Research map / Multi-agent systems and games / Human-AI and goal-conditioned
LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning
Jiawei Hou, Yuting Xiao, Xiangyang Xue, Taiping Zeng
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 local imperative planning to the global waypoint plan (ablation) | LOG-Nav · Real-world, 3 obstacles | SR (10 trials): 1/10 -> 6/10 | Improved |
| add local imperative planning to the global waypoint plan (ablation) | LOG-Nav · Real-world, 2 obstacles | SR (10 trials): 3/10 -> 8/10 | Improved |
| add local imperative planning to the global waypoint plan (ablation) | LOG-Nav · Real-world, 1 obstacle | SR (10 trials): 7/10 -> 10/10 | Improved |
| add local imperative planning to the global waypoint plan (ablation) | LOG-Nav · Real-world, 3 obstacles | time cost (s): 134 -> 116 | Improved |
| add local imperative planning to the global waypoint plan (ablation) | LOG-Nav · Real-world, 0 obstacles | time cost (s): 102 -> 96 | Improved |
| add global topological planning on top of local planning only (ablation) | LOG-Nav · MP3D (SR vs target distance) | SR | Improved |
| increase number of repeated runs in same workspace (amortize mapping) | LOG-Nav · MP3D repeated runs | SPL: 0.083 -> 0.656 | Improved |
| LOG-Nav explore-then-plan vs ESC in a single run | LOG-Nav · MP3D repeated runs (1-time run) | SPL: 0.249 -> 0.083 | Hurt |
| use image goal instead of text goal for chair target | LOG-Nav · Real-world chair | SR (10 trials): 10/10 -> 7/10 | Hurt |
| use image goal instead of text goal for sofa target | LOG-Nav · Real-world sofa | SR (10 trials): 6/10 -> 3/10 | Hurt |
| use instance navigation text-goal vs object navigation | LOG-Nav · MP3D | SR: 0.856 -> 0.786 | Hurt |
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.85)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.85)
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval (NeurIPS 2025 · similarity 0.84)
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World (NeurIPS 2025 · similarity 0.84)
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation (NeurIPS 2024 · similarity 0.84)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.83)
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.
