AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

LOG-Nav: Efficient Layout-Aware Object-Goal Navigation with Hierarchical Planning

Jiawei Hou, Yuting Xiao, Xiangyang Xue, Taiping Zeng

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
add local imperative planning to the global waypoint plan (ablation)LOG-Nav · Real-world, 3 obstaclesSR (10 trials): 1/10 -> 6/10Improved
add local imperative planning to the global waypoint plan (ablation)LOG-Nav · Real-world, 2 obstaclesSR (10 trials): 3/10 -> 8/10Improved
add local imperative planning to the global waypoint plan (ablation)LOG-Nav · Real-world, 1 obstacleSR (10 trials): 7/10 -> 10/10Improved
add local imperative planning to the global waypoint plan (ablation)LOG-Nav · Real-world, 3 obstaclestime cost (s): 134 -> 116Improved
add local imperative planning to the global waypoint plan (ablation)LOG-Nav · Real-world, 0 obstaclestime cost (s): 102 -> 96Improved
add global topological planning on top of local planning only (ablation)LOG-Nav · MP3D (SR vs target distance)SRImproved
increase number of repeated runs in same workspace (amortize mapping)LOG-Nav · MP3D repeated runsSPL: 0.083 -> 0.656Improved
LOG-Nav explore-then-plan vs ESC in a single runLOG-Nav · MP3D repeated runs (1-time run)SPL: 0.249 -> 0.083Hurt
use image goal instead of text goal for chair targetLOG-Nav · Real-world chairSR (10 trials): 10/10 -> 7/10Hurt
use image goal instead of text goal for sofa targetLOG-Nav · Real-world sofaSR (10 trials): 6/10 -> 3/10Hurt
use instance navigation text-goal vs object navigationLOG-Nav · MP3DSR: 0.856 -> 0.786Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy