Epistemic AI and Robust Decision-Making Under Advanced Uncertainty
A special issue of Systems (ISSN 2079-8954). This special issue belongs to the section "Artificial Intelligence and Digital Systems Engineering".
Deadline for manuscript submissions: 30 November 2026 | Viewed by 338
Editors
Interests: imprecise artificial intelligence; imprecise probability theory; optimization under imprecise uncertainty; decision-making under imprecise uncertainty; epistemic reinforcement learning; P&O under imprecise uncertainty; uncertainty quantification; trustworthy AI
Interests: application of machine learning/pattern recognition techniques to industrial topics signal and image processing: automated detection of defects, objects, lanes, etc.; sensor data fusion: evidence theory; reconstruction techniques: 3D-ultrasound tomography; nondestructive testing methods: ultrasound and X-ray; quality control: automated data analysis, defect classification, and online NDT and SHM system conception and development; driver assistance systems: signal- and video-based processing algorithms for driver assistance
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Artificial Intelligence systems are increasingly deployed in safety-critical, socio-technical, and high-stakes environments. However, most current AI models rely on precise probabilistic assumptions and often fail to properly distinguish between aleatoric and epistemic uncertainty. Under distribution shifts, incomplete knowledge, or sparse data, these limitations may lead to brittle decisions and overconfident predictions.
This Special Issue will focus on epistemic AI, a paradigm that explicitly models uncertainty due to lack of knowledge or advanced model uncertainty using frameworks such as credal sets, imprecise probabilities, interval methods, random sets, evidence theory, and robust optimization. We aim to bridge theoretical advances and real-world applications in robust decision-making under advanced uncertainty.
We welcome contributions addressing novel uncertainty representations, epistemic reinforcement learning, robust control, uncertainty-aware generative AI, trustworthy AI, decision-focused learning under advanced uncertainty, and applications in engineering systems, healthcare, robotics, manufacturing, and socio-technical systems.
This topic aligns strongly with the scope of Systems by emphasizing system-level modeling, decision processes, robustness, and interdisciplinary integration across engineering and computational sciences.
Dr. Keivan Shariatmadar
Prof. Dr. Ahmad Osman
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Systems is an international peer-reviewed open access monthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- epistemic uncertainty
- credal sets
- imprecise probability
- imprecise decision-making
- uncertainty quantification
- distribution shift
- decision-focused learning
- trustworthy AI
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
