Refining Process Descriptions from Execution Data in Hybrid Planning Domain Models
- Submitting institution
-
The University of Huddersfield
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 56
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling : (ICAPS 2020)
- First page
- 469
- Volume
- 30
- Issue
- -
- ISSN
- 2334-0835
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper’s novelty lies in the fact that it is the first work to define and validate a method for fusing data-driven learning with knowledge-based planning to refine engineered hybrid (PDDL+) planning models to self-configure to applied scenarios. Arising from Lindsay and McCluskey's involvement in work on applying AI Planning to Road Management: (https://www.h3bconnected.com/simplifai-urban-mobility-management-system-receives-near-e1m-innovate-uk-funding/, https://gtr.ukri.org/projects?ref=971549) the method adapts the PDDL+ to specific traffic scenarios to overcome the inherent brittleness of model-based AI. The hybrid model approach has led to the potential of other AI Planning applications such as automation of ultra high precision surface manufacture for fine-optics https://link.springer.com/article/10.1186/s41476-019-0119-y
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -