Research map / Vision-language and multimodal / Robot action and navigation
AeroVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control
Peng Xu, Zhengnan Deng, Jiayan Deng, Zonghua Gu, Shaohua Wan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use standard numerical tokens instead of custom action tokens (ablation) | AerialVLA · TravelUAV Unseen Map | SR: 26.51 -> 37.58 | Improved |
| use standard numerical tokens instead of custom action tokens (ablation) | AerialVLA · TravelUAV Seen | SR: 39.84 -> 47.96 | Improved |
| use standard numerical tokens instead of custom action tokens (ablation) | AerialVLA · TravelUAV Unseen Object | SR: 38.79 -> 56.60 | Improved |
| use dual-view (front+down) instead of five views (ablation) | AerialVLA · TravelUAV Unseen Map | SR: 21.71 -> 37.58 | Improved |
| use dual-view (front+down) instead of five views (ablation) | AerialVLA · TravelUAV Seen | SR: 41.54 -> 47.96 | Improved |
| use dual-view (front+down) instead of five views (ablation) | AerialVLA · TravelUAV Unseen Object | SR: 51.51 -> 56.60 | Improved |
| add geometry-consistent filtering of training demonstrations (ablation) | AerialVLA · TravelUAV Unseen Map | SR: 32.15 -> 37.58 | Improved |
| add geometry-consistent filtering of training demonstrations (ablation) | AerialVLA · TravelUAV Seen | SR: 40.90 -> 47.96 | Improved |
| add geometry-consistent filtering of training demonstrations (ablation) | AerialVLA · TravelUAV Unseen Object | SR: 51.99 -> 56.60 | Improved |
| AerialVLA (fuzzy hints, no oracle) vs LongFly | AerialVLA · TravelUAV Unseen Map | SR: 11.27 -> 37.58 | Improved |
| AerialVLA vs LongFly | AerialVLA · TravelUAV Seen | SR: 36.39 -> 47.96 | Improved |
| AerialVLA vs LongFly | AerialVLA · TravelUAV Unseen Object | SR: 43.87 -> 56.60 | Improved |
Closest papers by meaning
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.92)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.89)
- SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery (NeurIPS 2026 · similarity 0.89)
- Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation (CVPR 2026 · similarity 0.88)
- UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning (NeurIPS 2025 · similarity 0.87)
- Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory (CVPR 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
