S-Path uses the metric-semantic structure of indoor 3D scene graphs for two-stage planning with parallel subproblem decomposition and heuristic reuse on replanning, reporting 6x average planning time reduction versus classical sampling-based methods.
Hierarchical representations and explicit memory: Learning effective navigation policies on 3d scene graphs using graph neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Situationally-aware Path Planning Exploiting 3D Scene Graphs
S-Path uses the metric-semantic structure of indoor 3D scene graphs for two-stage planning with parallel subproblem decomposition and heuristic reuse on replanning, reporting 6x average planning time reduction versus classical sampling-based methods.