AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

AerialVLA: A Vision-Language-Action Model for Aerial Navigation with Online Dialogue

Jinyu Chen, Hongyu Li, Zongheng Tang, Xiaoduo Li, Wenjun Wu, Si Liu

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add OTDA data augmentation (ablation)AerialVLA baseline · AVDH seen validationSPL: 3.1 -> 13.0Improved
add OTDA data augmentation (ablation)AerialVLA baseline · AVDH unseen validationSPL: 5.5 -> 17.3Improved
replace video features with global map of history (ablation)AerialVLA with OTDA · AVDH seen validationSPL: 13.0 -> 21.1Improved
replace video features with global map of history (ablation)AerialVLA with OTDA · AVDH unseen validationSPL: 17.3 -> 19.5Improved
add Spatial-Temporal Attention (ablation)AerialVLA with OTDA and global map · AVDH unseen validationSPL: 19.5 -> 26.6Improved
add Spatial-Temporal Attention (ablation)AerialVLA with OTDA and global map · AVDH seen validationSPL: 21.1 -> 25.4Improved
use original-to-generated data ratio 1:2 instead of 1:1 (ablation)OTDA · AVDH unseen validationSPL: 14.4 -> 26.6Improved
increase generated data ratio from 1:2 to 1:3 (ablation)OTDA · AVDH unseen validationSPL: 26.6 -> 20.5Hurt
use STA distances 1,2,3 instead of higher 1,3,5 (ablation)STA · AVDH unseen validationSPL: 24.0 -> 26.6Improved
use STA distances 1,2,3 instead of lower 1,1,1 (ablation)STA · AVDH unseen validationSPL: 23.0 -> 26.6Improved
add PNaQ proactive questioning (online dialogue) instead of pre-recorded dialoguesAerialVLA · UNOD unseen validationSPL: 13.7 -> 21.6Improved
use AerialVLA instead of HAA-T on long-dialogue benchmarkAVDH-Full unseen testing · AVDH-Full unseen testingSPL: 4.3 -> 17.1Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy