Research map / Vision-language and multimodal / Robot action and navigation
Adaptive Zone-Aware Hierarchical Planner for Vision-Language Navigation
Chen Gao, Xingyu Peng, Mi Yan, He Wang, Lirong Yang, Haibing Ren, Hongsheng Li, Si Liu
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 |
|---|---|---|---|
| Use adaptive zone-aware hierarchical planning instead of DUET's single-step planning | VLN agents · REVERIE val-unseen | SPL: 33.73 -> 36.63 | Improved |
| Use adaptive zone-aware hierarchical planning instead of DUET's single-step planning | VLN agents · SOON val-unseen | SR: 36.28 -> 40.71 | Improved |
| Use adaptive zone-aware hierarchical planning instead of DUET's single-step planning | VLN agents · R2R test-unseen | SR: 69 -> 71 | Improved |
| Add hierarchical high-level action with heuristic SSM, partition, and selection (ablation) | AZHP Base-Net · REVERIE val-unseen | SR: 43.62 -> 44.90 | Improved |
| Add learned State-Switcher Module (SSM) (ablation) | AZHP #1 · REVERIE val-unseen | SR: 44.90 -> 46.95 | Improved |
| Add scene-aware adaptive zone partition (SZP) (ablation) | AZHP #2 · REVERIE val-unseen | SR: 46.95 -> 49.50 | Improved |
| Add goal-oriented zone selection (GZS) (ablation) | AZHP #3 · REVERIE val-unseen | SPL: 34.13 -> 36.63 | Improved |
| Set zone partition ratio to 0.3 rather than 0 (ablation) | AZHP · REVERIE val-unseen | SPL: 28.20 -> 36.63 | Improved |
| Increase zone partition ratio from 0.3 to 0.6 (ablation) | AZHP · REVERIE val-unseen | SPL: 36.63 -> 35.54 | Hurt |
| Increase zone partition ratio from 0.6 to 0.8 (ablation) | AZHP · REVERIE val-unseen | SPL: 35.54 -> 34.65 | Hurt |
| Set SZP distance threshold THRd to 6 rather than 0 (ablation) | AZHP · REVERIE val-unseen | SPL: 32.32 -> 36.63 | Improved |
| Increase SZP distance threshold from 6 to 8 (ablation) | AZHP · REVERIE val-unseen | SPL: 36.63 -> 33.69 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DUET — DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (AAAI 2023) · better on 12 of 13 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.90)
- STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization (NeurIPS 2025 · similarity 0.89)
- Affordances-Oriented Planning Using Foundation Models for Continuous Vision-Language Navigation (AAAI 2025 · similarity 0.88)
- General Scene Adaptation for Vision-and-Language Navigation (ICLR 2025 · similarity 0.88)
- Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method (CVPR 2025 · similarity 0.88)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 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.
