Saved in:
Bibliographic Details
Main Authors: Du, Yifan, Zhang, Chengwei, Liao, Siyu, Wang, Zhongfeng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17302
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916020496629760
author Du, Yifan
Zhang, Chengwei
Liao, Siyu
Wang, Zhongfeng
author_facet Du, Yifan
Zhang, Chengwei
Liao, Siyu
Wang, Zhongfeng
contents Ground robot navigation in complex 3D environments is often hindered by geometric ambiguity, where non-traversable structures such as furniture share local geometric properties with navigable ground. Furthermore, the computational cost of searching massive voxel spaces remains a significant challenge. To address these issues, we present a surface extraction framework that constructs a reduced state space of physically reachable standing positions by enforcing ground support, overhead clearance, and seed-based connectivity constraints. Evaluation across five Matterport3D indoor scenes and three PCT benchmark scenes demonstrates over 80\% state space reduction and sub-millisecond A* search on the Matterport3D scenes, with 100\% planning success across all 300 tested queries.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17302
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments
Du, Yifan
Zhang, Chengwei
Liao, Siyu
Wang, Zhongfeng
Robotics
Ground robot navigation in complex 3D environments is often hindered by geometric ambiguity, where non-traversable structures such as furniture share local geometric properties with navigable ground. Furthermore, the computational cost of searching massive voxel spaces remains a significant challenge. To address these issues, we present a surface extraction framework that constructs a reduced state space of physically reachable standing positions by enforcing ground support, overhead clearance, and seed-based connectivity constraints. Evaluation across five Matterport3D indoor scenes and three PCT benchmark scenes demonstrates over 80\% state space reduction and sub-millisecond A* search on the Matterport3D scenes, with 100\% planning success across all 300 tested queries.
title Beyond Geometry: Efficient Topologically-Grounded Navigation in Complex 3D Environments
topic Robotics
url https://arxiv.org/abs/2605.17302