Trustworthy Autonomous Systems
Module type: compulsory elective
Academic: Prof. Dr.-Ing. Vladislav Nenchev
Field of study: Applied Computer Technology (ACT), Applied Communication Technology (CT), Cyber Security (CYB)
Credit points: 3
Autonomous systems are used in various areas, such as driving, manufacturing, the military, medical procedures, and home assistance systems. Due to their diverse applications, autonomous systems must be able to operate in a wide range of environments with uncertainties (e.g., sensor errors, timing errors, environmental changes, etc.).
This module establishes a taxonomy of trustworthy autonomous systems that must be reliable, secure, resilient, transparent, explainable and interpretable, privacy-conscious, and fair. It presents concepts, methods, and technologies that are useful for specifying and verifying the trustworthiness characteristics of autonomously operating systems. Through the use of model checking, runtime verification, reachability analysis, or automated falsification, the trustworthy application of autonomous systems in the real world can be ensured. Furthermore, architectural countermeasures for vulnerabilities in artificial intelligence are discussed. Verification is carried out in practical laboratory experiments.