Trustworthy Autonomous Systems (TAS): The Verifiability Approach
DOI:
https://doi.org/10.26439/ciis2022.6063Keywords:
autonomous systems, trust, verifiability, validation and verification, testingAbstract
Autonomous systems are taking over the decision-making in many crucial aspects of our lives. Trust in them will help users benefit from such systems without harming themselves. Establishing the right level of trust involves a holistic validation and verification process, accounting for aspects such as interactions with the physical world and human users. In this talk, I present our ongoing effort to provide a holistic framework for ensuring the verifiability of autonomous systems
Downloads
References
Araujo, H. L. S., Damasceno, C. D. N., Dimitrova, R., Kefalidou, G., Mehtarizadeh, M., Mousavi, M. R., Onime, J., Ringert, J. O., Rojas, J. M., Verdezoto, N. X., & Wali, S. (2019, October 21-23). Trusted autonomous vehicles: An interactive exhibit.) [Conferencepresentation]. 2019 IEEE International Conferences on Ubiquitous Computing & Communications (IUCC) and Data Science and Computational Intelligence (DSCI) and Smart Computing, Networking and Services (SmartCNS), Shenyang, China. https://doi.org/10.1109/IUCC/DSCI/SmartCNS.2019.00091
Araujo, H., Hoenselaar, T., Mousavi, M. R., & Vinel, A. (2020, August 31-September 3). Connected automated driving: A model-based approach to the analysis of basic awareness services [Conference presentation]. 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, London, United Kingdom. https://doi.org/10.1109/PIMRC48278.2020.9217142
Araujo, H., Mousavi, M. R., & Varshosaz, M. (2022). Testing, validation, and verification of robotic and autonomous systems: A systematic review. ACM Transactions on Software Engineering and Methodology.. https://doi.org/10.1145/3542945
Biewer, S., Dimitrova, R., Fries, M., Gazda, M., Heinze, T., Hermanns, H., & Mousavi, M. R. (2022). Conformance relations and hyperproperties for doping detection in time and space. Logical Methods in Computer Science, 18(1). https://doi.org/10.46298/lmcs-18(1:14)2022
Damasceno, C. D. N., Mousavi, M. R., & da Silva Simao, A. (2019, December 2-6). Learning to reuse: Adaptive model learning for evolving systems [Conference presentation]. 15th International Conference, IFM 2019, Bergen, Norway.. https://doi.org/10.1007/978-3-030-34968-4_8
Damasceno, C. D. N., Mousavi, M. R., & Simao, A. da S. (2021). Learning by sampling: Learning behavioral family models from software product lines. Empirical Software Engineering, 26, 4. https://doi.org/10.1007/s10664-020-09912-w
Gou, M. S., Lakatos, G., Holthaus, P., Wood, L., Mousavi, M. R., Robins, B., & Amirabdollahian, F. (2022, August 29-September 2). Towards understanding causality – a retrospective study of using explanations in interactions between a humanoid robot and autistic children [Conference presentation]. 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Naples, Italy. https://doi.org/10.1109/RO-MAN53752.2022.9900660
Mousavi M. R., Cavalcanti A., Fisher M., Dennis L., Hierons R., Kaddouh B., Law E. L., Richardson R., Ringert J. O., Tyukin I., & Woodcock J (2022). Trustworthy autonomous systems through verifiability. IEEE Software.
Tavassoli, S., Damasceno, C. D. N., Khosravi, R., & Mousavi, M. R. (2022, September 12-16). Adaptive behavioral model learning for software product lines [Conference presentation]. Proceedings of the 26th ACM International Systems and Software Product Line Conference Graz, Austria. https://doi.org/10.1145/3546932.3546991
