# DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning

arXiv: https://arxiv.org/abs/2609.36845 · HTML: https://mlsanity.com/paper/2609.36845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for navigation, one of 11 directions in World models.
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- World models / [World models for navigation](https://mlsanity.com/wm/world-models-for-navigation/)

## Builds on (most cited first, 25 of 25)

- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics](https://mlsanity.com/paper/2511.08544/) (2025)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks](https://mlsanity.com/paper/1810.10408/) (2018)
- [General agents contain world models](https://mlsanity.com/paper/2506.01622/) (2025)
- [Deep Reinforcement Learning Based Dynamic Trajectory Control for UAV-assisted Mobile Edge Computing](https://mlsanity.com/paper/1911.03887/) (2019)
- [Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges](https://mlsanity.com/paper/2405.17454/) (2024)
- [Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction](https://mlsanity.com/paper/2311.12472/) (2023)
- [Evolutionary Multi-Objective Reinforcement Learning Based Trajectory Control and Task Offloading in UAV-Assisted Mobile Edge Computing](https://mlsanity.com/paper/2202.12028/) (2022)
- [Multi-objective Optimization for Multi-UAV-assisted Mobile Edge Computing](https://mlsanity.com/paper/2404.15292/) (2024)
- [ChatTraffic: Text-to-Traffic Generation via Diffusion Model](https://mlsanity.com/paper/2311.16203/) (2023)
- [Networked ISAC for Low-Altitude Economy: Coordinated Transmit Beamforming and UAV Trajectory Design](https://mlsanity.com/paper/2406.16946/) (2024)
- [Distributionally Robust Optimization for Aerial Multi-access Edge Computing via Cooperation of UAVs and HAPs](https://mlsanity.com/paper/2506.01972/) (2025)
- [MobiWorld: World Models for Mobile Wireless Network](https://mlsanity.com/paper/2507.09462/) (2025)
- [TJCCT: A Two-timescale Approach for UAV-assisted Mobile Edge Computing](https://mlsanity.com/paper/2403.15828/) (2024)
- [Hierarchical Multi-Agent DRL Based Dynamic Cluster Reconfiguration for UAV Mobility Management](https://mlsanity.com/paper/2412.16167/) (2024)
- [Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication](https://mlsanity.com/paper/2401.17880/) (2024)
- [Dynamic Trajectory Optimization and Power Control for Hierarchical UAV Swarms in 6G Aerial Access Network](https://mlsanity.com/paper/2508.18702/) (2025)
- [LAGS: Low-Altitude Gaussian Splatting with Groupwise Heterogeneous Graph Learning](https://mlsanity.com/paper/2604.16910/) (2026)

## Abstract (arXiv)

Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-entropy method whose imagined demand is anchored on the current observation window with mixing coefficient ρ=0.95. On a unified pipeline over three real datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.