Long-horizon navigation in unstructured environments demands terrain abstractions that scale to tens of km2 while preserving semantic and geometric structure, a combination existing methods fail to achieve. Grids scale poorly; quadtrees misalign with terrain boundaries; neither encodes landcover semantics essential for traversability-aware planning. This yields infeasible or unreliable paths for autonomous ground vehicles operating over 10+ km2 under real-time constraints. CLEAR (Connected Landcover Elevation Abstract Representation) couples boundary-aware spatial decomposition with recursive plane fitting to produce convex, semantically aligned regions encoded as a terrain-aware graph. Evaluated on maps spanning 9-100~km2 using a physics-based simulator, CLEAR achieves up to 10x faster planning than raw grids with only 6.7% cost overhead and delivers 6-9% shorter, more reliable paths than other abstraction baselines. These results highlight CLEAR's scalability and utility for long-range navigation in applications such as disaster response, defense, and planetary exploration.
@article{arxiv.2601.13361,
title = {CLEAR: A Semantic-Geometric Terrain Abstraction for Large-Scale Unstructured Environments},
author = {Pranay Meshram and Charuvahan Adhivarahan and Ehsan Tarkesh Esfahani and Souma Chowdhury and Chen Wang and Karthik Dantu},
journal= {arXiv preprint arXiv:2601.13361},
year = {2026}
}