MAgro dataset: A dataset for simultaneous localization and mapping in agricultural environments

Abstract

The agricultural industry is being transformed, thanks to recent innovations in computer vision and deep learning. However, the lack of specific datasets collected in natural agricultural environments is, arguably, the main bottleneck for novel discoveries and benchmarking. The present work provides a novel dataset, Magro, and a framework to expand data collection. We present the first version of the Magro Dataset V1.0, consisting of nine ROS bags (and the corresponding raw data) containing data collected in apple and pear crops. Data were gathered, repeating a fixed trajectory on different days under different illumination and weather conditions. To support the evaluation of loop closure algorithms, the trajectories are designed to have loop closures, revisiting some places from different viewpoints. We use a Clearpath’s Jackal robot equipped with stereo cameras pointing to the front and left side, a 3D LIDAR, three inertial measurement units (IMU), and wheel encoders. Additionally, we provide calibrated RTK GPS data that can be used as ground truth. Our dataset is openly available, and it will be updated to have more data and variability. Finally, we tested two existing state-of-the-art algorithms for vision and point cloud-based localization and mapping on our novel dataset to validate the dataset’s usability.

Multimodal Mobile Robotic Dataset for a Typical Mediterranean Greenhouse: The GREENBOT Dataset

“…These works focused on weed detection and mapping of different types of crops with an IMU, GPS, and LiDAR. Finally, in [ 10 ], Marzoa et al presented a dataset using a robot with autonomous navigation, displaying images with RGB-D cameras and 3D LiDAR on a row of apple trees, closing the control loop through a SLAM algorithm.…”

“…Large, open datasets are crucial for developing data-driven techniques and benchmarks in a new era of deep learning-based algorithms. In the literature, there are abundant datasets for urban environments (e.g., [ 6 , 7 ]), and to the authors’ knowledge, the most extensive datasets currently available for agricultural environments are the Rosario dataset [ 8 ], the Sugar Beets dataset [ 9 ], and the MAGRO dataset [ 10 ] for an apple orchard field. However, these datasets are focused on open-field agricultural environments where, on the one hand, localization and orientation may be less complex and, on the other hand, the permissible error is more significant than in closed environments, such as greenhouses, in particular, Mediterranean greenhouses.…”

Contrastive 3D Shape Completion and Reconstruction for Agricultural Robots Using RGB-D Frames

“…Recently, a few datasets have been released for mapping applications in agricultural environments. The MAgro dataset [23] consists of robotic sensor data, such as 3D LiDAR, date from an inertial measurement unit, and wheel encoders, gathered in apple and pear orchards with calibrated RTK GPS to evaluate localization methods. The Bacchus dataset [26] captures the whole canopy growth of a vineyard tailored for mapping and localization algorithms for longterm autonomous robotic operation.…”