ArborSplat: Online Semantic Gaussian Splatting SLAM for Orchards

2026-09-22

AI Summary

ArborSplat通过结合LiDAR里程计和语义优化，解决果园机器人需要高精度保留细小但重要结构（如树干、果实）的地图问题。

Abstract

Orchard robots need maps that preserve small but semantically important structures such as trunks, trellises, and fruit. 3D Gaussian Splatting (3DGS) SLAM achieves high photometric fidelity. However, its optimization remains appearance-driven, and transferring image semantics to 3D points is unreliable for thin structures, whose pixels may receive depth from background surfaces. We present ArborSplat, an online semantic 3DGS SLAM system that tracks with LiDAR odometry and optimizes semantics directly on the Gaussian map, constrained by class-specific height bands above a ground plane fitted to each keyframe's stereo point cloud, and fuses multi-view evidence into a semantic point cloud online while rejecting labels inconsistent with the local ground surface or with monocular depth. Class-constrained refinement reserves Gaussian capacity for underrepresented structures and, under reduced budgets, increases training-view accuracy on tree classes. We evaluate the approach on apple and pear orchards during dormancy, flowering, and harvesting. On full routes, it keeps ATE below 0.5 m on all 12 traversals. On shared 301-frame segments, it exceeds SGS-SLAM and GS3LAM by 0.23 to 0.50 training-view and 0.15 to 0.36 held-out mIoU while running 1.7 to 7.5 times faster, whereas SemGauss-SLAM runs out of GPU memory on all six.

Problem

• Orchard Robots
• Semantic Mapping
• 3D Gaussian Splatting
• Thin Structures
• Appearance-Driven Optimization

Innovation

• Online Semantic 3DGS SLAM
• Lidar Odometry
• Class-specific Height Bands
• Semantic Point Cloud Fusion
• Ground Plane Constraint