Abstract
Endowing robots with the capability of assessing risk and making risk-aware decisions is widely considered a key step toward ensuring safety for robots operating under uncertainty. But, how should a robot quantify risk? A natural and common approach is to consider the framework whereby costs are assigned to stochastic outcomes–an assignment captured by a cost random variable. Quantifying risk then corresponds to evaluating a risk metric, i.e., a mapping from the cost random variable to a real number. Yet, the question of what constitutes a “good” risk metric has received little attention within the robotics community. The goal of this paper is to explore and partially address this question by advocating axioms that risk metrics in robotics applications should satisfy in order to be employed as rational assessments of risk. We provide instantiations of the class of risk metrics that satisfy these axioms (referred to as distortion risk metrics) and also discuss pitfalls of commonly used risk metrics in robotics that do not satisfy these axioms. Our hope is that the ideas presented here will lead to a foundational framework for quantifying risk (and hence safety) in robotics applications.
Anirudha Majumdar—Work performed as a postdoctoral scholar at Stanford University.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., Mané, D.: Concrete problems in AI safety (2016). arXiv:1606.06565
Artzner, P., Delbaen, F., Eber, J.-M., Heath, D.: Coherent measures of risk. Math. Financ. 9(3), 203–228 (1999)
Föllmer, H., Schied, A.: Stochastic Finance: An Introduction in Discrete Time. Walter de Gruyter (2011)
García, J., Fernández, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437–1480 (2015)
Glover, K., Doyle, J.C.: Relations between H\(_\infty \) and risk sensitive controllers. Analysis and Optimization of Systems. Springer, Berlin (1987)
Kuindersma, S., Grupen, R., Barto, A.: Variable risk control via stochastic optimization. Int. J. Robot. Res. 32(7), 806–825 (2013)
Maccheroni, F., Marinacci, M., Rustichini, A., Taboga, M.: Portfolio selection with monotone mean-variance preferences. Math. Finan. 19(3), 487–521 (2009)
Majumdar, A., Pavone, M.: How should a robot assess risk? Towards an axiomatic theory of risk in robotics. Extended version of ISRR 2017 paper (2017). arXiv:1710.11040
Majumdar, A., Singh, S., Mandlekar, A., Pavone, M.: Risk-sensitive inverse reinforcement learning via coherent risk models. Robotics Science and Systems (2017)
Mannor, S., Tsitsiklis, J.N.: Mean-variance optimization in Markov decision processes. In: International Conference on Machine Learning (2011)
B.C. on Banking Supervision: Fundamental Review of the Trading Book: A Revised Market Risk Framework. Bank for International Settlements (2014)
Rockafellar, R.T., Uryasev, S.: Optimization of conditional value-at-risk. J. Risk 2, 21–41 (2000)
Shapiro, A., Dentcheva, D., Ruszczyński, A.: Lectures on stochastic programming: Modeling and theory. SIAM, 2nd edn. (2014)
Wang, S.: A class of distortion operators for pricing financial and insurance risks. J. Risk Insur. 67(1), 15–36 (2000)
Whittle, P.: Risk-sensitive linear/quadratic/gaussian control. Adv. Appl. Probab. 13(4), 764–777 (1981)
Acknowledgements
The authors were partially supported by the Office of Naval Research, Science of Autonomy Program, under Contract N00014-15-1-2673.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Majumdar, A., Pavone, M. (2020). How Should a Robot Assess Risk? Towards an Axiomatic Theory of Risk in Robotics. In: Amato, N., Hager, G., Thomas, S., Torres-Torriti, M. (eds) Robotics Research. Springer Proceedings in Advanced Robotics, vol 10. Springer, Cham. https://doi.org/10.1007/978-3-030-28619-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-28619-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-28618-7
Online ISBN: 978-3-030-28619-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)