{"ID":2896210,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08885","arxiv_id":"2507.08885","title":"AirScape: An Aerial Generative World Model with Motion Controllability","abstract":"How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predicts future observation sequences based on current visual inputs and motion intentions. Specifically, we construct a dataset for aerial world model training and testing, which consists of 11k video-intention pairs. This dataset includes first-person-view videos capturing diverse drone actions across a wide range of scenarios, with over 1,000 hours spent annotating the corresponding motion intentions. Then we develop a two-phase schedule to train a foundation model--initially devoid of embodied spatial knowledge--into a world model that is controllable by motion intentions and adheres to physical spatio-temporal constraints. Experimental results demonstrate that AirScape significantly outperforms existing foundation models in 3D spatial imagination capabilities, especially with over a 50% improvement in metrics reflecting motion alignment. The project is available at: https://embodiedcity.github.io/AirScape/.","short_abstract":"How to enable agents to predict the outcomes of their own motion intentions in three-dimensional space has been a fundamental problem in embodied intelligence. To explore general spatial imagination capability, we present AirScape, the first world model designed for six-degree-of-freedom aerial agents. AirScape predict...","url_abs":"https://arxiv.org/abs/2507.08885","url_pdf":"https://arxiv.org/pdf/2507.08885v2","authors":"[\"Baining Zhao\",\"Rongze Tang\",\"Mingyuan Jia\",\"Ziyou Wang\",\"Fanghang Man\",\"Xin Zhang\",\"Yu Shang\",\"Weichen Zhang\",\"Wei Wu\",\"Chen Gao\",\"Xinlei Chen\",\"Yong Li\"]","published":"2025-07-10T16:05:30Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}