AI Paper Atlas

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

IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environments

Xu Liu, Yu Liu, Hanshuo Qiu, Yang Qirong, Zhouhui Lian

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 15 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 GPT-4o instruction decomposition into short sub-instructions executed sequentially by pi0 (ablation)pi0 VLA policy · IndoorUAV-VLN test seenSR (%): 2.92 -> 7.29Improved
add GPT-4o instruction decomposition into short sub-instructions executed sequentially by pi0 (ablation)pi0 VLA policy · IndoorUAV-VLN test unseenSR (%): 2.83 -> 5.06Improved
use fine-tuned pi0 instead of LSTM-style Seq2Seq/CMA on short-horizon tasksIndoorUAV-VLA · IndoorUAV-VLA test (full)SR (%): 1.33 (Seq2Seq) -> 27.16Improved
fine-tune NaVid on IndoorUAV (ground-based VLM) for long-horizon VLNNaVid · IndoorUAV-VLN test seenSR (%): OSR 14.70 vs SR 0.75Hurt
increase task difficulty from easy to hardpi0 (fine-tuned) · IndoorUAV-VLA testSR (%): 46.58 -> 7.55Hurt
use GPT-4o zero-shot instead of fine-tuned models on long-horizon VLN (unseen)GPT-4o · IndoorUAV-VLN test unseenSR (%): 0.56 vs 5.06 (Ours)Hurt

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