Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation

About

Semantic navigation is a fundamental task for embodied agents operating in unseen environments, requiring both semantic understanding and long-term decision-making. Recent foundation models have empowered agents with rich semantic priors for this task. However, without structured global representations, decision-making often falls back on local observations and greedy strategies, resulting in inefficient exploration and myopic behaviors, especially in long-distance navigation. To address these challenges, we propose a zero-shot semantic navigation framework. Our method incrementally maintains an online Hierarchical 3D Scene Graph (HSG) to form a multi-granular semantic topology over objects, zones, and regions, serving as a compact state abstraction for global planning. Building on this memory, we introduce a hierarchical belief-based planning framework that fuses semantic priors with exploration evidence on the HSG, and performs finite-horizon rollouts on an HSG-based simulator to explicitly estimate the long-term expected returns of candidate macro-actions. This enables globally consistent decisions and reduces redundant backtracking. Extensive experiments in high-fidelity simulation environments across multiple tasks and datasets demonstrate that our method outperforms existing state-of-the-art methods, particularly in long-distance scenarios, where our approach improves SR and SPL by an average of 9.4\% and 5.0\%, respectively.

Bing Wu, Zuyao Chen, Changwen Chen• 2026

Related benchmarks

TaskDatasetResultRank
Object Goal NavigationMP3D
SR45.9
172
Object NavigationHM3D v1
SR61.6
49
Object NavigationHM3D v2
Success Rate (SR)80.1
30
Embodied NavigationHSSD
Success Rate69.9
15
Instance NavigationInstanceNav
SR38.1
9
Showing 5 of 5 rows

Other info

Follow for update