Abstract
Accurately predicting risk or potentially risky situations is critical for the safe operation of autonomous systems. Risk refers to the expected likelihood of an undesirable outcome, such as a collision. We draw on an existing conceptualization of the risk to evaluate a robot’s options (e.g. choice of a path to travel). In this context, risk consists of two components: 1) the probability of an undesirable outcome computed by a Bayesian Network (BN) and 2) an estimate of the loss associated with the undesirable outcome. We demonstrate that our risk assessment tool is effective at computing the anticipated risk over a wide variety of the robot’s options and selecting the option with the lowest risk for two different types of autonomous systems: An Autonomous Vehicle (AV) operating near a college campus and a pair of Unmanned Aerial Vehicles (UAVs) flying from Washington DC to Baltimore. The method for assessing risk is used to identify higher risk routes, days to travel, and travel times for an autonomous vehicle and higher risk routes for a UAV.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Allouch, A., Koubaa, A., Khalgui, M., Abbes, T.: Qualitative and quantitative risk analysis and safety assessment of unmanned aerial vehicles missions over the internet. IEEE Access 7, 53392–53410 (2019)
Ancel, E., Capristan, F.M., Foster, J.V., Condotta, R.C.: Real-time risk assessment frame-work for unmanned aircraft system (UAS) traffic management (UTM). In: 17th AIAA Aviation Technology, Integration, and Operations Conference. p. 3273 (2017)
Barr, L.C., et al.: Preliminary risk assessment for small unmanned aircraft systems. In: 17th AIAA Aviation Technology, Integration, and Operations Conference, p. 3272 (2017)
Berger, J.O.: Prior information and subjective probability. In: Berger, J.O. (ed.) Statistical Decision Theory and Bayesian Analysis. SSS, pp. 74–117. Springer, New York (1985). https://doi.org/10.1007/978-1-4757-4286-2_3
Chinea, A., Parent, M.: Risk assessment algorithms based on recursive neural networks. In: 2007 International Joint Conference on Neural Networks, pp. 1434–1440. IEEE (2007)
Cornett, M.M., Saunders, A.: Financial Institutions Management: A Risk Management Approach. McGraw-Hill/Irwin, New York (2003)
Dalamagkidis, K., Valavanis, K.P., Piegl, L.A.: Evaluating the risk of unmanned aircraft ground impacts. In: 2008 16th Mediterranean Conference on Control and Automation, pp. 709–716. IEEE (2008)
Dávid, B., Láncz, G., Hunyady, G.: Highway situation analysis with scenario classification and neural network based risk estimation for autonomous vehicles. In: 2019 IEEE 17th World Symposium on Applied Machine Intelligence and Informatics (SAMI), pp. 375–380. IEEE (2019)
De Filippis, L., Guglieri, G., Quagliotti, F.: A minimum risk approach for path planning of UAVs. J. Intell. Robot. Syst. 61(1–4), 203–219 (2011). https://doi.org/10.1007/s10846-010-9493-9
Geramifard, A., Redding, J., Roy, N., How, J.P.: UAV cooperative control with stochastic risk models. In: Proceedings of the 2011 American Control Conference, pp. 3393–3398. IEEE (2011)
Greytak, M., Hover, F.: Motion planning with an analytic risk cost for holonomic vehicles. In: Proceedings of the 48th IEEE Conference on Decision and Control (CDC) Held Jointly with 2009 28th Chinese Control Conference, pp. 5655–5660. IEEE (2009)
Kwag, S., Gupta, A., Dinh, N.: Probabilistic risk assessment based model validation method using Bayesian network. Reliab. Eng. Syst. Saf. 169, 380–393 (2018)
Mokhtari, K., Wagner, A.R.: The pedestrian patterns dataset. In: AAAI Fall 2019 Symposium (2019)
Rudnick-Cohen, E., Herrmann, J.W., Azarm, S.: Risk-based path planning optimization methods for UAVs over inhabited areas. In: ASME 2015 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers Digital Collection (2015)
Strickland, M., Fainekos, G., Amor, H.B.: Deep predictive models for collision risk assessment in autonomous driving. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–8. IEEE (2018)
Waggoner, B.: Developing a risk assessment tool for unmanned aircraft system operations. Ph.D. thesis, University of Washington (2010)
Weibel, R., Hansman, R.J.: Safety considerations for operation of different classes of UAVs in the NAS. In: AIAA 4th Aviation Technology, Integration and Operations (ATIO) Forum, p. 6244 (2004)
Yu, M.Y., Vasudevan, R., Johnson-Roberson, M.: Occlusion-aware risk assessment for autonomous driving in urban environments. IEEE Robot. Autom. Lett. 4(2), 2235–2241 (2019)
Acknowledgment
This work was supported by Air Force Office of Sponsored Research contract FA9550-17-1-0017 and Navy STTR contract N68335-19-C-0106.
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
Mokhtari, K., Lang, K.A., Wagner, A.R. (2020). Don’t Go That Way! Risk-Aware Decision Making for Autonomous Vehicles. In: Wagner, A.R., et al. Social Robotics. ICSR 2020. Lecture Notes in Computer Science(), vol 12483. Springer, Cham. https://doi.org/10.1007/978-3-030-62056-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-62056-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62055-4
Online ISBN: 978-3-030-62056-1
eBook Packages: Computer ScienceComputer Science (R0)