New Agricultural multi-month dataset with overlapping paths for mapping and localisation algorithms for autonomous robots

In March 2022, we started conduct the long-term data acquisition campaign at Ktima Gerovassiliou vineyard. This vineyard extends for more than 100ha located in the outskirts of Epanomi, Greece.

3D LiDAR scan example

Agricultural environments present seasonal changes, repetitive strucures, uneven terrain and different weather conditions, which make achieving long-term autonomy for robots a challenging problem.

Motivated by these challenging conditions and the lack of agricultural dataset in the literature, we present the BLT dataset. Its primary objective is to push developments and evaluations of different mapping and localisation algorithms for long-term autonomous robots operating in agricultural fields. However, we believe that thanks to its temporal aspect, the dataset can also be used for phenotyping and crop mapping tasks.

SAGA Torvald Robot used in the dataset collection

The dataset covers 10 sessions of recording between March and September 2022, comprising ROS bags of RTK-GPS precise location, image streams from front and side RGBD cameras, IMU data, as well as 16-beam 360 degrees LiDAR scans. Read more at