Qualitative Planning with Quantitative Constraints for Online Learning of Robotic Behaviours
Abstract
This paper resolves previous problems in the Multi-Strategy architecture for online learning of robotic behaviours. The hybrid method includes a symbolic qualitative planner that constructs an approximate solution to a control problem. The approximate solution provides constraints for a numerical optimisation algorithm, which is used to refine the qualitative plan into an operational policy. Introducing quantitative constraints into the planner gives previously unachievable domain independent reasoning. The method is demonstrated on a multi-tracked robot intended for urban search and rescue.
Cite
Text
Wiley et al. "Qualitative Planning with Quantitative Constraints for Online Learning of Robotic Behaviours." AAAI Conference on Artificial Intelligence, 2014. doi:10.1609/AAAI.V28I1.9055Markdown
[Wiley et al. "Qualitative Planning with Quantitative Constraints for Online Learning of Robotic Behaviours." AAAI Conference on Artificial Intelligence, 2014.](https://mlanthology.org/aaai/2014/wiley2014aaai-qualitative/) doi:10.1609/AAAI.V28I1.9055BibTeX
@inproceedings{wiley2014aaai-qualitative,
title = {{Qualitative Planning with Quantitative Constraints for Online Learning of Robotic Behaviours}},
author = {Wiley, Timothy and Sammut, Claude and Bratko, Ivan},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2014},
pages = {2578-2584},
doi = {10.1609/AAAI.V28I1.9055},
url = {https://mlanthology.org/aaai/2014/wiley2014aaai-qualitative/}
}