Página principal

The Rosario Dataset

This web page presents an agricultural dataset collected on-board out weed removing robot. The dataset is composed by six different sequences in a soybean field and it contains stereo images, IMU measurements, wheel odometry and GPS-RTK (position ground-truth).

Animated samples.gif

If you use the Rosario Dataset in an academic work, please cite

Taihú Pire, Martín Mujica, Javier Civera and Ernesto Kofman. **The Rosario Dataset: Multisensor Data for Localization and Mapping in Agricultural Environments**. In: International Journal of Research Robotics, 2019. RosarioDataset2019.pdf

@article{pire2019rosario,\\ author = {Taih{\'u} Pire and Mart{\'i}n Mujica and Javier Civera and Ernesto Kofman},\\ title = {The Rosario dataset: Multisensor data for localization and mapping in agricultural environments},\\ journal = {The International Journal of Robotics Research},\\ volume = {38},\\ number = {6},\\ pages = {633-641},\\ year = {2019},\\ doi = {10.1177/0278364919841437}\\ }

Available Data

 * **Stereo images** (ZED Stereo Camera: colour images 672x376 @ 15 fps)
 * **MEMS IMU** (LSM6DS0 6-DoF Inertial Measurement Unit working at 140 Hz)
 * **Wheel Odometry** ( 3 x Hall effect sensors coupled to each rear wheel and 1 encoder attached to the robot direction)
 * **GPS-RTK system** (GPS-RTK modules working at 5 Hz)
 * **Calibration** (Intrinsic and extrinsic parameters)
 * **Positional Ground-Truth** (3D position Ground-truth computed from GPS-RTK)

---

Downloads

The dataset can be downloaded by torrent [coming soon] or by direct download using the provided links below. For direct download the aria2c command line from aria2c software is recommended:

aria2c -s 8 -x 8 <URL>

Sequence 01
Rosbag	sequence01.bag.00 sequence01.bag.01 sequence01.bag.02 sequence01.bag.03
Raw data	sequence01.tar.gz.00 sequence01.tar.gz.01 sequence01.tar.gz.02 sequence01.tar.gz.03
Calibration	calibration01.yaml
Ground-Truth	sequence01_gt.txt
MD5 checksum (Rosbag)	313c38109f9981b0c48e53e39be25b98
MD5 checksum (Raw Data)	667dbab7158540a403a0edc2c4aef5c3

Sequence 02
Rosbag	sequence02.bag.00 sequence02.bag.01
Raw data	sequence02.tar.gz.00 sequence02.tar.gz.01
Calibration	calibration02.yaml
Ground-Truth	sequence02_gt.txt
MD5 checksum (Rosbag)	753d9eb435a7fd6b8e40fad68672cac2
MD5 checksum (Raw Data)	c01d280723471530ebede1763b04c0ea

Sequence 03
Rosbag	sequence03.bag
Raw data	sequence03.tar.gz]
Calibration	calibration03.yaml
Ground-Truth	sequence03_gt.txt
MD5 checksum (Rosbag)	b5659a491932910617a96b88405074a3
MD5 checksum (Raw Data)	25c53f826cc1db165965db03daff53d4

Sequence 04
Rosbag	sequence04.bag
Raw data	sequence04.tar.gz
Calibration	calibration04.yaml
Ground-Truth	sequence04_gt.txt
MD5 checksum (Rosbag)	887ad3b3173356c03ab02ae9ad27cc8d
MD5 checksum (Raw Data)	e9a9d6fbcad3fe77785454058fe6bb65

Sequence 05
Rosbag	sequence05.bag.00 sequence05.bag.01
Raw data	sequence05.tar.gz.00 sequence05.tar.gz.01
Calibration	calibration05.yaml
Ground-Truth	sequence05_gt.txt
MD5 checksum (Rosbag)	a4e61b22c9ac0b818ceff9e23ea6d076
MD5 checksum (Raw Data)	df7c6201762916d56520c17299eb03c0

Sequence 06 ^ ^ Sequence 06 ^ ^ Rosbag | [[1]] [[2]] [[3]]| ^ Raw data | [[4]] [[5]] [[6]] [[7]] | ^ Calibration | [[8]] | ^ Ground-Truth | [[9]] | ^ MD5 checksum (Rosbag) | e149bd1bec465c446d1d1c050fc003b4 | ^ MD5 checksum (Raw Data) | 6c70ceacf717568947c92b592a037115 | Dataset join and decompress Some sequences were compressed and split in order to facilitate their download. To join the different parts the following command should be used: cat sequenceXX.bag.* > sequenceXX.bag rosbag decompress sequenceXX.bag cat sequenceXX.tar.gz.* > sequenceXX.tar.gz tar xvzf sequenceXX.tar.gz Note: ** To check if the data is not corrupted you can use the MD5 checksum numbers. Observe that provided checksum numbers for .bag files correspond to the compressed rosbags. Raw data format The raw data format is detailed in [[10]]. Dataset parsers A simple dataset parser is available here: [[11]]. To create a rosbag from the raw data use: python create_bagfile.py --images <sequence04/zed/> --imu <sequence04/imu.log> --gps <sequence04/gps.log> --calibration <calibration04.yaml> --odom <sequence04/odometry_raw.log> --out sequence4.bag Dataset samples.jpg?direct&600 Figure 1: Datasets samples. Trajectories.png?direct&600 Figure 2: GPS-RTK trajectory for each sequence. Platform and Sensors The weed robot was used for the dataset collection (see Figure 3). The weed removing robot was supported by the //Development of a weed remotion mobile robot// project at CIFASIS (CONICET-UNR). The sensors coordinate systems and the relations among them are depicted too. All the sensors are synchronised by software. Robot sensors coordinate systems.png?direct&400Robot TF coordinate systems.png?direct&450 Figure 3: Sensors coordinate systems. Ground-Truth and Evaluation We provide a 3D position ground-truth computed from the GPS-RTK system (no orientation is provided). The GPS-RTK system is composed by two [Reach] modules (one module is mounted on the rover and the other one mounted on the base station). We assessed the accuracy and performance of the GPS-RTK system in Fullpaper 3 articulocientifico jar 2017.pdf (spanish). As there is no magnetometer mounted on the robot, it is not possible to know precisely the robot orientation in GPS UTM coordinate frame. To mitigate this issue, we propose to use the [[12]] library for SLAM algorithms evaluation. In particular, the following command should be used to compute the Absolute Pose Error (APE): evo_ape tum sequenceXX_gt.txt slam_tum_XX.txt -p --verbose --align Changelog The dataset changes are depicted in [[13]]. License License.png?direct&100 All data in the Rosario Dataset is licensed under a [Commons 4.0 Attribution License (CC BY 4.0)] and the accompanying source code is licensed under a [License]. ~~QUICKSTATS:pages;;-1~~