Research map / Vision-language and multimodal / Robot action and navigation
Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
Bing Wu, Zuyao Chen, Chang Wen Chen
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 exploration evidence to the belief (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SR: 76.0 -> 80.1 | Improved |
| add exploration evidence to the belief (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SPL: 37.4 -> 39.5 | Improved |
| add long-horizon rollouts (H>0) (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SR: 76.7 -> 80.1 | Improved |
| add long-horizon rollouts (H>0) (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SPL: 35.9 -> 39.5 | Improved |
| add zone level to the hierarchy (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SR: 79.5 -> 80.1 | Improved |
| add zone level to the hierarchy (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SPL: 38.2 -> 39.5 | Improved |
| use Qwen3-VL-8B instead of Qwen3-VL-4B (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SR: 77.2 -> 80.1 | Improved |
| use Qwen3-VL-8B instead of Qwen3-VL-4B (ablation) | HSG belief planner · ObjectNav HM3Dv2 | SPL: 37.9 -> 39.5 | Improved |
| increase planning horizon H too far (ablation) | HSG belief planner · ObjectNav HM3Dv2 long-range | SR/SPL | Hurt |
| use deeper hierarchy L=2 instead of L=1 (needs shorter horizon) (ablation) | HSG belief planner · ObjectNav HM3Dv2 long-range | SR/SPL | Mixed |
| replace ApexNav with HSG belief planner | zero-shot ObjectNav · ObjectNav (four datasets) | SR and SPL: 5.4% and 2.3% | Improved |
| replace UniGoal with HSG belief planner | zero-shot TextInstanceNav · TextInstanceNav | SR: 20.2 -> 38.1 | Improved |
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.93)
- Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation (CVPR 2026 · similarity 0.93)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.90)
- D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation (CVPR 2026 · similarity 0.89)
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · 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.
