Hierarchical 3D Scene Graph Construction and Belief-based Planning for Semantic Navigation
For embodied agents performing semantic navigation in unseen environments, this work addresses the problem of inefficient exploration and myopic decision-making in long-distance tasks.
The paper proposes a zero-shot semantic navigation framework that builds an online Hierarchical 3D Scene Graph (HSG) and uses hierarchical belief-based planning to improve long-distance navigation, achieving 9.4% improvement in Success Rate and 5.0% in SPL over state-of-the-art methods.
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.