Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Pathdreamer: A World Model for Indoor Navigation
Jing Yu Koh, Honglak Lee, Yinfei Yang, Jason Baldridge, Peter Anderson
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 |
|---|---|---|---|
| replace repeated-panorama look-ahead with Pathdreamer predictions (3 planning steps) | VLN agent with compatibility model · R2R Val-Unseen VLN | SR: 40.6 -> 50.4 | Improved |
| replace repeated-panorama look-ahead with Pathdreamer predictions (1 planning step) | VLN agent with compatibility model · R2R Val-Unseen VLN | SR: 35.7 -> 39.9 | Improved |
| replace blank-panorama look-ahead with Pathdreamer predictions (2 planning steps) | VLN agent with compatibility model · R2R Val-Unseen VLN | SR: 40.0 -> 46.5 | Improved |
| use ground-truth look-ahead observations instead of Pathdreamer (3 planning steps) | VLN agent with compatibility model · R2R Val-Unseen VLN | SR: 50.4 -> 59.3 | Improved |
| increase planning horizon from 1 to 3 steps with ground-truth observations | VLN agent · R2R Val-Unseen VLN | SR: 44.6 -> 59.3 | Improved |
| increase planning horizon from 1 to 3 steps with repeated panorama | VLN agent · R2R Val-Unseen VLN | SR: 35.7 -> 40.6 | Improved |
| add semantic and depth inputs to the Image Generator (ablation) | Image Generator · Val-Unseen RGB, 1-6 steps, 1 context | FID: 90.8 -> 39.9 | Improved |
| add RGB context and guidance image to the Image Generator (vs SPADE) (ablation) | Image Generator · Val-Unseen RGB, 1-6 steps, 1 context | FID: 50.3 -> 39.9 | Improved |
| add RGB context and guidance image to the Image Generator (vs SPADE) (ablation) | Image Generator · Val-Seen RGB, 1-6 steps, 1 context | FID: 24.9 -> 31.3 | Hurt |
| use ground-truth semantics instead of Structure Generator predictions | Image Generator · Val-Unseen RGB, 1-6 steps, 1 context | FID: 70.4 -> 39.9 | Improved |
| use the learned Structure Generator instead of nearest-neighbor hole filling | Structure Generator · Val-Unseen semantics, 1-6 steps, 1 context | mIoU: 30.6 -> 50.8 | Improved |
| use recurrent training instead of teacher forcing (ablation) | Structure Generator · Val-Seen semantics, 1-6 steps, 1 context | mIoU: 59.2 -> 65.9 | Improved |
Closest papers by meaning
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.90)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.89)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.88)
- CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs? (ICLR 2026 · similarity 0.88)
- Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation (NeurIPS 2025 · similarity 0.88)
- Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions (NeurIPS 2024 · similarity 0.88)
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.
