The World Outside, the Motion Within: Holistic Spatial Intelligence for UAVs

Haoyu Zhang, Meng Liu, Qianlong Xiang, Qiaohui Chu, Yaowei Wang, Liqiang NieOpenReview 2027 · Submission to ICLR 2027 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Spatial intelligence for unmanned aerial vehicles (UAVs) relies on the tight coupling of external environmental perception and internal ego-motion awareness. However, existing models struggle to preserve spatial knowledge across viewpoint changes and to disentangle ego-motion from object motion while capturing how the UAV's motion shapes future observations. To address these challenges, we introduce EnvSelf-UAV, a unified framework that couples external spatial perception with internal ego-motion understanding. Specifically, a Dynamic Environment Spatial Memory (DESM) module maintains spatially grounded memory by updating regional appearance and geometry across video frames. An Ego-Motion Dynamics Modeling (EMDM) module infers UAV motion from shared geometric changes across matched regions and uses a latent world model to predict future environmental representations conditioned on this motion. A Question-Guided Memory Injection (QGMI) mechanism then selectively integrates environmental, motion, and predictive evidence into a language decoder for spatial reasoning. Extensive evaluations across three key benchmarks demonstrate that EnvSelf-UAV achieves superior performance, while downstream navigation tasks further validate the effectiveness of the proposed architecture.
BibTeX
@misc{zhang2027world,
  author = {Haoyu Zhang and Meng Liu and Qianlong Xiang and Qiaohui Chu and Yaowei Wang and Liqiang Nie},
  title = {{The World Outside, the Motion Within: Holistic Spatial Intelligence for UAVs}},
  year = {2027},
  url = {https://openreview.net/forum?id=HpIznwhIZB},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2027},
}

Loading related content...

Figure