AI Paper Atlas

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

AerialVLN: Vision-and-Language Navigation for UAVs

Shubo Liu, Hongsheng Zhang, Yuankai Qi, Peng Wang, Yanning Zhang, Qi Wu

ICCV 2023 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 126 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 Dataset Aggregation (DA) student-forcing to CMA (ablation)CMA · AerialVLN-S Val SeenSR (%): 3.0 -> 9.9Improved
add Dataset Aggregation to CMA (ablation)CMA · AerialVLN-S Val UnseenSR (%): 3.2 -> 4.5Improved
add look-ahead guidance (LAG) to CMACMA · AerialVLN-S Val UnseenSR (%): 4.5 -> 5.1Improved
add look-ahead guidance (LAG) vs CMA-DACMA · AerialVLN-S Val SeenSR (%): 9.9 -> 7.2Hurt
remove depth input from CMA (ablation)CMA · AerialVLN Val UnseenSR (%): 4.5 -> 3.2Hurt
remove RGB input from CMA (ablation)CMA · AerialVLN Val UnseenSR (%): 4.5 -> 3.0Hurt
remove language instruction from CMA (ablation)CMA · AerialVLN Val UnseenSR (%): 4.5 -> 2.1Hurt
remove all vision from CMA (ablation)CMA · AerialVLN Val UnseenSR (%): 4.5 -> 1.3Hurt
longer pathsSeq2Seq / CMA · AerialVLNSR (%): 7.4% (short) -> 1.8% (long)Hurt
use LingUNet without recurrence instead of Seq2Seq/CMALingUNet · AerialVLN-S unseenSR (%): Test: 0.1 vs Seq2Seq 2.2Hurt

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