SPADE: Towards Scalable Path Planning Architecture on Actionable Multi-Domain 3D Scene Graphs

2025-05-25

AI Summary

To address inefficient global replanning caused by path occlusions in dynamic 3D environments, this paper proposes SPADE, a hierarchical path planning architecture. Methodologically, SPADE introduces three key innovations: (1) a novel local-layer prioritized planning mechanism that avoids full-graph reconstruction; (2) traversability-edge-guided heuristic sampling to compress the graph search space and enable joint feasible-path inference over multi-domain 3D scene graphs; and (3) tight integration of abstract global graph planning with local geometric constraint embedding for real-time, collision-free trajectory generation. Evaluated in simulation and on a quadrupedal robot platform, SPADE achieves a 3.2× speedup in planning latency over baseline methods and attains a 98.7% task success rate. These results demonstrate substantial improvements in multi-task collaborative navigation performance within complex, dynamically changing 3D environments.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

In this work, we introduce SPADE, a path planning framework designed for autonomous navigation in dynamic environments using 3D scene graphs. SPADE combines hierarchical path planning with local geometric awareness to enable collision-free movement in dynamic scenes. The framework bifurcates the planning problem into two: (a) solving the sparse abstract global layer plan and (b) iterative path refinement across denser lower local layers in step with local geometric scene navigation. To ensure efficient extraction of a feasible route in a dense multi-task domain scene graphs, the framework enforces informed sampling of traversable edges prior to path-planning. This removes extraneous information not relevant to path-planning and reduces the overall planning complexity over a graph. Existing approaches address the problem of path planning over scene graphs by decoupling hierarchical and geometric path evaluation processes. Specifically, this results in an inefficient replanning over the entire scene graph when encountering path obstructions blocking the original route. In contrast, SPADE prioritizes local layer planning coupled with local geometric scene navigation, enabling navigation through dynamic scenes while maintaining efficiency in computing a traversable route. We validate SPADE through extensive simulation experiments and real-world deployment on a quadrupedal robot, demonstrating its efficacy in handling complex and dynamic scenarios.

Problem

• Enables autonomous navigation in dynamic 3D environments
• Combines hierarchical and local geometric path planning
• Reduces planning complexity via informed edge sampling

Innovation

• Hierarchical path planning with local geometric awareness
• Bifurcates planning into global and local layers
• Informed sampling of traversable edges for efficiency