RoboCup Data Sets
RoboCup community produced a significant effort to build data sets that are useful for many robotics applications. This page provides an overview of the data sets developed by RoboCup teams in different leagues. The list is in reverse order, i.e., the newest dataset is listed first. We also provide additional links and tools to create data sets.
To add your paper and your dataset to this page, please send an e-mail to info@robocup.org
To add your paper and your dataset to this page, please send an e-mail to info@robocup.org
2022:
Pre 2019 data sets:
- Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL. Roberto Fernandes, Walber M. Rodrigues and Edna Barros
https://github.com/bebetocf/ssl-dataset - Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation. Haresh Karnan, Anirudh Nair, Xuesu Xiao, Garrett Warnell, Soeren Pirk, Alexander Toshev, Justin Hart, Joydeep Biswas and Peter Stone
https://arxiv.org/abs/2203.15041
- Learning from the Crowd: Improving the Decision Making Process in Robot Soccer using the Audience Noise. Emanuele Antonioni, Vincenzo Suriani, Filippo Solimando, Domenico Bloisi and Daniele Nardi.
https://sites.google.com/unibas.it/crowdsounddataset - TORSO-21 Dataset: Typical Objects in RoboCup Soccer 2021. Marc Bestmann, Timon Engelke, Niklas Fiedler, Jasper Güldenstein, Jan Gutsche, Jonas Hagge and Florian Vahl, 2021.
https://github.com/bit-bots/TORSO_21_dataset - Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL. Roberto Fernandes, Walber M. Rodrigues and Edna Barros, 2021. Small size league, 931 images + labels for robots, ball, goals.
https://github.com/bebetocf/ssl-dataset - Soccer Field Boundary Detection Using Convolutional Neural Networks. Arne Hasselbring and Andreas Baude, 2021.
https://github.com/bhuman/DeepFieldBoundary - Real-time Pose Estimation for Multi-Humanoid Robots. Arash Amini, Hafez Farazi, and Sven Behnke, 2021
https://github.com/AIS-Bonn/HumanoidRobotPoseEstimation - Faster YOLO-LITE: Faster Object Detection on Robot and Edge Devices. ZhengBai Yao, Will Douglas, Simon O'Keeffe, and Rudi Villing.
https://roboeireann.maynoothuniversity.ie/research/SPLObjDetectDatasetV2.zip
- Neural Semantic Parsing with Anonymization for Command Understanding in General-Purpose Service Robots. Nick Walker, Yu-Tang Peng, Maya Cakmak, 2019. RoboCup@Home General Purpose Service Robot task.
https://zenodo.org/record/3244800#.YNcp5RNKh6E - Tell Your Robot What To Do: Evaluation of Natural Language Models for Robot Command Processing. Erick Romero Kramer, Argentina Ortega Sainz, Alex Mitrevski, and Paul G. Plöger, 2019. RoboCup@Home General Purpose Service Robot task.
https://github.com/ErickKramer/NLU_Benchmarking - ObjectDetection@Work. Benjamin Schnieders, Shan Luo, Gregory Palmer, Karl Tuyls, (2019?).
http://wordpress.csc.liv.ac.uk/smartlab/objectdetectionwork/ - RoboCup@Home-OBJECTS benchmark. Nizar Massouh, Lorenzo Brigato, Luca Iocchi, 2019. Annotated images.
https://sites.google.com/diag.uniroma1.it/robocupathome-objects - JET-Net: Real-Time Object Detection for Mobile Robots. Bernd Poppinga and Tim Laue, 2019. Object detection RoboCup SPL with 27.000 images from ImageTagger and 28.000 images generated in simulation.
https://sibylle.informatik.uni-bremen.de/public/JET-Net/ - RoboCup SPL Instance Segmentation Dataset. Piet Broemmel et al, 2019. Segmented images from the NaoDevils Team.
https://www.kaggle.com/pietbroemmel/naodevils-segmentation-upper-camera
- B-Human 2019 — complex team play under natural lighting conditions. Thomas Röfer, Tim Laue, Gerrit Felsch, Arne Hasselbring, Tim Haß, Jan Oppermann, Philip Reichenberg, and Nicole Schrader. Dataset (ball detection)
https://sibylle.informatik.uni-bremen.de/public/datasets/b-alls-2019/
Nao lower camera ball detection dataset that was auto-labelled available at
https://sibylle.informatik.uni-bremen.de/public/datasets/balldetector_lc/ - Soccer Field Boundary Detection Using Convolutional Neural Networks. Arne Hasselbring, Andreas Baude
Dataset
https://sibylle.informatik.uni-bremen.de/public/datasets/fieldboundary/ - Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation. Jan Blumenkamp, Andreas Baude, Tim Laue
https://sibylle.informatik.uni-bremen.de/public/datasets/semantic_segmentation/ - Whistle detection dataset available
https://sibylle.informatik.uni-bremen.de/public/datasets/whistle-2017/ - JET-Net: Real-time object detection for mobile robots. Bernd Poppinga and Tim Laue.
