Abstract
This paper describes a framework for a hybrid algorithm that combines both AI Planning and Model Predictive Control approaches to reason with processes and events within a domain. This effectively utilises the strengths of search-based and model-simulation-based methods. We explore this control approach and show how it can be embedded into existing, modern AI Planning technology. This preserves the many advantages of the AI Planning approach, to do with domain independence through declarative modelling, and explicit reasoning, while leveraging the capability of MPC to deal with continuous processes computation within such domains. The developed technique is tested on an urban traffic control application and the results demonstrate the potential in utilising MPC as a heurisic to guide planning search.
| Language | English |
|---|---|
| Number of pages | 8 |
| Journal | CEUR Workshop Proceedings |
| Volume | 1782 |
| Publication status | Published - 16 Jan 2017 |
| Event | 34th Workshop of the UK Planning and Scheduling Special Interest Group - University of Huddersfield, Huddersfield, United Kingdom Duration: 15 Dec 2016 → 16 Dec 2016 Conference number: 34 https://plansig2016.wordpress.com/ (Link to Event Website) |
Fingerprint
Cite this
}
Towards the integration of model predictive control into an AI planning framework. / Jimoh, Falilat; McCluskey, Thomas L.
In: CEUR Workshop Proceedings, Vol. 1782, 16.01.2017.Research output: Contribution to journal › Conference article
TY - JOUR
T1 - Towards the integration of model predictive control into an AI planning framework
AU - Jimoh, Falilat
AU - McCluskey, Thomas L.
PY - 2017/1/16
Y1 - 2017/1/16
N2 - This paper describes a framework for a hybrid algorithm that combines both AI Planning and Model Predictive Control approaches to reason with processes and events within a domain. This effectively utilises the strengths of search-based and model-simulation-based methods. We explore this control approach and show how it can be embedded into existing, modern AI Planning technology. This preserves the many advantages of the AI Planning approach, to do with domain independence through declarative modelling, and explicit reasoning, while leveraging the capability of MPC to deal with continuous processes computation within such domains. The developed technique is tested on an urban traffic control application and the results demonstrate the potential in utilising MPC as a heurisic to guide planning search.
AB - This paper describes a framework for a hybrid algorithm that combines both AI Planning and Model Predictive Control approaches to reason with processes and events within a domain. This effectively utilises the strengths of search-based and model-simulation-based methods. We explore this control approach and show how it can be embedded into existing, modern AI Planning technology. This preserves the many advantages of the AI Planning approach, to do with domain independence through declarative modelling, and explicit reasoning, while leveraging the capability of MPC to deal with continuous processes computation within such domains. The developed technique is tested on an urban traffic control application and the results demonstrate the potential in utilising MPC as a heurisic to guide planning search.
UR - http://www.scopus.com/inward/record.url?scp=85013301843&partnerID=8YFLogxK
M3 - Conference article
VL - 1782
JO - CEUR Workshop Proceedings
T2 - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
ER -