Abstract
Autonomous systems such as “self-driving” vehicles and closed-loop medical devices increasingly rely on learning-enabled components such as neural networks to perform safety critical perception and control tasks. As a result, the problem of verifying that these systems operate correctly is of the utmost importance. We will briefly examine the role of neural networks in the design and implementation of autonomous systems, and how various verification approaches can contribute towards engineering verified autonomous systems. In doing so, we examine promising initial solutions that have been proposed over the past three years and the big challenges that remain to be tackled.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abadi, M., Agarwal, A., Barham, P., et al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/
Alshiekh, M., Bloem, R., Ehlers, R., Könighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding (2018). https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/17211
Shih, A., Darwiche, A., Choi, A.: Verifying binarized neural networks by local automaton learning (2019). http://reasoning.cs.ucla.edu/fetch.php?id=193&type=pdf
Annpureddy, Y., Liu, C., Fainekos, G., Sankaranarayanan, S.: S-TaLiRo: a tool for temporal logic falsification for hybrid systems. In: Abdulla, P.A., Leino, K.R.M. (eds.) TACAS 2011. LNCS, vol. 6605, pp. 254–257. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-19835-9_21
Bojarski, M., et al.: End to end learning for self-driving cars. CoRR abs/1604.07316 (2016). http://arxiv.org/abs/1604.07316
Chen, X., Ábrahám, E., Sankaranarayanan, S.: Flow*: an analyzer for non-linear hybrid systems. In: Sharygina, N., Veith, H. (eds.) CAV 2013. LNCS, vol. 8044, pp. 258–263. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39799-8_18
Chen, X., Sankaranarayanan, S.: Model-predictive real-time monitoring of linear systems. In: IEEE Real-Time Systems Symposium (RTSS), pp. 297–306. IEEE Press (2017)
Cheng, C., Nührenberg, G., Ruess, H.: Maximum resilience of artificial neural networks. CoRR abs/1705.01040 (2017). http://arxiv.org/abs/1705.01040
Cheng, C., Nührenberg, G., Ruess, H.: Verification of binarized neural networks. CoRR abs/1710.03107 (2017). http://arxiv.org/abs/1710.03107
Cousot, P., Cousot, R.: Abstract interpretation: a unified lattice model for static analysis of programs by construction or approximation of fixpoints. In: ACM Principles of Programming Languages, pp. 238–252 (1977)
Cybenko, G.: Approximation by superpositions of a sigmoidal function. Math. Sig. Syst. 2, 303–314 (1989)
Dreossi, T., Donzé, A., Seshia, S.A.: Compositional falsification of cyber-physical systems with machine learning components. In: Barrett, C., Davies, M., Kahsai, T. (eds.) NFM 2017. LNCS, vol. 10227, pp. 357–372. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-57288-8_26
Dutta, S., Chen, X., Sankaranarayanan, S.: Reachability analysis for neural feedback systems using regressive polynomial rule inference. In: Proceedings of the Hybrid Systems: Computation and Control (HSCC), HSCC 2019, pp. 157–168. ACM, New York (2019)
Dutta, S., Kushner, T., Sankaranarayanan, S.: Robust data-driven control of artificial pancreas systems using neural networks. In: Češka, M., Šafránek, D. (eds.) CMSB 2018. LNCS, vol. 11095, pp. 183–202. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99429-1_11
Fremont, D.J., Dreossi, T., Ghosh, S., Yue, X., Sangiovanni-Vincentelli, A.L., Seshia, S.A.: Scenic: a language for scenario specification and scene generation. In: Proceedings of the ACM Programming Language Design and Implementation (PLDI), pp. 63–78 (2019)
Gehr, T., Mirman, M., Drachsler-Cohen, D., Tsankov, P., Chaudhuri, S., Vechev, M.: Ai2: safety and robustness certification of neural networks with abstract interpretation. In: 2018 IEEE Symposium on Security and Privacy (SP), pp. 3–18, May 2018
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The Kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354–3361, June 2012
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http://www.deeplearningbook.org
Hashimoto, D.A., Rosman, G., Rus, D., Meireles, O.: Artificial intelligence in surgery: promises and perils. Ann. Surg. 268, 70–76 (2018)
Huang, C., Fan, J., Li, W., Chen, X., Zhu, Q.: Reachnn: reachability analysis of neural-network controlled systems. CoRR abs/1906.10654 (2019). http://arxiv.org/abs/1906.10654
