Back to search

FRINATEK-Fri prosj.st. mat.,naturv.,tek

Unlocking the potential of autonomous systems and operations through supervisory risk control

Alternative title: Risikomodellering og risikokontroll av autonome systemer og operasjoner

Awarded: NOK 10.2 mill.

Autonomous systems are emerging and important for allowing novel and challenging operations, such as mapping and monitoring of oceans and land areas, inspections of constructions which are difficult for people to access, and autonomous sea and land-based transportation. On one hand autonomy may contribute to safer and more efficient operations, but on the other hand; increased reliance on software and advanced control systems also leads to risks, couplings, and complexities that are challenging to identify, assess, and mitigate. Autonomous systems are used in operations with different potential hazardous consequences; from major hazards to occupational risk that may cause human fatalities and injuries, negative environmental impact, and material damage. In this research project, a supervisory risk control concept has been developed, with special emphasis on unmanned aerial vehicles (UAV) used for industrial inspection of confined areas, and autonomous underwater vehicles (AUV), used e.g., in ocean monitoring under-ice operations. The supervisory risk control concept includes selected risk analysis methods combined with control theory that enables the autonomous systems to consider safety and efficiency during operation. This means that supervisory risk control is incorporated as an autonomous functionality in the systems, which enables risk-based decisions supporting safe operations. 2 PhD students and 1 Post Doc have been funded by the project. Master theses have also been associated to the project.

Prosjektet " Unlocking the potential of autonomous systems and operations through supervisory risk control" har bidratt til ny og verdifull kunnskap om sikkerhet og effektivitet i autonome systemer og operasjoner, som kan anvendes i fremtidig forskning og næringsutvikling. Prosjektet har vært tverrfaglig og har koblet sammen fagområdene risikostyring, kybernetikk og kunstig intelligens. Arbeidet har ført til i) et nytt rammeverk for risikobaserte beslutninger i autonome systemer, med fokus på ubemannede luftfarkoster og undervannsdroner, ii) ny teknologi for økt autonomi, det vil si nye og forbedrede metoder for kollisjonsunngåelse, inspeksjonsbaserte beslutninger, undervannsnavigasjon og baneplanlegging. Dette arbeidet forventes å ha stor nytteverdi for industribedrifter, leverandører, myndigheter og FoU-miljø som jobber med autonome systemer. Prosjektet har utdannet to ph.d.-studenter, samt en post doc. To masteroppgaver har blitt levert på tema knyttet til prosjektet. Dette bidrar til å gi norsk industri, forskningsinstitutter og statlige virksomheter dyktige kandidater med spesiell kompetanse på prosjektområdet. Resultatene i prosjektet er ikke bare relevante for ubemannede og autonome farkoster, men kan også anvendes på andre komplekse systemer, for eksempel autonome skip.

This proposal addresses fundamental research challenges related to risk acceptance and supervisory risk control of autonomous systems and operations. The aim is to develop more powerful risk control solutions to achieve safe system performances and allow for widespread use of autonomous systems. The outcomes of this ambitious project will support and enhance the achievement of higher-level autonomy and intelligence in advanced control systems through the integration of online risk modelling, testing and verification of safe responses with model predictive control (MPC). Autonomous systems are emerging and essential for allowing new and challenging operations, such as mapping and monitoring of oceans and areas on land, inspections of structures difficult to access, and autonomous transportation, both land based and at sea. Autonomous functionality may be a step towards safer and more efficient operations, but software and advanced control systems also lead to complexity and interlocks that are extremely challenging to identify, assess, and control. Autonomous systems are used in very different operations with a range of hazards; from major hazards to occupational risk that may cause human fatalities and injuries, environmental and asset damage, and economic losses. The lack of knowledge, standards and limited operational experience, make traditional risk reducing measures, such as component redundancy and existing methods for verification and validation (V&V), ineffective. Acceptance of highly intelligent systems with built-in learning and optimization capabilities require supervisory risk control and online risk modelling, testing and verification to become a driver in design, operation and system validation. Thus, the interdisciplinary research approach in this project builds on the most powerful theories of risk modelling, V&V, control engineering and autonomous systems. The fundamental research results will be applicable to a wide range of autonomous systems.

Publications from Cristin

No publications found

Funding scheme:

FRINATEK-Fri prosj.st. mat.,naturv.,tek