Research map / Vision-language and multimodal / Robot action and navigation
PanoNav: Mapless Zero-Shot Object Navigation with Panoramic Scene Parsing and Dynamic Memory
Qunchao Jin, Yilin Wu, Changhao 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 |
|---|---|---|---|
| use six-view panorama instead of three forward views (ablation) | PanoNav · HM3D ObjectNav (200 val episodes) | SR (%): 19.5 -> 43.5 | Improved |
| decouple parsing (MLLM) and decision (LLM) instead of one-step (ablation) | PanoNav · HM3D ObjectNav (200 val episodes) | SR (%): 35.0 -> 43.5 | Improved |
| add Dynamic Bounded Memory Queue (ablation) | PanoNav · HM3D ObjectNav (200 val episodes) | SR (%): 38.5 -> 43.5 | Improved |
| add memory queue in deadlock test (ablation) | PanoNav · Deadlock avoidance test (5 deceptive episodes x 10 runs) | SR (%): 12.0 -> 48.0 | Improved |
| add memory queue in deadlock test (ablation) | PanoNav · Deadlock avoidance test (5 deceptive episodes x 10 runs) | Escape rate (%): 32.0 -> 82.0 | Improved |
| PanoNav vs PixNav, same RGB-only mapless setting | PanoNav · HM3D ObjectNav (200 val episodes) | SR (%): 37.9 -> 43.5 | Improved |
| PanoNav vs strongest baselines with depth or maps | PanoNav · HM3D ObjectNav (200 val episodes) | SR (%): 43.5 vs 62.0 (OVRL), 53.0 (ImagineNav), 52.2 (VLFM) | Hurt |
| PanoNav vs VLFM on SPL | PanoNav · HM3D ObjectNav (200 val episodes) | SPL (%): 23.7 vs 30.4 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 3 on most shared results.
- ImagineNav — ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025) · better on 0 of 2 shared results
- VoroNav — VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model (ICML 2024) · better on 1 of 2 shared results
- ZSON — ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings (NeurIPS 2022) · better on 2 of 2 shared results
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
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.89)
- VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model (ICML 2024 · similarity 0.89)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025 · similarity 0.88)
- PanoWorld: Towards Spatial Supersensing in 360◦ Panorama World (NeurIPS 2026 · similarity 0.88)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.87)
- SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation (NeurIPS 2024 · similarity 0.87)
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.
