<div class="csl-bib-body">
<div class="csl-entry">Bartocci, E., Češka, M., Hudák, D., Novotný, P., & Tappler, M. (2026). Towards Robust and Safe Decision-Making Under Uncertainty: A Model-Centric View. In T. Margaria & B. Steffen (Eds.), <i>Leveraging Applications of Formal Methods, Verification and Validation. X-by-Construction Meets Intersymbolic AI : 13th International Symposium, ISoLA 2026, Kos, Greece, October 24–28, 2026, Proceedings, Part IV</i> (pp. 31–54). Springer. https://doi.org/10.1007/978-3-032-40121-2_3</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/232409
-
dc.description.abstract
Intelligent autonomous systems are increasingly deployed in safety-critical domains operating in open, complex, and potentially adversarial environments. Ensuring the trustworthiness of their decision-making requires addressing fundamental challenges, such as uncertainty in agent-environment interactions, high-dimensional state spaces, and partial observability. In this paper, we present a unifying perspective on our ongoing work toward safe, robust decision-making in autonomous systems. We argue that adequate symbolic models (whether designed or learned from observations) are essential for achieving trust by design. Building on this insight, we outline a neuro-symbolic decision-making framework that integrates model checking, controller synthesis, and reinforcement learning through a continuous loop of model construction and data-driven refinement, verification, and testing, both at development time and runtime. Finally, we propose a research roadmap toward hybrid verification approaches that combine learning and formal methods to enable adaptive, scalable, and trustworthy autonomous systems utilising agentic AI. This vision highlights the role of model learning and model-based verification and synthesis for bridging the gap between decision-level guarantees and efficient data-driven learning.
en
dc.description.sponsorship
FFG - Österr. Forschungsförderungs- gesellschaft mbH
-
dc.description.sponsorship
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
-
dc.language.iso
en
-
dc.relation.ispartofseries
Lecture Notes in Computer Science
-
dc.subject
Autonomous systems
en
dc.subject
Safe decision-making
en
dc.subject
Neuro-symbolic AI
en
dc.subject
Model checking
en
dc.subject
Controller synthesis
en
dc.subject
Reinforcement learning
en
dc.subject
Formal verification
en
dc.subject
Model learning
en
dc.subject
Runtime verification
en
dc.title
Towards Robust and Safe Decision-Making Under Uncertainty: A Model-Centric View
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.contributor.affiliation
Brno University of Technology, Czechia
-
dc.contributor.affiliation
Brno University of Technology, Czechia
-
dc.contributor.affiliation
Masaryk University, Czechia
-
dc.contributor.editoraffiliation
University of Limerick, Ireland
-
dc.contributor.editoraffiliation
TU Dortmund University, Germany
-
dc.relation.isbn
978-3-032-40120-5
-
dc.relation.doi
10.1007/978-3-032-40121-2
-
dc.relation.issn
0302-9743
-
dc.description.startpage
31
-
dc.description.endpage
54
-
dc.relation.grantno
936797
-
dc.relation.grantno
ICT22-023
-
dc.type.category
Full-Paper Contribution
-
dc.relation.eissn
1611-3349
-
tuw.booktitle
Leveraging Applications of Formal Methods, Verification and Validation. X-by-Construction Meets Intersymbolic AI : 13th International Symposium, ISoLA 2026, Kos, Greece, October 24–28, 2026, Proceedings, Part IV
-
tuw.container.volume
1
-
tuw.peerreviewed
true
-
tuw.relation.publisher
Springer
-
tuw.relation.publisherplace
Cham
-
tuw.project.title
Neuro-symbolic Ethical Safe Traffic
-
tuw.project.title
Training and Guiding AI Agents with Ethical Rules
-
tuw.researchTopic.id
I2
-
tuw.researchTopic.name
Computer Engineering and Software-Intensive Systems
-
tuw.researchTopic.value
100
-
tuw.publication.orgunit
E191-01 - Forschungsbereich Cyber-Physical Systems
-
tuw.publication.orgunit
E192-04 - Forschungsbereich Formal Methods in Systems Engineering
-
tuw.publication.orgunit
E056-13 - Fachbereich LogiCS
-
tuw.publication.orgunit
E056-17 - Fachbereich Trustworthy Autonomous Cyber-Physical Systems
-
tuw.publication.orgunit
E056-26 - Fachbereich Automated Reasoning
-
tuw.publisher.doi
10.1007/978-3-032-40121-2_3
-
dc.description.numberOfPages
24
-
tuw.author.orcid
0000-0002-8004-6601
-
tuw.author.orcid
0009-0003-9158-3407
-
tuw.author.orcid
0000-0002-7229-0997
-
tuw.editor.orcid
0000-0002-5547-9739
-
tuw.editor.orcid
0000-0001-9619-1558
-
tuw.event.name
International Symposium on Leveraging Applications of Formal Methods, Verification, and Validation (ISoLA 2026)
en
tuw.event.startdate
24-10-2026
-
tuw.event.enddate
28-10-2026
-
tuw.event.online
On Site
-
tuw.event.type
Event for scientific audience
-
tuw.event.place
Kos
-
tuw.event.country
GR
-
tuw.event.presenter
Češka, Milan
-
tuw.event.presenter
Hudák, David
-
wb.sciencebranch
Informatik
-
wb.sciencebranch.oefos
1020
-
wb.sciencebranch.value
100
-
item.openairetype
conference paper
-
item.fulltext
no Fulltext
-
item.grantfulltext
none
-
item.openairecristype
http://purl.org/coar/resource_type/c_5794
-
item.cerifentitytype
Publications
-
item.languageiso639-1
en
-
crisitem.author.dept
E191-01 - Forschungsbereich Cyber-Physical Systems
-
crisitem.author.dept
Brno University of Technology, Czechia
-
crisitem.author.dept
Brno University of Technology, Czechia
-
crisitem.author.dept
Masaryk University, Czechia
-
crisitem.author.dept
E191-01 - Forschungsbereich Cyber-Physical Systems
-
crisitem.author.orcid
0000-0002-8004-6601
-
crisitem.author.orcid
0009-0003-9158-3407
-
crisitem.author.orcid
0000-0002-7229-0997
-
crisitem.author.parentorg
E191 - Institut für Computer Engineering
-
crisitem.author.parentorg
E191 - Institut für Computer Engineering
-
crisitem.project.funder
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds