Tree-SLAM: semantic object SLAM for efficient mapping of individual trees in orchards

TL;DR

Tree-SLAM is a semantic SLAM method that accurately maps individual orchard trees using RGB-D images, overcoming GPS unreliability and visual confusion, enabling precise orchard mapping for precision agriculture.

Contribution

We introduce Tree-SLAM, a novel semantic SLAM approach that detects, re-identifies, and maps individual orchard trees using a cascade-graph data association and factor graph framework.

Findings

Geo-localization error as low as 18 cm

Robust performance across different orchard datasets

Effective in scenarios with unreliable GPS signals

Abstract

Accurate mapping of individual trees is an important component for precision agriculture in orchards, as it allows autonomous robots to perform tasks like targeted operations or individual tree monitoring. However, creating these maps is challenging because GPS signals are often unreliable under dense tree canopies. Furthermore, standard Simultaneous Localization and Mapping (SLAM) approaches struggle in orchards because the repetitive appearance of trees can confuse the system, leading to mapping errors. To address this, we introduce Tree-SLAM, a semantic SLAM approach tailored for creating maps of individual trees in orchards. Utilizing RGB-D images, our method detects tree trunks with an instance segmentation model, estimates their location and re-identifies them using a cascade-graph-based data association algorithm. These re-identified trunks serve as landmarks in a factor graph framework that integrates noisy GPS signals, odometry, and trunk observations. The system produces maps of individual trees with a geo-localization error as low as 18 cm, which is less than 20\% of the planting distance. The proposed method was validated on diverse datasets from apple and pear orchards across different seasons, demonstrating high mapping accuracy and robustness in scenarios with unreliable GPS signals.