Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 HiNL with a VTNet visual extractor instead of the strongest reported baseline | Object-goal visual navigation · iTHOR | Success rate (%): 75.1±0.8 -> 80.1±1.4 | Helped |
| Use HiNL with a VTNet visual extractor instead of the strongest reported baseline | Object-goal visual navigation · iTHOR | SPL (%): 47.7±0.9 -> 49.8±1.9 | Helped |
| Use HiNL with a VTNet visual extractor instead of VTNet | Object-goal visual navigation · RoboTHOR | Success rate (%): 53.2±1.1 -> 60.6±1.0 | Helped |
| Use HiNL with a VTNet visual extractor instead of VTNet | Object-goal visual navigation · RoboTHOR | SPL (%): 27.5±1.7 -> 30.8±1.2 | Helped |
| Add HaSE to HiNL (ablation) | HiNL with VTNet visual extractor · iTHOR | Success rate (%): 77.9 -> 80.1 | Helped |
| Add HaSE to HiNL (ablation) | HiNL with VTNet visual extractor · iTHOR | SPL (%): 45.7 -> 49.8 | Helped |
| Add HbSR to HiNL (ablation) | HiNL with VTNet visual extractor · iTHOR | Success rate (%): 75.4 -> 80.1 | Helped |
| Add HbSR to HiNL (ablation) | HiNL with VTNet visual extractor · iTHOR | SPL (%): 46.9 -> 49.8 | Helped |
| Use absolute temporal embedding rather than no temporal embedding (ablation) | HaSE in HiNL with VTNet visual extractor · iTHOR | SPL (%): 39.8 -> 49.8 | Helped |
| Use absolute rather than learnable temporal embedding (ablation) | HaSE in HiNL with VTNet visual extractor · iTHOR | SPL (%): 45.8 -> 49.8 | Helped |
| Use absolute rather than relative temporal embedding (ablation) | HaSE in HiNL with VTNet visual extractor · iTHOR | SPL (%): 44.1 -> 49.8 | Helped |
| Regularize only positive state correlations rather than both positive and negative correlations (ablation) | HbSR in HiNL with VTNet visual extractor · iTHOR | Success rate (%): 75.4 -> 80.1 | Helped |
Closest papers by meaning
- Online Learning of Reusable Abstract Models for Object Goal Navigation (CVPR 2022 · similarity 0.87)
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.87)
- C-NAV: Towards Self-Evolving Continual Object Navigation in Open World (NeurIPS 2025 · similarity 0.86)
- HiconAgent: History Context-aware Policy Optimization for GUI Agents (CVPR 2026 · similarity 0.86)
- Trajectory Diffusion for ObjectGoal Navigation (NeurIPS 2024 · similarity 0.86)
- Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR 2024 · similarity 0.86)
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.