---
title: "Tsinghua's WorldFly Teaches Drones to Imagine Around Corners Before Flying"
subtitle: "WorldFly teaches drones to imagine their path forward, using a world model to predict future video frames and navigation actions simultaneously in dense urban environments."
url: "https://alphasignal.ai/news/tsinghua-s-worldfly-teaches-drones-to-imagine-around-corners-before-flying"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-04T00:00:00.000Z"
updated: "2026-06-12T01:43:43.691Z"
type: "Paper"
topics:
  - "Robotics"
  - "Video"
subtopics:
  - "Vla Models"
  - "Autonomous Driving"
  - "World Models"
upvotes: 1775
source_url: "https://arxiv.org/abs/2606.06147"
comments: 0
truncated: true
---

# Tsinghua's WorldFly Teaches Drones to Imagine Around Corners Before Flying

> WorldFly teaches drones to imagine their path forward, using a world model to predict future video frames and navigation actions simultaneously in dense urban environments.

Most autonomous drone navigation systems react to what they can see right now. That works fine in open skies, but in dense urban environments -- tight corridors between buildings, sharp corners, sudden occlusions -- a purely reactive approach breaks down fast. A new paper from researchers at Tsinghua University and Ryerson University proposes a different strategy: teach the drone to **imagine** what it is about to see before it gets there.

The result is [WorldFly](https://arxiv.org/abs/2606.06147), a Vision-Language-Action (VLA) framework that couples a world model directly into the navigation policy. Rather than mapping observations to actions in one step, WorldFly jointly generates a prediction of future video frames **and** the corresponding flight actions at the same time, using each to guide the other.

## Why drones struggle in cities

Extending the VLA paradigm to aerial platforms introduces fundamental challenges absent in ground-based settings. UAVs operate in a fully dynamic 6-DoF state space subject to continuous gravitational and inertial forces, where pitch and roll dynamics are tightly coupled with translational motion. Add buildings into the mix and the problem compounds: a drone rounding a corner between two skyscrapers loses visual context almost instantly.

Current vision-language navigation research for UAVs relies on detailed, pre-specified instructions to guide the UAV along predetermined routes. However, real-world outdoor exploration typically occurs in unknown environments where detailed navigation instructions are unavailable. Instead, only coarse-grained positional or directional guidance can be provided, requiring UAVs to autonomously navigate through continuous planning and obstacle avoidance.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation](https://arxiv.org/abs/2606.06147)
- [OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation](https://arxiv.org/html/2502.18041v6)
- [AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild](https://arxiv.org/abs/2602.09657)
- [World Model for Robot Learning: A Comprehensive Survey](https://arxiv.org/html/2605.00080v1)
- [AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control](https://arxiv.org/pdf/2603.14363)