A paradigm for safe adaptation of collaborating robots

Investor logo

Warning

This publication doesn't include Faculty of Economics and Administration. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

CIOROAICA Emilia BÜHNOVÁ Barbora TOMUR Emrah

Year of publication 2022
Type Article in Proceedings
Conference SEAMS '22: Proceedings of the 17th Symposium on Software Engineering for Adaptive and Self-Managing Systems
MU Faculty or unit

Faculty of Informatics

Citation
Doi http://dx.doi.org/10.1145/3524844.3528061
Keywords Virtual Evaluation; Runtime Prediction; Building Trust; Safety-Critical Systems; Robots
Description 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.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.