Abstract
We investigate deceptive planning, the problem of generating a plan such that an observer is unable to determine its ultimate goal. Most work in this area has focused on path and/or motion planning. However planning problems can be quite varied and challenging. We present domain-independent approaches for deceptive plan generation utilising the concepts of landmarks, centroids, and minimum covering states. We introduce new, domain-independent metrics to evaluate a plan's deceptivity as a ratio between its deceptive quantity and cost; and we extensively evaluate the performance of our proposed approaches over widely different planning domains providing guidelines as to when to use each approach.
Original language | English |
---|---|
Pages (from-to) | 95-103 |
Number of pages | 9 |
Journal | Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS |
Volume | 2023-May |
State | Published - 2023 |
Externally published | Yes |
Event | 22nd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2023 - London, United Kingdom Duration: 29 May 2023 → 2 Jun 2023 |
Bibliographical note
Publisher Copyright:© 2023 International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Funding
Peta Masters’ research is supported by the UKRI Trustworthy Autonomous Systems (TAS) Hub (EP/V00784X/1).
Funders | Funder number |
---|---|
UKRI Trustworthy Autonomous Systems | |
Tennessee Academy of Science | EP/V00784X/1 |
Keywords
- Deception
- Domain-Independent
- Plan Recognition
- Planning