A paradigm for safe adaptation of collaborating robots

Logo poskytovatele

Varování

Publikace nespadá pod Ekonomicko-správní fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

CIOROAICA Emilia BÜHNOVÁ Barbora TOMUR Emrah

Rok publikování 2022
Druh Článek ve sborníku
Konference SEAMS '22: Proceedings of the 17th Symposium on Software Engineering for Adaptive and Self-Managing Systems
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
Doi http://dx.doi.org/10.1145/3524844.3528061
Klíčová slova Virtual Evaluation; Runtime Prediction; Building Trust; Safety-Critical Systems; Robots
Popis The dynamic forces that transit back and forth traditional boundaries of system development have led to the emergence of digital ecosystems. Within these, business gains are achieved through the development of intelligent control that requires a continuous design and runtime co-engineering process endangered by malicious attacks. The possibility of inserting specially crafted faults capable to exploit the nature of unknown evolving intelligent behavior raises the necessity of malicious behavior detection at runtime. Adjusting to the needs and opportunities of fast AI development within digital ecosystems, in this paper, we envision a novel method and framework for runtime predictive evaluation of intelligent robots' behavior for assuring a cooperative safe adjustment.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.