Low Cost, High Efficiency: LiDAR Place Recognition in Vineyards with Matryoshka Representation Learning

TL;DR

This paper introduces MinkUNeXt-VINE, a lightweight deep-learning method for vineyard place recognition using low-cost LiDAR, achieving high efficiency and robustness in real-time agricultural robot localization.

Contribution

The paper presents a novel Matryoshka Representation Learning approach that outperforms existing methods in vineyard place recognition with low-cost LiDAR inputs.

Findings

Outperforms state-of-the-art methods in vineyard environments

Demonstrates robustness with low-resolution and low-cost LiDAR data

Provides comprehensive ablation studies and long-term dataset evaluations

Abstract

Localization in agricultural environments is challenging due to their unstructured nature and lack of distinctive landmarks. Although agricultural settings have been studied in the context of object classification and segmentation, the place recognition task for mobile robots is not trivial in the current state of the art. In this study, we propose MinkUNeXt-VINE, a lightweight, deep-learning-based method that surpasses state-of-the-art methods in vineyard environments thanks to its pre-processing and Matryoshka Representation Learning multi-loss approach. Our method prioritizes enhanced performance with low-cost, sparse LiDAR inputs and lower-dimensionality outputs to ensure high efficiency in real-time scenarios. Additionally, we present a comprehensive ablation study of the results on various evaluation cases and two extensive long-term vineyard datasets employing different LiDAR sensors. The results demonstrate the efficiency of the trade-off output produced by this approach, as well as its robust performance on low-cost and low-resolution input data. The code is publicly available for reproduction.