Lightweight Path-Aware Frontier Re-ranking for LiDAR-Based UAV Exploration
Lightweight Path-Aware Frontier Re-ranking for LiDAR-Based UAV Exploration
This research paper introduces a lightweight path-aware frontier re-ranking method designed to improve the efficiency of autonomous 3D exploration using LiDAR-based unmanned aerial vehicles (UAVs). The proposed approach addresses limitations in conventional Euclidean-distance-based frontier selection by incorporating feasible path cost estimates through time-bounded RRT* planning. By retaining a small set of promising candidates and reusing generated paths for navigation, the method reduces redundant global planning. Experimental results across three warehouse-like environments show that the technique consistently produces shorter exploration trajectories, achieving up to 14.1% reduction in traveled distance and up to 9.5% reduction in exploration time in two environments, while maintaining map detail comparable to conventional OctoMap-based baselines.
The study demonstrates a lightweight path-aware re-ranking method for LiDAR-based UAV exploration that reduces traveled distance by up to 14.1% and exploration time by up to 9.5% in simulated warehouse-like environments while maintaining map detail comparable to OctoMap baselines.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S2
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2611.09561v1 Announce Type: new Abstract: Autonomous 3D exploration with UAVs requires efficient target selection under limited flight time and onboard computation. In conventional Euclidean-distance-based frontier pipelines, geometric distance may poorly represent the actual collision-free travel cost in cluttered environments, leading to inefficient frontier choices. This paper presents a lightweight path-awa
Open source S2
like environments show that the proposed method consistently produces shorter exploration trajectories than conventional frontier baselines, with traveled-distance reductions of up to 14.1%, while reducing exploration time by up to 9.5% in two environments and remaining competitive in the third. The method maintains map detail comparable to the conventional OctoMap-based baseline, demonstrating an effective trade-off
Open source S4
Lightweight Path-Aware Frontier Re-ranking for LiDAR-Based UAV Exploration
Open source S1
re frontier re-ranking method for LiDAR-based UAV exploration. The method first retains a small top-N set of promising frontier candidates using a lightweight utility function and then applies time-bounded RRT* planning to estimate their feasible path costs for re-ranking. The path generated for the selected frontier is further reused for navigation to reduce redundant global planning. Experiments in three warehouse-
Open source S3
Source：arXiv Robotics — research abstracts · arxiv.org