SPL teams have released a number of datasets suitable for machine learning. Most of these datasets are oriented towards vision tasks (classification, object detection, semantic segmentation, and pose detection) but sound recognition is also present. In the problem domain of robot soccer vision there are relatively few object classes to be handled but there are significant challenges related to the movement of the camera platform and motion blur, changes in scene illumination, and issues related to camera image quality (e.g. noise, limited dynamic range, color shifts). A significant aspect of the challenge is that computer vision solutions must run in real-time on an embedded platform (E.g. an Intel Atom E3485 for the Nao V6).
Outside of RoboCup, these datasets may prove useful to developers of embedded or edge device machine learning-based solutions.
2024
- Neural Network and Prior Knowledge Ensemble for Whistle Recognition and Direction and Distance Estimation of Whistle Events on a NAO Robot. Robocup 2024 symposium. Dataset available at: https://tu-dortmund.sciebo.de/s/hDiglhXxhO0JCB6
Dataset for Whistle Localisation available at: https://tu-dortmund.sciebo.de/s/XXrULjGMD53JdqG
Use together with this labelling tool available at: https://github.com/NaoDevils/AudioProcessing
2023
- Structural Pruning for Real-Time Multi-Object Detection on NAO Robots. RoboCup 2023 symposium. Dataset available at: https://drive.google.com/drive/folders/1WeY1_Ql4ZJsH01DIFtnlDYj5c_jsGL59
- Neural Network-based Joint Angle Prediction for the NAO Robot. RoboCup 2023 symposium. Dataset available at: https://b-human.informatik.uni-bremen.de/public/datasets/joint_angles/
2022
- Dataset of annotated side-view images from RoboCup 2019 games. Dataset available at https://github.com/RoboCup-SPL/Datasets/tree/master/RoboCup 2022/Open Research Challenge – Video analysis & statistics
2021
- Arne Hasselbring, Andreas Baude. Soccer Field Boundary Detection Using Convolutional Neural Networks. RoboCup 2021 symposium (2022). Dataset available at https://b-human.informatik.uni-bremen.de/public/datasets/fieldboundary/
- Jan Blumenkamp, Andreas Baude, Tim Laue. Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation. RoboCup 2021 symposium (2022). Dataset available at https://b-human.informatik.uni-bremen.de/public/datasets/semantic_segmentation/
- Emanuele Antonioni, Vincenzo Suriani, Filippo Solimando, Domenico Daniele Bloisi and Daniele Nardi. Learning from the Crowd: Improving the Decision Making Process in Robot Soccer using the Audience Noise. RoboCup 2021 symposium (2022). Dataset available at https://sites.google.com/unibas.it/crowdsounddataset
- ZhengBai Yao, Will Douglas, Simon O’Keeffe, and Rudi Villing. Faster YOLO-LITE: Faster Object Detection on Robot and Edge Devices. RoboCup 2021 symposium (2022). Dataset (object detection) available at https://roboeireann.maynoothuniversity.ie/research/SPLObjDetectDatasetV2.zip
2020
- Hidde Lekanne gezegd Deprez. Enhancing simulation images with gans. Bachelor thesis, Universiteit van Amsterdam, 2020. [ https://staff.fnwi.uva.nl/a.visser/education/bachelorAI/thesis_hidde_lekanne_deprez.pdf ] Dataset available at https://uvaauas.figshare.com/articles/figure/The_Dutch_Nao_Team_synthetic_dataset/12570902
- Robot soccer semantic segmentation dataset available at https://www.kaggle.com/pietbroemmel/naodevils-segmentation-upper-camera
2019
- Bernd Poppinga and Tim Laue. JET-Net: Real-time object detection for mobile robots. In Stephan Chalup, Tim Niemueller, Jackrit Suthakorn, and Mary-Anne Williams, editors, RoboCup 2019: Robot World Cup XXIII, volume 11531 of Lecture Notes in Artificial Intelligence, pages 227–240. Springer, 2019. Dataset available at https://b-human.informatik.uni-bremen.de/public/JET-Net/
- Heinrich Mellmann, Benjamin Schlotter, and Philipp Strobel. Toward Data Driven Development in RoboCup. In RoboCup 2019: Robot Soccer World Cup XXIII, 2019. Lecture Notes in Computer Science, vol 11531. Springer, Cham. Dataset (annotated robot logs) available at https://www2.informatik.hu-berlin.de/~naoth/videolabeling/
- Di Giambattista Valerio, Mulham Fawakherji, Vincenzo Suriani, Domenico D. Bloisi, and Daniele Nardi. On field gesture-based robot-to-robot communication with nao soccer players. In RoboCup 2019: Robot World Cup XXIII, Springer International Publishing, pp. 367-375, 2019. Dataset (non-verbal) available at http://www.dis.uniroma1.it/~labrococo/?q=node/459
- Marton Szemenyei and Vladimir Estivill-Castro. ROBO: robust, fully neural object detection for robot soccer. In Stephan K. Chalup, Tim Niemüller, Jackrit Suthakorn, and Mary-Anne Williams, editors, RoboCup 2019: Robot World Cup XXIII [Sydney, NSW, Australia, July 8, 2019], volume 11531 of Lecture Notes in Computer Science, pages 309–322. Springer, 2019. [ DOI | https://doi.org/10.1007/978-3-030-35699-6\_24 ]. Dataset available at https://github.com/szemenyeim/ROBO
- Ball detection dataset available at https://www.kaggle.com/berlinunitednaoth/tk3balldetectionrobocup2019sydney
- Nao lower camera ball detection dataset that was auto-labeled available at https://b-human.informatik.uni-bremen.de/public/datasets/balldetector_lc/
2018
- Robot and ball detection dataset available at https://imagetagger.bit-bots.de/users/team/28/
2017
- Simon O’Keeffe and Rudi Villing. A benchmark data set and evaluation of deep learning architectures for ball detection in the robocup spl. In RoboCup 2017: Robot World Cup XXI, Lecture Notes in Artificial Intelligence. 2017.
Dataset available at http://www.roboeireann.ie/research/SampleDataset.zip - Domenico Bloisi, Francesco Del Duchetto, Tiziano Manoni, Vincenzo Suriani. Machine Learning for Realistic Ball Detection in RoboCup SPL. [ arXiv 2017 | https://arxiv.org/abs/1707.03628v1 ]
Dataset (Realistic Ball) available at http://www.diag.uniroma1.it//~labrococo/?q=node/459 - Dario Albani, Ali Youssef, Vincenzo Suriani, Daniele Nardi, and Domenico Daniele Bloisi. A Deep Learning Approach for Object Recognition with NAO Soccer Robots, pages 392–403. Springer International Publishing, 2017. [ http://www.dis.uniroma1.it/~bloisi/papers/bloisi-robocup2016-draft.pdf ]
Dataset available at http://www.diag.uniroma1.it//~labrococo/?q=node/459 - Whistle detection dataset available at https://b-human.informatik.uni-bremen.de/public/datasets/whistle-2017/