TEMPO-VINE: A Multi-Temporal Sensor Fusion Dataset for Localization and Mapping in Vineyards

TL;DR

TEMPO-VINE tackles the absence of realistic, long-term benchmarks for autonomous localization and mapping in agricultural settings, specifically vineyards. It introduces a multi-temporal, multi-modal dataset collected with heterogeneous LiDARs, RGB-D vision, AHRS, and RTK-GPS across trellis and pergola vineyard architectures, with ground-truth trajectories and ROS-compatible packaging. The paper provides extensive campaign data, a detailed data organization format, ground-truth generation, and baseline SLAM and place-recognition evaluations to establish a reproducible benchmark. By capturing seasonal growth, weather, and topology changes, TEMPO-VINE enables robust assessment of sensor fusion and perception algorithms for agricultural robotics and precision viticulture.

Abstract

In recent years, precision agriculture has been introducing groundbreaking innovations in the field, with a strong focus on automation. However, research studies in robotics and autonomous navigation often rely on controlled simulations or isolated field trials. The absence of a realistic common benchmark represents a significant limitation for the diffusion of robust autonomous systems under real complex agricultural conditions. Vineyards pose significant challenges due to their dynamic nature, and they are increasingly drawing attention from both academic and industrial stakeholders interested in automation. In this context, we introduce the TEMPO-VINE dataset, a large-scale multi-temporal dataset specifically designed for evaluating sensor fusion, simultaneous localization and mapping (SLAM), and place recognition techniques within operational vineyard environments. TEMPO-VINE is the first multi-modal public dataset that brings together data from heterogeneous LiDARs of different price levels, AHRS, RTK-GPS, and cameras in real trellis and pergola vineyards, with multiple rows exceeding 100 m in length. In this work, we address a critical gap in the landscape of agricultural datasets by providing researchers with a comprehensive data collection and ground truth trajectories in different seasons, vegetation growth stages, terrain and weather conditions. The sequence paths with multiple runs and revisits will foster the development of sensor fusion, localization, mapping and place recognition solutions for agricultural fields. The dataset, the processing tools and the benchmarking results will be available at the dedicated webpage upon acceptance.

Figures (7)

• Figure 1: Schematic of the sensors disposition on the rover used for the data collection activity in the vineyards.
• Figure 2: Samples of RGB-D images and LiDAR point cloud collected in the trellis and pergola vineyards in the same position over different seasons from winter to summer. Different vegetation growth stages represent a key dynamic environmental aspect for robotics navigation.
• Figure 3: Trajectories for the three runs conducted in the trellis vineyard and in the pergola vineyards, overlaid with the satellite image of the field.
• Figure 4: File structure of the TEMPO-VITE dataset: the folders are organized to easily select the vineyard field, the run and the campaign date. For each experiment a bag file with metadata containing all the complete sensor data stream is provided, together with the RGB camera video and the ground truth trajectory file.
• Figure 5: SLAM results and ground truth trajectories on trellis (top) and pergola (bottom) vineyards from campaign 02 (March) with two LiDARs and the RGB-D camera.