Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Weichen, Tang, Peizhi, Zeng, Xin, Man, Fanhang, Yu, Shiquan, Dai, Zichao, Zhao, Baining, Chen, Hongjin, Shang, Yu, Wu, Wei, Gao, Chen, Chen, Xinlei, Wang, Xin, Li, Yong, Zhu, Wenwu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917182568398848
author Zhang, Weichen
Tang, Peizhi
Zeng, Xin
Man, Fanhang
Yu, Shiquan
Dai, Zichao
Zhao, Baining
Chen, Hongjin
Shang, Yu
Wu, Wei
Gao, Chen
Chen, Xinlei
Wang, Xin
Li, Yong
Zhu, Wenwu
author_facet Zhang, Weichen
Tang, Peizhi
Zeng, Xin
Man, Fanhang
Yu, Shiquan
Dai, Zichao
Zhao, Baining
Chen, Hongjin
Shang, Yu
Wu, Wei
Gao, Chen
Chen, Xinlei
Wang, Xin
Li, Yong
Zhu, Wenwu
contents Unmanned aerial vehicles (UAVs) have emerged as powerful embodied agents. One of the core abilities is autonomous navigation in large-scale three-dimensional environments. Existing navigation policies, however, are typically optimized for low-level objectives such as obstacle avoidance and trajectory smoothness, lacking the ability to incorporate high-level semantics into planning. To bridge this gap, we propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions, thereby enabling agents to rank candidate trajectories by their semantic plausibility and navigational utility. ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection (FFP), which projects past frames into future viewpoints to provide coarse geometric priors. This module mitigates representational uncertainty in long-distance visual generation and captures the mapping between 3D trajectories and egocentric observations. Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21887
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
Zhang, Weichen
Tang, Peizhi
Zeng, Xin
Man, Fanhang
Yu, Shiquan
Dai, Zichao
Zhao, Baining
Chen, Hongjin
Shang, Yu
Wu, Wei
Gao, Chen
Chen, Xinlei
Wang, Xin
Li, Yong
Zhu, Wenwu
Robotics
Artificial Intelligence
Unmanned aerial vehicles (UAVs) have emerged as powerful embodied agents. One of the core abilities is autonomous navigation in large-scale three-dimensional environments. Existing navigation policies, however, are typically optimized for low-level objectives such as obstacle avoidance and trajectory smoothness, lacking the ability to incorporate high-level semantics into planning. To bridge this gap, we propose ANWM, an aerial navigation world model that predicts future visual observations conditioned on past frames and actions, thereby enabling agents to rank candidate trajectories by their semantic plausibility and navigational utility. ANWM is trained on 4-DoF UAV trajectories and introduces a physics-inspired module: Future Frame Projection (FFP), which projects past frames into future viewpoints to provide coarse geometric priors. This module mitigates representational uncertainty in long-distance visual generation and captures the mapping between 3D trajectories and egocentric observations. Empirical results demonstrate that ANWM significantly outperforms existing world models in long-distance visual forecasting and improves UAV navigation success rates in large-scale environments.
title Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2512.21887