Power Prediction for Heterogeneous Ground Robots Through Spatial Mapping and Sharing of Terrain Data
Michael Quann, Lauro V. Ojeda, William Smith, Denise M. Rizzo, Matthew P. Castanier, Kira Barton
Abstract
Ground robot power consumption often varies significantly throughout an off-road environment, depending on the terrain. Previous traversals over the environment can inform future predictions through spatial mapping of collected power data. However, such predictions are particular to a single robot. We develop a framework based on multi-task Gaussian process regression (MTGP) to share terrain information across multiple robots. The framework allows for the efficient selection of hyperparameters and the prediction of power consumption along paths through nearest neighbor data selection. The scaling of this approach is demonstrated in simulation. Furthermore, experimental testing with two robots shows a significant reduction in power prediction error when an environment, mapped by one robot, informs the power predictions of another robot.
BibTeX
@inproceedings{ral2020_powerpredictionf,
title = {Power Prediction for Heterogeneous Ground Robots Through Spatial Mapping and Sharing of Terrain Data},
author = {Michael Quann and Lauro V. Ojeda and William Smith and Denise M. Rizzo and Matthew P. Castanier and Kira Barton},
booktitle = {RA-L 2020},
year = {2020}
}