https://sibylle.informatik.uni-bremen.de/public/JET-Net/ - Ball detection dataset available at https://www.kaggle.com/berlinunitednaoth/tk3balldetectionrobocup2019sydney
- Toward Data Driven Development in RoboCup. Heinrich Mellmann, Benjamin Schlotter, and Philipp Strobel.
https://www2.informatik.hu-berlin.de/~naoth/videolabeling/ - Enhancing simulation images with gans. Hidde Lekanne gezegd Deprez.
https://staff.fnwi.uva.nl/a.visser/education/bachelorAI/thesis_hidde_lekanne_deprez.pdf - ROBO: robust, fully neural object detection for robot soccer. Marton Szemenyei and Vladimir Estivill-Castro.
https://github.com/szemenyeim/ROBO - Robot and ball detection.
https://imagetagger.bit-bots.de/users/team/28/ - Robot soccer semantic segmentation dataset.
https://www.kaggle.com/pietbroemmel/naodevils-segmentation-upper-camera
Pre 2019 data sets:
- RoboCup@Home Spoken Corpus: Using Robotic Competitions for Gathering Datasets. Emanuele Bastianelli, Luca Iocchi, Daniele Nardi, Giuseppe Castellucci, Danilo Croce, Roberto Basil, 2014.
https://github.com/crux82/huric - Robot-centric Activity Recognition 'in the Wild'.Ilaria Gori, Jivko Sinapov, Priyanka Khante, Peter Stone, and J.K. Aggarwal.
https://www.cs.utexas.edu/~pstone/Papers/bib2html/b2hd-ICSR2015-gori.html - SPQR Team NAO image dataset. Dario Albani, Ali Youssef, Vincenzo Suriani, Daniele Nardi, and Domenico D. Bloisi, 2016. Raw + annotated images.
http://www.diag.uniroma1.it//~labrococo/?q=node/459 - Robot@Home, a robotic dataset for semantic mapping of home environments. J.R. Ruiz-Sarmiento, C. Galindo, J. Gonzalez-Jimenez, 2017; SLAM; 87,000+ observations by mobile robot, four RGB-D cameras and 2D laser scanner data.
http://mapir.isa.uma.es/mapirwebsite/index.php/mapir-downloads/203-robot-at-home-dataset - RoboCupSimData: A RoboCup soccer research dataset. Olivia Michael, Oliver Obst, Falk Schmidsberger, Frieder Stolzenburg, 2017. RoboCup Soccer 2D Simulation League, perception and ground truth of 1125 simulated matches from 10 teams.
https://arxiv.org/abs/1711.01703, http://oliver.obst.eu/data/RoboCupSimData/overview.html - RoboCup Rescue Victim Dataset. Peter Lorenz, Gerald Steinbauer, 2018. Annotated images from RoboCup rescue.
https://osf.io/dwsnm/ - Hamburg Bit-Bots Ball Dataset. Niklas Fiedler, 2018. Midsize league, 25K images, ball localization
https://robocup.informatik.uni-hamburg.de/en/documents/bit-bots-ball-dataset-2018/ - Machine Learning for Realistic Ball Detection in RoboCup SPL. Domenico Bloisi, Francesco Del Duchetto, Tiziano Manoni, Vincenzo Suriani. Dataset (Realistic Ball)
http://www.diag.uniroma1.it//~labrococo/?q=node/459 - A benchmark data set and evaluation of deep learning architectures for ball detection in the RoboCup SPL. 2017.
http://www.roboeireann.ie/research/SampleDataset.zip - A Deep Learning Approach for Object Recognition with NAO Soccer Robots. Dario Albani, Ali Youssef, Vincenzo Suriani, Daniele Nardi, and Domenico Daniele Bloisi. 2017.
Dataset available at http://www.diag.uniroma1.it//~labrococo/?q=node/459 - On field gesture-based robot-to-robot communication with nao soccer players. Di Giambattista Valerio, Mulham Fawakherji, Vincenzo Suriani, Domenico D. Bloisi, and Daniele Nardi. 2019:
Dataset (non-verbal)
http://www.dis.uniroma1.it/~labrococo/?q=node/459
- RoboCup@home 20XX (competition environment data)
https://github.com/RoboCupAtHome/ - Imagetagger: An open source online platform for collaborative image labeling. Fiedler, Niklas, Marc Bestmann, and Norman Hendrich. 2018
https://github.com/bit-bots/imagetagger
- Tools for Data Driven Research and Development in RoboCup. Heinrich Mellmann, Benjamin Schlotter, and Philipp Strobel
https://berlin-united.org/project-tools.html
- Generating a dataset for learning setplays from demonstration. Marco A. C. Simões, Jadson Nobre, Gabriel Sousa, Caroline Souza, Robson M. Silva, Jorge Campos, Josemar R. Souza & Tatiane Nogueira, 2021
https://doi.org/10.1007/s42452-021-04571-y - Chen, D. L. and Mooney, R. J. (2008). Learning to sportscast: a test of grounded language acquisition. In Proceedings of the 25th international conference on Machine learning, pages 128–135. ACM