CTSG: Integrating Context and Way Topology Into Scene Graph for Zero-shot Navigation

Abstract

A robust environment representation is critical for enabling robot systems to accomplish embodied navigation tasks. While offering efficient and sparse representations of environments compared to dense semantic maps, traditional 3D Scene Graphs often rely on multi-level semantic hierarchies that risk semantic discrepancies between high-level nodes and objects. Furthermore, separating semantic context from way topological relationships creates a disconnect between scene interpretation and actionable navigation strategies. To address these challenges, we propose CTSG, a hierarchical 3D scene graph mapping framework for zero-shot object navigation that supports both visual and textual queries. CTSG features a dual-layer structure: an object layer and a novel conway layer (contextual information + way topology). The conway layer integrates topological waypoints with rich multi-modal context, enhancing the continuity of environmental semantics. By aligning observations with navigation-centric perspectives, CTSG bridges the gap between scene understanding and task execution. We validate our method through simulation and real-world experiments across diverse environments, demonstrating robust performance in both visual target and language-guided navigation scenarios.