Beyond Visibility: Real-Time Surface Accessibility Fields from Sparse LiDAR
Beyond Visibility: Real-Time Surface Accessibility Fields from Sparse LiDAR
This research paper introduces the Accessibility Field, a method that labels surface points as physically accessible or inaccessible based on tool geometry and approach clearance, computed in real-time from streaming sparse LiDAR data. The system uses GPU-based evaluation against precomputed tool-geometry kernels and a scan-centric TSDF integration scheme, achieving an F1 score of 90.8% on synthetic primitives compared to 69.8% for a Hidden Point Removal baseline. It is tool-agnostic, requires no prior scene model, and runs on both workstation and Jetson Orin edge hardware.
The authors introduce a real-time accessibility field method using sparse LiDAR to distinguish between visible and physically accessible surfaces for robotic tools, achieving an F1 score of 90.8% on synthetic data while running on edge hardware.
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.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
el, and runs in real time on both workstation and Jetson Orin edge hardware. On synthetic primitives, our method achieves F1=90.8%, against 69.8% for a Hidden Point Removal baseline; ablations within our own pipeline give 81.5% replacing the TSDF query with a point-cloud collision check, and 33.9% replacing scan-centric integration with projective, nvblox-style integration. On a mature synthetic Pinus radiata model,
Open source S4
the method labels 56.8% of visible pine branch surfaces as physically inaccessible.
Open source S5
Beyond Visibility: Real-Time Surface Accessibility Fields from Sparse LiDAR
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org