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 
  • Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL. Roberto Fernandes, Walber M. Rodrigues and Edna Barros

  • 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


Pre 2019 data sets:
Additional links and tools to create data sets:
  • 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

  • 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