Heuristic Guidance for Forward-Chaining Planning with Numeric Uncertainty. Marinescu, L. & Coles, A. In Proceedings of the Twenty-Sixth International Conference on Automated Planning and Scheduling (ICAPS 2016), pages 230–234, 2016. ISSN: 09226389doi abstract bibtex Uncertainty hinders many interesting applications of planning – it may come in the form of sensor noise, unpredictable environments, or known limitations in problem models. In this paper we explore heuristic guidance for forward-chaining planning with continuous random variables, while ensuring a probability of plan success. We extend the Metric Relaxed Planning Graph heuristic to capture a model of uncertainty, providing better guidance in terms of heuristic estimates and dead-end detection. By tracking the accumulated error on nu- meric values, our heuristic is able to check if preconditions in the planning graph are achievable with a sufficient degree of confidence; it is also able to consider acting to reduce the accumulated error. Results indicate that our approach offers improvements in performance compared to prior work where a less-informed relaxation was used.
@inproceedings{marinescu_heuristic_2016,
title = {Heuristic {Guidance} for {Forward}-{Chaining} {Planning} with {Numeric} {Uncertainty}},
isbn = {978-1-61499-671-2},
doi = {10.3233/978-1-61499-672-9-1694},
abstract = {Uncertainty hinders many interesting applications of planning – it may come in the form of sensor noise, unpredictable environments, or known limitations in problem models. In this paper we explore heuristic guidance for forward-chaining planning with continuous random variables, while ensuring a probability of plan success. We extend the Metric Relaxed Planning Graph heuristic to capture a model of uncertainty, providing better guidance in terms of heuristic estimates and dead-end detection. By tracking the accumulated error on nu- meric values, our heuristic is able to check if preconditions in the planning graph are achievable with a sufficient degree of confidence; it is also able to consider acting to reduce the accumulated error. Results indicate that our approach offers improvements in performance compared to prior work where a less-informed relaxation was used.},
booktitle = {Proceedings of the {Twenty}-{Sixth} {International} {Conference} on {Automated} {Planning} and {Scheduling} ({ICAPS} 2016)},
author = {Marinescu, Liana and Coles, Andrew},
year = {2016},
note = {ISSN: 09226389},
keywords = {Technical Papers: Main Track},
pages = {230--234}
}
Downloads: 0
{"_id":"fHfwj2aNgDcYwxmS6","bibbaseid":"marinescu-coles-heuristicguidanceforforwardchainingplanningwithnumericuncertainty-2016","downloads":0,"creationDate":"2016-03-09T03:15:17.849Z","title":"Heuristic Guidance for Forward-Chaining Planning with Numeric Uncertainty","author_short":["Marinescu, L.","Coles, A."],"year":2016,"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/tillhofmann","bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Heuristic Guidance for Forward-Chaining Planning with Numeric Uncertainty","isbn":"978-1-61499-671-2","doi":"10.3233/978-1-61499-672-9-1694","abstract":"Uncertainty hinders many interesting applications of planning – it may come in the form of sensor noise, unpredictable environments, or known limitations in problem models. In this paper we explore heuristic guidance for forward-chaining planning with continuous random variables, while ensuring a probability of plan success. We extend the Metric Relaxed Planning Graph heuristic to capture a model of uncertainty, providing better guidance in terms of heuristic estimates and dead-end detection. By tracking the accumulated error on nu- meric values, our heuristic is able to check if preconditions in the planning graph are achievable with a sufficient degree of confidence; it is also able to consider acting to reduce the accumulated error. Results indicate that our approach offers improvements in performance compared to prior work where a less-informed relaxation was used.","booktitle":"Proceedings of the Twenty-Sixth International Conference on Automated Planning and Scheduling (ICAPS 2016)","author":[{"propositions":[],"lastnames":["Marinescu"],"firstnames":["Liana"],"suffixes":[]},{"propositions":[],"lastnames":["Coles"],"firstnames":["Andrew"],"suffixes":[]}],"year":"2016","note":"ISSN: 09226389","keywords":"Technical Papers: Main Track","pages":"230–234","bibtex":"@inproceedings{marinescu_heuristic_2016,\n\ttitle = {Heuristic {Guidance} for {Forward}-{Chaining} {Planning} with {Numeric} {Uncertainty}},\n\tisbn = {978-1-61499-671-2},\n\tdoi = {10.3233/978-1-61499-672-9-1694},\n\tabstract = {Uncertainty hinders many interesting applications of planning – it may come in the form of sensor noise, unpredictable environments, or known limitations in problem models. In this paper we explore heuristic guidance for forward-chaining planning with continuous random variables, while ensuring a probability of plan success. We extend the Metric Relaxed Planning Graph heuristic to capture a model of uncertainty, providing better guidance in terms of heuristic estimates and dead-end detection. By tracking the accumulated error on nu- meric values, our heuristic is able to check if preconditions in the planning graph are achievable with a sufficient degree of confidence; it is also able to consider acting to reduce the accumulated error. Results indicate that our approach offers improvements in performance compared to prior work where a less-informed relaxation was used.},\n\tbooktitle = {Proceedings of the {Twenty}-{Sixth} {International} {Conference} on {Automated} {Planning} and {Scheduling} ({ICAPS} 2016)},\n\tauthor = {Marinescu, Liana and Coles, Andrew},\n\tyear = {2016},\n\tnote = {ISSN: 09226389},\n\tkeywords = {Technical Papers: Main Track},\n\tpages = {230--234}\n}\n\n","author_short":["Marinescu, L.","Coles, A."],"key":"marinescu_heuristic_2016","id":"marinescu_heuristic_2016","bibbaseid":"marinescu-coles-heuristicguidanceforforwardchainingplanningwithnumericuncertainty-2016","role":"author","urls":{},"keyword":["Technical Papers: Main Track"],"downloads":0},"search_terms":["heuristic","guidance","forward","chaining","planning","numeric","uncertainty","marinescu","coles"],"keywords":["classical planning","probabilistic planning; mdps and pomdps","planning under (non-probabilistic) uncertainty","technical papers: main track"],"authorIDs":[],"dataSources":["9pYjFWPBodPyDyb7N"]}