Accurate, resource-efficient localization and tracking enables numerous location-aware services in next-generation wireless networks. However, existing machine learning-based methods often require large labeled datasets while overlooking spectrum and energy efficiencies. To fill this gap, we propose LocDreamer, a world model (WM)-based framework for joint target tracking and scheduling of localization anchors. LocDreamer learns a WM that captures the latent representation of the target motion and localization environment, thereby generating synthetic measurements to imagine arbitrary anchor deployments. These measurements enable imagination-driven training of both the tracking model and the reinforcement learning (RL)-based anchor scheduler that activates only the most informative anchors, which significantly reduce energy and signaling costs while preserving high tracking accuracy. Experiments on a real-world indoor dataset demonstrate that LocDreamer substantially improves data efficiency and generalization, outperforming conventional Bayesian filter with random scheduling by 37% in tracking accuracy, and achieving 86% of the accuracy of same model trained directly on real data.
@article{arxiv.2602.08204,
title = {LocDreamer: World Model-Based Learning for Joint Indoor Tracking and Anchor Scheduling},
author = {Geng Wang and Zhouyou Gu and Shenghong Li and Peng Cheng and Jihong Park and Branka Vucetic and Yonghui Li},
journal= {arXiv preprint arXiv:2602.08204},
year = {2026}
}