This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Toward a Framework for Highly Automated Vehicle Safety Validation
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 3, 2018 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
Validating the safety of Highly Automated Vehicles (HAVs) is a significant autonomy challenge. HAV safety validation strategies based solely on brute force on-road testing campaigns are unlikely to be viable. While simulations and exercising edge case scenarios can help reduce validation cost, those techniques alone are unlikely to provide a sufficient level of assurance for full-scale deployment without adopting a more nuanced view of validation data collection and safety analysis. Validation approaches can be improved by using higher fidelity testing to explicitly validate the assumptions and simplifications of lower fidelity testing rather than just obtaining sampled replication of lower fidelity results. Disentangling multiple testing goals can help by separating validation processes for requirements, environmental model sufficiency, autonomy correctness, autonomy robustness, and test scenario sufficiency. For autonomy approaches with implicit designs and requirements, such as machine learning training data sets, establishing observability points in the architecture can help ensure that vehicles pass the right tests for the right reason. These principles could improve both efficiency and effectiveness for demonstrating HAV safety as part of a phased validation plan that includes both a “driver test” and lifecycle monitoring as well as explicitly managing validation uncertainty.
CitationKoopman, P. and Wagner, M., "Toward a Framework for Highly Automated Vehicle Safety Validation," SAE Technical Paper 2018-01-1071, 2018, https://doi.org/10.4271/2018-01-1071.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
- Koopman, P. and Wagner, M., “Autonomous Vehicle Safety: An Interdisciplinary Challenge,” IEEE Intelligent Transportation Systems Magazine 9(1):90-96, Spring 2017.
- NHTSA, “Automated Driving Systems: a vision for safety,” US Dept. of Transportation, DOT HS 812 442, Sept. 2017.
- Carson, B., “Uber’s self-driving cars hit 2 million miles as program regains momentum,” Forbes, Dec. 22, 2017.
- Waymo, “On the Road to Fully Self-Driving: Waymo safety report,” 2017, https://goo.gl/7HUiew.
- General Motors, “2018 Self-Driving Safety Report,” 2018, https://goo.gl/ruLJvV.
- SAE, “Automated Driving (from SAE J3016),” http://www.sae.org/misc/pdfs/automated_driving.pdf, accessed 10/13/2017.
- Wagner and Koopman, “A Philosophy for Developing Trust in Self-Driving Cars,” . In: Meyer G., Beiker S., editors. Road Vehicle Automation 2, Lecture Notes in Mobility. (Springer, 2015), 163-170.
- Road vehicles -- Functional Safety -- Management of functional safety, ISO 26262, 2011.
- Road vehicles - Safety of the Intended Functionality, ISO/WD PAS 21448. Under development.
- Salay, R., Queioz, R., & Czarnecki, K., “An analysis of ISO 26262: Using Machine Learning Safely in Automotive Software,” https://arxiv.org/pdf/1709.02435.pdf.
- Dosovitskiy, A., and T. Brox, “Inverting convolutional networks with convolutional networks,” CoRR, vol. abs/1506.02753, 2015.
- Koopman, P. and Wagner, M., “Challenges in Autonomous Vehicle Testing and Validation,” SAE Int. J. Trans. Safety 4(1):15-24, 2016, doi:10.4271/2016-01-0128.
- Urmson, C. et al., “Autonomous driving in urban environments: Boss and the Urban Challenge,” Journal of Field Robotics 425-466, 2008, doi:10.1002/rob.
- Levinson et al., “Towards fully autonomous driving: systems and algorithms,” IEEE Intelligent Vehicles Symp., June 5-9, 2011, pp. 163-168.
- Broggi et al., “Extensive tests of autonomous driving technologies,” IEEE Trans. Intelligent Transportation Systems 14(3):1403-1415, Sept. 2013.
- Ziegler, J. et al., “Making Bertha drive - an autonomous journey on a historic route,” IEEE Intelligent Transportation Systems Magazine, Summer 2014, pp. 8-20.
- Aeberhard, M. et al., “Experience, results and lessons learned from automated driving on Germany’s highways,” IEEE Intelligent Transportation Systems Magazine, Spring 2015, pp. 42-57.
