML: https://mlsanity.com/paper/2609.32360/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [A Survey on Deep Learning for Human Mobility](https://mlsanity.com/paper/2012.02825/) (2020)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2007.14189/) (2020)
- [Injecting Semantic Concepts into End-to-End Image Captioning](https://mlsanity.com/paper/2112.05230/) (2021)
- [Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation](https://mlsanity.com/paper/2402.07369/) (2024)

## Abstract (arXiv)

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.