Ivanov, R., Weimer, J., Alur, R., Pappas, G.J., Lee, I.: Verisig: verifying safety properties of hybrid systems with neural network controllers. In: Proceedings of the Hybrid Systems: Computation and Control (HSCC), HSCC 2019, pp. 169–178. ACM, New York (2019)
LeCun, Y., Kavukcuoglu, K., Farabet, C.: Convolutional networks and applications in vision. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 253–256, May 2010. https://doi.org/10.1109/ISCAS.2010.5537907
Narodytska, N., Kasiviswanathan, S.P., Ryzhyk, L., Sagiv, M., Walsh, T.: Verifying properties of binarized deep neural networks. CoRR abs/1709.06662 (2017). http://arxiv.org/abs/1709.06662
Nielson, F., Nielson, H.R., Hankin, C.: Principles of Program Analysis. Springer, Heidelberg (1999). https://doi.org/10.1007/978-3-662-03811-6
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Workshop on Automatic Differentiation (2017). https://openreview.net/forum?id=BJJsrmfCZ
Prajna, S., Jadbabaie, A.: Safety verification using barrier certificates. In: Proceedings of the HSCC 2004, vol. 2993, pp. 477–492 (2004)
Sha, L.: Using simplicity to control complexity. IEEE Softw. 18(4), 20–28 (2001)
Sun, X., Khedr, H., Shoukry, Y.: Formal verification of neural network controlled autonomous systems. In: Proceedings of the Hybrid Systems: Computation and Control (HSCC), HSCC 2019, pp. 147–156. ACM, New York (2019)
Tuncali, C.E., Fainekos, G., Ito, H., Kapinski, J.: Simulation-based adversarial test generation for autonomous vehicles with machine learning components. In: 2018 IEEE Intelligent Vehicles Symposium, pp. 1555–1562 (2018)
Tuncali, C.E., Kapinski, J., Ito, H., Deshmukh, J.V.: Reasoning about safety of learning-enabled components in autonomous cyber-physical systems. In: Proceedings of the Design Automation Conference, DAC 2018, pp. 30:1–30:6 (2018)
U.S Food and Drug Administration: Computer-assisted surgical systems (2019). https://www.fda.gov/medical-devices/surgery-devices/computer-assisted-surgical-systems. Accessed July 2019
Wang, S., Chen, Y., Abdou, A., Jana, S.: Mixtrain: scalable training of formally robust neural networks. CoRR abs/1811.02625 (2018). http://arxiv.org/abs/1811.02625
Wang, S., Pei, K., Whitehouse, J., Yang, J., Jana, S.: Formal security analysis of neural networks using symbolic intervals. CoRR abs/1804.10829 (2018). http://arxiv.org/abs/1804.10829
Wong, E., Kolter, J.Z.: Provable defenses against adversarial examples via the convex outer adversarial polytope. In: Proceedings of the International Conference on Machine Learning, ICML, pp. 5283–5292 (2018). http://proceedings.mlr.press/v80/wong18a.html
Xiang, W., Tran, H., Johnson, T.T.: Reachable set computation and safety verification for neural networks with relu activations. CoRR abs/1712.08163 (2017). http://arxiv.org/abs/1712.08163
Xiang, W., Tran, H.D., Johnson, T.T.: Reachable set computation and safety verification for neural networks with relu activations (2107). https://arxiv.org/pdf/1712.08163.pdf. Posted on arxiv December 2017
Xiang, W., Tran, H.D., Rosenfeld, J.A., Johnson, T.T.: Reachable set estimation and verification for a class of piecewise linear systems with neural network controllers (2018). To Appear in the American Control Conference (ACC), invited session on Formal Methods in Controller Synthesis
Yaghoubi, S., Fainekos, G.: Gray-box adversarial testing for control systems with machine learning components. In: Proceedings of Hybrid Systems: Computation and Control, pp. 179–184 (2019)
Yoon, H., Chou, Y., Chen, X., Frew, E., Sankaranarayanan, S.: Predictive runtime monitoring for linear stochastic systems and applications to geofence enforcement for UAVs (2019). In: Proceedings of the Runtime Verification 2019, October 2019 (to appear)
Zhu, H., Xiong, Z., Magill, S., Jagannathan, S.: An inductive synthesis framework for verifiable reinforcement learning. In: ACM Programming Language Design and Implementation (PLDI), pp. 686–701 (2019)
Acknowledgments
This work was supported in part by the Air Force Research Laboratory (AFRL) and by the US NSF under Award # 1646556.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sankaranarayanan, S., Dutta, S., Mover, S. (2019). Reaching Out Towards Fully Verified Autonomous Systems. In: Filiot, E., Jungers, R., Potapov, I. (eds) Reachability Problems. RP 2019. Lecture Notes in Computer Science(), vol 11674. Springer, Cham. https://doi.org/10.1007/978-3-030-30806-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-30806-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30805-6
Online ISBN: 978-3-030-30806-3
eBook Packages: Computer ScienceComputer Science (R0)