Research map / Vision-language and multimodal / Robot action and navigation
FloVerse: Floor Plan-Guided Multi-Modal Navigation
Weiqi Huang, Shuangyi Dong, Jiaxin Li, Yifei Guo, Zan Wang, Wei Liang
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 floor plan input (ablation) | ThreeDiff · PointNav | SR: 25.8 -> 42.0 | Improved |
| add floor plan input (ablation) | ThreeDiff · ImageNav | SR: 22.6 -> 28.9 | Improved |
| add floor plan input (ablation) | ThreeDiff · ObjectNav | SR: 20.9 -> 28.6 | Improved |
| add floor plan input (ablation) | ThreeDiff · ObjectNav | SPL: 16.5 -> 22.3 | Improved |
| train jointly on three modalities with random masking vs Point-only (ablation) | ThreeDiff · PointNav | SPL: 38.9 -> 36.6 | Hurt |
| train jointly on three modalities vs Image-only (ablation) | ThreeDiff · ImageNav | SR: 25.4 -> 28.9 | Improved |
| train jointly on three modalities vs Object-only (ablation) | ThreeDiff · ObjectNav | SR: 24.3 -> 28.6 | Improved |
| add depth-based refiner (ablation) | ThreeDiff · PointNav | SR: 34.3 -> 42.0 | Improved |
| add depth-based refiner (ablation) | ThreeDiff · ImageNav | SR: 27.7 -> 28.9 | Improved |
| use ThreeDiff vs RL Skill Chain on GOAT ImageNav | ThreeDiff · GOAT-Bench ImageNav | SR: 42.2 -> 31.0 (SR), 18.0 -> 25.6 (SPL) | Mixed |
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.
- ZSON — ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings (NeurIPS 2022) · better on 1 of 1 shared result
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
- FloNa: Floor Plan Guided Embodied Visual Navigation (AAAI 2025 · similarity 0.93)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.86)
- RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation (CVPR 2025 · similarity 0.86)
- REGNav: Room Expert Guided Image-Goal Navigation (AAAI 2025 · similarity 0.86)
- Task Planning for Object Rearrangement in Multi-Room Environments (AAAI 2024 · similarity 0.86)
- NavBench: Probing Multimodal Large Language Models for Embodied 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.
