STAG: A Sparse Traversability-Aware Graph Representation from Grid-Based Costmaps for Robotic Navigation

Key points

• Autonomous rovers navigating large unstructured environments need efficient global planning that accounts for terrain traversability.1
• STAG combines a medial-axis topological backbone, representative nodes for homogeneous traversability regions, and transition nodes near strong traversability gradients.1
• We compare A on STAG and dense grids using synthetic cave maps, mine maps and the DARPA CERBERUS dataset.1
• STAG offers a compact representation for global planning, trading dense-grid traversability optimality for faster, less memory-intensive search.1

Sources (1)

• [1]STAG: A Sparse Traversability-Aware Graph Representation from Grid-Based Costmaps for Robotic Navigation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 01:33 PM

  We introduce STAG, a Sparse Traversability-Aware Graph that converts costmaps into compact graphs.

  Autonomous rovers navigating large unstructured environments need efficient global planning that accounts for terrain traversability.

Extractive summary: sentences quoted from the sources.