Functional Uncertainty in Real-Time Safety-Critical Systems
Pages 1 - 11
Abstract
Safety-critical cyber-physical systems increasingly use components that are unable to provide deterministic guarantees of the correctness of their functional outputs; rather, they characterize each outcome of a computation with an associated “uncertainty” regarding its correctness. The problem of assuring correctness in such systems is considered. A model is proposed in which components are characterized by bounds on the degree of uncertainty under both worst-case and typical circumstances; the objective is to assure safety under all circumstances while optimizing for performance for typical circumstances. A problem of selecting components for execution in order to obtain a result of a certain minimum uncertainty as soon as possible, while guaranteeing to do so within a specified deadline, is considered. An optimal semi-adaptive algorithm for solving this problem is derived. The scalability of this algorithm is investigated via simulation experiments comparing this semi-adaptive scheme with a purely static approach.
References
[1]
Aysegul Acar, Yakup Demir, and Cuneyt Guzelis. 2017. Object recognition and detection with deep learning for autonomous driving applications. SIMULATION 93, 9 (2017), 759–769.
[2]
Kunal Agrawal and Sanjoy Baruah. 2019. Adaptive Real-Time Routing in Polynomial Time. In Real-Time Systems Symposium (RTSS), 2019 IEEE.
[3]
Kunal Agrawal, Sanjoy Baruah, and Alan Burns. 2020. The Safe and Effective Use of Learning-Enabled Components in Safety-Critical Systems. In 2020 32nd Euromicro Conference on Real-Time Systems. Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik.
[4]
Sanjoy Baruah. 2018. Rapid routing with guaranteed delay bounds. In Real-Time Systems Symposium (RTSS), 2018 IEEE.
[5]
Sanjoy Baruah. 2021. Real-Time Scheduling of Multistage IDK-Cascades. In 2021 IEEE 24th International Symposium on Real-Time Distributed Computing (ISORC). 79–85. https://doi.org/10.1109/ISORC52013.2021.00021
[6]
Sanjoy Baruah, Alan Burns, and Yue Wu. 2021. Optimal Synthesis of IDK-Cascades. In Proceedings of the Twenty-Ninth International Conference on Real-Time and Network Systems(RTNS ’21). ACM, New York, NY, USA.
[7]
Peter Bishop, Robin Bloomfield, and Peter Adelard. 2002. Justifying the use of software of uncertain pedigree (SOUP) in safety related applications. In Proceedings of the 5th International Symposium Programmable Electronic Systems in Safety Related Applications.
[8]
Robin E. Bloomfield. 2001. Methods for assessing the safety integrity of safety-related software of uncertain pedigree (SOUP). Prepared by Adelard for the Health and Safety Executive (HSE), UK.
[9]
R. Calinescu, K. Johnson, and C. Paterson. 2016. FACT: A Probabilistic Model Checker for Formal Verification with Confidence Intervals. In Tools and Algorithms for the Construction and Analysis of Systems, Marsha Chechik and Jean-François Raskin (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 540–546.
[10]
Claudia D’Ambrosio, Fabio Furini, Michele Monaci, and Emiliano Traversi. 2018. On the Product Knapsack Problem. Optimization Letters 12, 4 (2018). https://doi.org/10.1007/s11590-017-1227-5
[11]
J. Fowers, K. Ovtcharov, M. Papamichael, T. Massengill, M. Liu, D. Lo, S. Alkalay, M. Haselman, L. Adams, M. Ghandi, S. Heil, P. Patel, A. Sapek, G. Weisz, L. Woods, S. Lanka, S. K. Reinhardt, A. M. Caulfield, E. S. Chung, and D. Burger. 2018. A Configurable Cloud-Scale DNN Processor for Real-Time AI. In Proc. ACM/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 1–14.
[12]
Y. Gal and Z. Ghahramani. 2016. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In Proc. of the 33rd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 48), Maria Florina Balcan and Kilian Q. Weinberger (Eds.). PMLR, New York, New York, USA, 1050–1059.
[13]
David Griffin, Iain Bate, and Robert I. Davis. 2020. Generating Utilization Vectors for the Systematic Evaluation of Schedulability Tests. In IEEE Real-Time Systems Symposium, RTSS 2020, Houston, Texas, USA. IEEE. http://eprints.whiterose.ac.uk/167646/
[14]
C. Guo, G. Pleiss, Y. Sun, and K.Q. Weinberger. 2017. On Calibration of Modern Neural Networks. In Proc. of the 34th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 70), Doina Precup and Yee Whye Teh (Eds.). PMLR, International Convention Centre, Sydney, Australia, 1321–1330.
[15]
David Harel, Assaf Marron, and Joseph Sifakis. 2019. Autonomics: In Search of a Foundation for Next Generation Autonomous Systems. arxiv:1911.07133 [cs.SE]
[16]
S. Heo, S. Cho, Y. Kim, and H. Kim. 2020. Real-Time Object Detection System with Multi-Path Neural Networks. In Proc. IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). 174–187.
