A Large-Scale Dataset for Humanoid Robotics Enabling a Novel Data-Driven Fall Prediction

In this paper, we present a comprehensive dataset comprising 37.9 hours of sensor data collected from humanoid robots, including 18.3 hours of walking and 2,519 recorded falls. This extensive dataset is a valuable resource for various robotics and machine learning applications. Leveraging this data, we propose {RePro}-{TCN}, a Temporal Convolutional Network ({TCN}) enhanced with two novel extensions: Relaxed Loss Formulation and Progressive Forecasting. Predicting falls is a critical capability in humanoid robotics for implementing countermeasures such as lunging or stopping the walk. Thanks to the new dataset, we train {RePro}-{TCN} and demonstrate its superiority over previous approaches under real-world conditions that were previously unattainable.

  • Published in:
    2025 IEEE International Conference on Robotics and Automation (ICRA)
  • Type:
    Inproceedings
  • Authors:
    Urbann, Oliver; Eßer, Julian; Kleingarn, Diana; Moos, Arne; Brämer, Dominik; Brömmel, Piet; Bach, Nicolas; Jestel, Christian; Larisch, Aaron; Kirchheim, Alice
  • Year:
    2025
  • Source:
    https://ieeexplore.ieee.org/abstract/document/11128646

Citation information

Urbann, Oliver; Eßer, Julian; Kleingarn, Diana; Moos, Arne; Brämer, Dominik; Brömmel, Piet; Bach, Nicolas; Jestel, Christian; Larisch, Aaron; Kirchheim, Alice: A Large-Scale Dataset for Humanoid Robotics Enabling a Novel Data-Driven Fall Prediction, 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025, 13906--13912, May, IEEE, https://ieeexplore.ieee.org/abstract/document/11128646, Urbann.etal.2025a,