Safe Active Learning and Probabilistic Design of Experiment for Autonomous Hydraulic Excavators
Maximilian Dio, Ozan Demir, Adrian Trachte, Knut Graichen
Abstract
Recently, data-driven and hybrid control of hydraulic cylinders for excavator assistance functions have been in the focus of many research papers. To ensure an accurate behavior, data-driven controllers and models need a large amount of data to cover all relevant operation regions, which requires a time-consuming data generation process. In this work, we introduce two learning-based methods to enhance the efficiency of this procedure: a static learning method and an active learning method. Both methods reduce the amount of required data to learn a hydraulic inverse actuation model. Compared to previous collection methods, the required data was reduced by factor 7.5, while the information content of the dataset remains nearly the same.
BibTeX
@inproceedings{iros2023_safeactivelearni,
title = {Safe Active Learning and Probabilistic Design of Experiment for Autonomous Hydraulic Excavators},
author = {Maximilian Dio and Ozan Demir and Adrian Trachte and Knut Graichen},
booktitle = {IROS 2023},
year = {2023}
}