Terra: Hierarchical Terrain-Aware 3D Scene Graph for Task-Agnostic Outdoor Mapping

Abstract

Outdoor intelligent autonomous robotic operation relies on a sufficiently expressive map of the environment. Classical geometric mapping methods retain essential structural environment information, but lack a semantic understanding and organization to allow high-level robotic reasoning. 3D scene graphs (3DSGs) address this limitation by integrating geometric, topological, and semantic relationships into a multi-level graph-based map. Outdoor autonomous operations commonly rely on terrain information either due to task-dependence or the traversability of the robotic platform. We propose a novel approach that combines indoor 3DSG techniques with standard outdoor geometric mapping and terrain-aware reasoning, producing terrain-aware place nodes and hierarchically organized regions for outdoor environments. Our method generates a task-agnostic metric-semantic sparse map and constructs a 3DSG from this map for downstream planning tasks, all while remaining lightweight for autonomous robotic operation. Our thorough evaluation demonstrates our 3DSG method performs on par with state-of-the-art camera-based 3DSG methods in object retrieval and surpasses them in region classification while remaining memory efficient. We demonstrate its effectiveness in diverse robotic tasks of object retrieval and region monitoring in both simulation and real-world environments.

Figures (8)

• Figure 3: Visual breakdown of our proposed three-phase Terra 3DSG approach built on our large south campus dataset.
• Figure B1: Overview of the three phases that make up our Terra method.
• Figure C1: Visual comparison of region clustering techniques on campus dataset: (a) agglomerative and (b) spectral.
• Figure D1: Birds-eye-view of the simulated HoloOcean environment and the three different trajectories taken to collect the three simulation datasets.
• Figure D2: Memory usage of three methods across simulated experiments. N/A indicates failure due to RAM or clustering failures. Terra 3DSG remains more memory-efficient than all Clio variants, even on the largest dataset.