BIBLIOGRAPHY 59
[157] Jur Van Den Berg, Stephen Miller, Daniel Duckworth, Humphrey Hu, Andrew Wan,
Xiao-Yu Fu, Ken Goldberg, and Pieter Abbeel. Superhuman performance of surgi-
cal tasks by robots using iterative learning from human-guided demonstrations. In
IEEE International Conference on Robotics and Automation, pages 2074–2081, 2010. DOI:
10.1109/robot.2010.5509621 28
[158] T. Hester, M. Vecerik, O. Pietquin, M. Lanctot, T. Schaul, B. Piot, D. Horgan, J. Quan,
A. Sendonaris, G. Dulac-Arnold, et al. Learning from demonstrations for real world
reinforcement learning. ArXiv, 2017. 28
[159] Davide Castelvecchi. Can we open the black box of AI? Nature News, 538(7623):20,
2016. DOI: 10.1038/538020a 28, 31
[160] Perry Van Wesel and Alwyn E. Goodloe. Challenges in the verification of reinforcement
learning algorithms. Technical report, NASA, 2017. 29, 39
[161] International Organization for Standardization. ISO 26262: Road vehicles-functional
safety. International Standard ISO/FDIS, 2011. 31
[162] Xiaodong Zhang, Matthew Clark, Kudip Rattan, and Jonathan Muse. Controller
verification in adaptive learning systems towards trusted autonomy. In Proc. of the
ACM/IEEE 6th International Conference on Cyber-Physical Systems, pages 31–40, 2015.
DOI: 10.1145/2735960.2735971 31
[163] Matthew Clark, Xenofon Koutsoukos, Joseph Porter, Ratnesh Kumar, George Pappas,
Oleg Sokolsky, Insup Lee, and Lee Pike. A study on run time assurance for complex cyber
physical systems. Technical Report, Air Force Research Lab Wright-Patterson AFB, OH,
Aerospace Systems DIR, 2013. DOI: 10.21236/ada585474 33, 34
[164] Bojan Cukic. e need for verification and validation techniques for adaptive control
system. In Autonomous Decentralized Systems. Proc. of the 5th International Symposium on,
pages 297–298, IEEE, 2001. DOI: 10.1109/isads.2001.917431
[165] Stephen Jacklin, Johann Schumann, Pramod Gupta, Michael Richard, Kurt Guenther,
and Fola Soares. Development of advanced verification and validation procedures and tools
for the certification of learning systems in aerospace applications. In Infotech@ Aerospace,
page 6912, 2005. DOI: 10.2514/6.2005-6912
[166] Chris Wilkinson, Jonathan Lynch, and Raj Bharadwaj. Final report, regulatory consid-
erations for adaptive systems. National Aeronautics and Space Administration, Langley
Research Center, 2013. 31
[167] Anh Nguyen, Jason Yosinski, and Jeff Clune. Deep neural networks are easily
fooled: High confidence predictions for unrecognizable images. In Proc. of the IEEE