# OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency

arXiv: https://arxiv.org/abs/2603.10682 · HTML: https://mlsanity.com/paper/2603.10682/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2026.

## Built on by (most cited first, 4 of 4)

- [See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View](https://mlsanity.com/paper/2606.20045/) (2026)
- [VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots](https://mlsanity.com/paper/2609.20191/) (2026)
- [SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery](https://mlsanity.com/paper/2609.31507/) (2026)
- [LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation](https://mlsanity.com/paper/2610.05024/) (2026)

## Abstract (arXiv)

Aerial vision-language navigation (AVLN) enables UAVs to follow natural-language instructions in complex 3D environments. However, existing zero-shot AVLN methods often suffer from unstable single-stream Vision-Language Model decision-making, unreliable long-horizon progress monitoring, and a trade-off between safety and efficiency. We propose OnFly, a fully onboard, real-time framework for zero-shot AVLN. OnFly adopts a shared-perception dual-agent architecture that decouples high-frequency target generation from low-frequency progress monitoring, thereby stabilizing decision-making. It further employs a hybrid keyframe-recent-frame memory to preserve global trajectory context while maintaining KV-cache prefix stability, enabling reliable long-horizon monitoring with termination and recovery signals. In addition, a semantic-geometric verifier refines VLM-predicted targets for instruction consistency and geometric safety using VLM features and depth cues, while a receding-horizon planner generates optimized collision-free trajectories under geometric safety constraints, improving both safety and efficiency. In simulation, OnFly improves task success from 26.4% to 67.8%, compared with the strongest state-of-the-art baseline, while fully onboard real-world flights validate its feasibility for real-time deployment. The code will be released at https://github.com/Robotics-STAR-Lab/OnFly