B-Human

Neural Network-based Joint Angle Prediction for the NAO Robot. RoboCup 2023 symposium.

• The dataset contains the requested and measured joint angles of the leg joints of all B-Human robots during walking, recorded on multiple different fields during four full RoboCup tournaments in 2019 and 2022.
  https://b-human.informatik.uni-bremen.de/public/datasets/joint_angles/

Soccer Field Boundary Detection Using Convolutional Neural Networks.
Arne Hasselbring, Andreas Baude.  RoboCup 2021 symposium (2022).

• This dataset that can be used to train a fieldboundary detection. The images are stored binary and every image has a label that consists of 4 values for each direction.
  https://b-human.informatik.uni-bremen.de/public/datasets/fieldboundary/

Closing the Reality Gap with Unsupervised Sim-to-Real Image Translation.
Jan Blumenkamp, Andreas Baude, Tim Laue. In RoboCup 2021 symposium (2022).

• https://b-human.informatik.uni-bremen.de/public/datasets/semantic_segmentation/

JET-Net: Real-time object detection for mobile robots.
Bernd Poppinga and Tim Laue. 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.

• https://b-human.informatik.uni-bremen.de/public/JET-Net/

Nao lower camera ball detection dataset that was auto-labeled available at 

• https://b-human.informatik.uni-bremen.de/public/datasets/balldetector_lc/

Whistle detection

• https://b-human.informatik.uni-bremen.de/public/datasets/whistle-2017/