- Kalra, N., and Paddock, S., Driving to Safety: how many miles of driving would it take to demonstrate autonomous vehicle reliability? Rand Corporation, RR-1479-RC, 2016.
- Butler and Finelli, “The infeasibility of experimental quantification of life-critical software reliability,” IEEE Trans. SW Engr. 19(1):3-12, Jan 1993.
- Madrigal, A., “Inside Waymo’s secret world for Training self-driving cars,” The Atlantic, Aug. 23, 2017.
- Ding, Z., “Accelerated evaluation of automated vehicles,” http://www-personal.umich.edu/~zhaoding/accelerated-evaluation.html on 10/15/2017.
- Golson, J., Tesla’s new autopilot will run in “shadow mode” to prove that it’s safer than human driving, The Verge, Oct, 19, 2016.
- Davies, A., The very human problem blocking the path to self-driving cars, Wired, Jan 1, 2017.
- Box, G., “Robustness in the strategy of scientific model building”, MRC Technical Summary Report #1954, University of Wisconsin-Madison, 1979.
- Putz, A., Zlocki, A., Bock, J., and Eckstein, L., “System validation of highly automated vehicles with a database of relevant traffic scenarios,” 12th ITS European Congress, Strasbourg, June 19-22, 2017.
- Bustcon, J., & Randell, B., (Eds.) Software Engineering Techniques: report on a conference sponsored by the NATO Science Committee, April 1970.
- Beizer, B., “Black-Box Testing: Techniques for functional testing of software and systems,” (Wiley, 1995).
- Zhou, N., “Volvo admits its self-driving cars are confused by kangaroos,” The Guardian, June 30, 2017. https://goo.gl/jgA7Ck.
- Koopman, P., “Challenges in Autonomous Vehicle Validation,” SCAV 17, April 2017.
- Kane, Chowdhury, Datta, and Koopman, “A Case Study on Runtime Monitoring of an Autonomous Research Vehicle (ARV) System,” RV 2015.
- Sargent, R., “Verifying and Validating Simulation Models,” 2014 Winter Simulation Conference, pp. 118-131.
- Law, A. and Kelton, W.D., “Simulation Modeling and Analysis,” 3rd Edition (McGraw Hill, 2000).
- Freedman, R., “Testability of software components,” IEEE Trans. Software Engineering 553-564, June 1991.
- Dragan, A., Lee, K., and Srinivasa, S., “Legibility and predictability of robot motion,” Human-Robot Interaction (HRI), 2013, pp. 301-308.
- Bojarski, M. et al., “VisualBackProp: efficient visualization of CNNs,” arXiv:1611.05418v3.
- Bojarski, M. et al., “End to End Learning for Self-Driving Cars,” arXiv:1604.07316v1.
- Wang, Y., Lin, Z., Shen, X., Cohen, S., and Cottrell, G., “Skeleton Key: image captioning by skeleton-attribute decomposition,” arXiv preprint arXiv:1704.06972.
- Redmon, J., and Farhadi, A., “YOLO9000: Better, Faster, Stronger,” https://arxiv.org/pdf/1612.08242.pdf.
- Morris, E., “The Certainty of Donald Rumsfeld (Part 2),” NY Times, 26 March 2014, https://goo.gl/Pv7SB7.
- Wang, R., Guiochet, J. & Motet, G., “Confidence assessment framework for safety arguments,” SAFECOMP, 2017, pp. 55-68.
- Casner, S., Hutchins, E., & Norman, D., “The Challenges of Partially Automated Driving,” Comm. ACM, May 2016, pp. 70-77.
- Leveson, “An investigation of the Therac-25 Accidents,” IEEE Computer 18-41, July 1993.
- Sullivan, M., and Chillarege, R., “Software Defects and their Impact on System Availability A Study of Field Failures in Operating Systems,” FTCS-21, 1991.
- Kalra, N. and Groves, D., “The Enemy of Good: estimating the cost of waiting for nearly perfect automated vehicles,” (Rand Corporation, RR-2150-RC, 2017).
- Burton, S., “Making the case for safety of machine learning in highly automated driving,” SAFECOMP, Sept. 2017, pp. 5-16.
- Kane, Fuhrman, Koopman, “Monitor Based Oracles for Cyber-Physical System Testing,” DSN 2014.