Research map / Graph learning / Knowledge and temporal graphs
STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
Hao Ren, Zetong Bi, Yiming Zeng, Zhaoliang Wan, Lu Qi, Hui Cheng
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 spatial graph aggregation (ablation) | STRNet · 2D-3D-S long-horizon | success rate (%): 88% -> 98% | Improved |
| add spatial graph aggregation (ablation) | STRNet · 2D-3D-S long-horizon | collision: 0.12 -> 0.02 | Improved |
| add temporal fusion module (ablation) | STRNet · 2D-3D-S long-horizon | success rate (%): 38% -> 98% | Improved |
| add temporal fusion module (ablation) | STRNet · 2D-3D-S long-horizon | collision: 0.78 -> 0.02 | Improved |
| add both SA and temporal fusion (ablation) | STRNet · 2D-3D-S long-horizon | success rate (%): 28% -> 98% | Improved |
| add spatial aggregation (ablation) | STRNet · 2D-3D-S long-horizon | path length (m): 144.60 -> 145.63 | No clear effect |
| use STRNet encoder instead of NoMaD | NoMaD · Citysim adaptation task | success rate (%): 36% -> 92% | Improved |
| use STRNet encoder instead of NoMaD | NoMaD · 2D-3D-S long-horizon | success rate (%): 30% -> 98% | Improved |
| use STRNet instead of NaviBridger | NaviBridger · Citysim basic task | success rate (%): 60% -> 100% | Improved |
| use STRNet instead of NaviBridger on indoor adaptation | NaviBridger · Indoor 2D-3D-S adaptation task | success rate (%): 100% -> 100% | No clear effect |
| add historical observations to NoMaD (NoMaD vs NoMaD-0) | NoMaD · Indoor 2D-3D-S basic task | success rate (%): 84% -> 70% | Hurt |
| use STRNet under noisy sub-target selection | NaviBridger · 2D-3D-S noisy sub-target | success rate (%): 76% -> 84% | Improved |
Closest papers by meaning
- Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach (CVPR 2025 · similarity 0.86)
- Robotic Visual Instruction (CVPR 2025 · similarity 0.86)
- MemoNav: Working Memory Model for Visual Navigation (CVPR 2024 · similarity 0.86)
- PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs (ICML 2024 · similarity 0.86)
- Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation (NeurIPS 2026 · similarity 0.86)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.85)
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.
