Safety + AI: A Novel Approach to Update Safety Models Using Artificial Intelligence
- Submitting institution
-
The University of Hull
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2853693
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2019.2941566
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 135855
- Volume
- 7
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2019
- 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
-
-
- Research group(s)
-
-
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper describes work on safety of cooperative autonomous systems done the DEIS EU research project (2017-2020, http://www.deis-project.eu/home/). Predictive models of safety, like fault trees or Bayesian nets, can be incorrect and this paper shows how AI techniques could detect issues and repair them. This is essential in real-time management of safety in cooperative intelligent systems. AVL and Siemens are currently applying this work. A new project on safety and security of multi-robot systems (SESAME, 2021-2024) will extend this work to address model-repair in dynamic certification of multi-robot systems. The paper contributes to the BIOLOGIC ICS.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -