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
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 |
|---|---|---|---|
| add GPT-4o instruction decomposition into short sub-instructions executed sequentially by pi0 (ablation) | pi0 VLA policy · IndoorUAV-VLN test seen | SR (%): 2.92 -> 7.29 | Improved |
| add GPT-4o instruction decomposition into short sub-instructions executed sequentially by pi0 (ablation) | pi0 VLA policy · IndoorUAV-VLN test unseen | SR (%): 2.83 -> 5.06 | Improved |
| use fine-tuned pi0 instead of LSTM-style Seq2Seq/CMA on short-horizon tasks | IndoorUAV-VLA · IndoorUAV-VLA test (full) | SR (%): 1.33 (Seq2Seq) -> 27.16 | Improved |
| fine-tune NaVid on IndoorUAV (ground-based VLM) for long-horizon VLN | NaVid · IndoorUAV-VLN test seen | SR (%): OSR 14.70 vs SR 0.75 | Hurt |
| increase task difficulty from easy to hard | pi0 (fine-tuned) · IndoorUAV-VLA test | SR (%): 46.58 -> 7.55 | Hurt |
| use GPT-4o zero-shot instead of fine-tuned models on long-horizon VLN (unseen) | GPT-4o · IndoorUAV-VLN test unseen | SR (%): 0.56 vs 5.06 (Ours) | Hurt |
Closest papers by meaning
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.94)
- SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery (NeurIPS 2026 · similarity 0.90)
- WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation (NeurIPS 2026 · similarity 0.89)
- Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation (CVPR 2026 · similarity 0.89)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.89)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.89)
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.
