Research map / Vision-language and multimodal / Robot action and navigation
Hi-Nav: Hierarchical Framework for Continuous Vision-Language Navigation via Map Guidance and Waypoint Reasoning
Zhiyu Zhou, Bin Guan, Wenbin Yang, Zhi Gao, Hao Fang
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 depth encoder (ablation) | Hi-VLN · VLN-CE R2R Val-Unseen | SR: 21.8 -> 22.8 | No clear effect |
| add cross-attention RGB-depth fusion (ablation) | Hi-VLN with depth · VLN-CE R2R Val-Unseen | SR: 22.8 -> 40.9 | Improved |
| add temporal embeddings (ablation) | Hi-VLN · VLN-CE R2R Val-Unseen | SR: 40.9 -> 47.3 | Improved |
| add ISOM map guidance (ablation) | Hi-Nav · Gazebo overall | SR: 25.0 -> 53.3 | Improved |
| add sub-task decomposition (ablation) | Hi-Nav without ISOM · Gazebo overall | SR: 25.0 -> 26.7 | No clear effect |
| combine sub-task decomposition with ISOM (ablation) | Hi-Nav · Gazebo overall | SR: 53.3 -> 80.0 | Improved |
| hierarchical Hi-Nav vs end-to-end baselines | Hi-Nav · Gazebo overall | SR: 33.3 -> 80.0 | Improved |
| hierarchical Hi-Nav vs Uni-NaVid on hard tasks | Hi-Nav · Gazebo Hard | SR: 20.0 -> 70.0 | Improved |
Closest papers by meaning
- Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation (CVPR 2026 · similarity 0.91)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.91)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.91)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.89)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.89)
- OVER-NAV: Elevating Iterative Vision-and-Language Navigation with Open-Vocabulary Detection and StructurEd Representation (CVPR 2024 · similarity 0.88)
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.
