A Large-Scale Dataset for Humanoid Robotics Enabling a Novel Data-Driven Fall Prediction
Oliver Urbann, Julian Eßer, Diana Kleingarn, Arne Moos, Dominik Brämer, Piet Brömmel, Nicolas Bach, Christian Jestel
Abstract
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.
BibTeX
@inproceedings{icra2025_alargescaledatas,
title = {A Large-Scale Dataset for Humanoid Robotics Enabling a Novel Data-Driven Fall Prediction},
author = {Oliver Urbann and Julian Eßer and Diana Kleingarn and Arne Moos and Dominik Brämer and Piet Brömmel and Nicolas Bach and Christian Jestel and Aaron Larisch and Alice Kirchheim},
booktitle = {ICRA 2025},
year = {2025}
}