[17]
Hanzhang Hu, Debadeepta Dey, Martial Hebert, and J. Andrew Bagnell. 2019. Learning Anytime Predictions in Neural Networks via Adaptive Loss Balancing. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019. AAAI Press, 3812–3821. https://doi.org/10.1609/aaai.v33i01.33013812
[18]
Wonseok Jang, Hansaem Jeong, Kyungtae Kang, Nikil Dutt, and Jong-Chan Kim. 2020. R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving. arxiv:2011.06372 [cs.CV]
[19]
Weiwen Jiang, Edwin H.-M. Sha, Xinyi Zhang, Lei Yang, Qingfeng Zhuge, Yiyu Shi, and Jingtong Hu. 2019. Achieving Super-Linear Speedup across Multi-FPGA for Real-Time DNN Inference. ACM Trans. Embed. Comput. Syst. 18, 5s, Article 67(2019), 23 pages.
[20]
A. Kendall, V. Badrinarayanan, and R. Cipolla. 2016. Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding. arxiv:1511.02680 [cs.CV]
[21]
F. Khani, M. Rinard, and P. Liang. 2016. Unanimous Prediction for 100% Precision with Application to Learning Semantic Mappings. In Association for Computational Linguistics (ACL).
[22]
B. Lakshminarayanan, A. Pritzel, and C. Blundell. 2017. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. arxiv:1612.01474 [stat.ML]
[23]
J. Lee, A. Prajogi, E. Rafalovsky, and P. Sarathy. 2016. Assuring Behavior of Autonomous UxV Systems. In S5: The Air Force Research Laboratory (AFRL) Safe and Secure Systems and Software Symposium.
[24]
S. Lee and S. Nirjon. 2020. SubFlow: A Dynamic Induced-Subgraph Strategy Toward Real-Time DNN Inference and Training. In Proc. IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). 15–29.
[25]
Xiaolong Ma, Fu-Ming Guo, Wei Niu, Xue Lin, Jian Tang, Kaisheng Ma, Bin Ren, and Yanzhi Wang. 2020. PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-Time Execution on Mobile Devices. Proc. of the AAAI Conference on Artificial Intelligence 34, 04(2020), 5117–5124.
[26]
Dr. Sandeep Neema. [n.d.]. Assurance for Autonomous Systems is Hard. https://www.darpa.mil/attachments/AssuredAutonomyProposersDay_Program Brief.pdf. Accessed: 2019-03-07.
[27]
Wei Niu, Xiaolong Ma, Sheng Lin, Shihao Wang, Xuehai Qian, Xue Lin, Yanzhi Wang, and Bin Ren. 2020. PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-Based Weight Pruning. In Proc. oTwenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). Association for Computing Machinery, 907–922.
[28]
M.E. Paoletti, J.M. Haut, J. Plaza, and A. Plaza. 2019. Deep learning classifiers for hyperspectral imaging: A review. ISPRS Journal of Photogrammetry and Remote Sensing 158 (2019), 279–317.
[29]
F. Pereira, T. Mitchell, and m. Botvinick. 2009. Machine learning classifiers and fMRI: – a tutorial overview. NeuroImage (2009), S199–S209.
[30]
Ulrich Pferschy, Joachim Schauer, and Clemens Thielen. 2019. The Product Knapsack Problem: Approximation and Complexity. arXiv.
[31]
Sophie Quinton, Matthias Hanke, and Rolf Ernst. 2012. Formal Analysis of Sporadic Overload in Real-time Systems. In Proceedings of the Conference on Design, Automation and Test in Europe (Dresden, Germany) (DATE ’12). EDA Consortium, San Jose, CA, USA, 515–520. http://dl.acm.org/citation.cfm?id=2492708.2492836
[32]
Joseph Sifakis. 2018. Autonomous Systems – An Architectural Characterization. arxiv:1811.10277 [cs.SY]
[33]
John A. Stankovic and Krithi Ramamritham. 1990. What is Predictability for Real-time Systems?Real-Time Syst. 2, 4 (Oct. 1990), 247–254. https://doi.org/10.1007/BF01995673
[34]
T. P. Trappenberg and A. D. Back. 2000. A classification scheme for applications with ambiguous data. In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium, Vol. 6. 296–301 vol.6.
[35]
Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, and Joseph E. Gonzalez. 2017. IDK Cascades: Fast Deep Learning by Learning not to Overthink. CoRR abs/1706.00885(2017). arxiv:1706.00885http://arxiv.org/abs/1706.00885
[36]
Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell, and Joseph E. Gonzalez. 2018. SkipNet: Learning Dynamic Routing in Convolutional Networks. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII(Lecture Notes in Computer Science, Vol. 11217), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 420–436. https://doi.org/10.1007/978-3-030-01261-8_25
[37]
P. Wei, L. Cagle, T. Reza, J. Ball, and J. Gafford. 2018. LiDAR and Camera Detection Fusion in a Real-Time Industrial Multi-Sensor Collision Avoidance System. Electronics 7, 6 (2018).
[38]
Y. Xiang and H. Kim. 2019. Pipelined Data-Parallel CPU/GPU Scheduling for Multi-DNN Real-Time Inference. In Proc. IEEE Real-Time Systems Symposium (RTSS). 392–405.
[39]
S. Yao, Y. Hao, Y. Zhao, H. Shao, D. Liu, S. Liu, T. Wang, J. Li, and T. Abdelzaher. 2020. Scheduling Real-time Deep Learning Services as Imprecise Computations. In Proc. IEEE 26th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA). 1–10.
[40]
York. 2021. Assuring autonomy international programme. https://www.york.ac.uk/assuring-autonomy/. Accessed: 2021-01-17.
[41]
J. Zhang, F. Li, H. Wu, and F. Ye. 2019. Autonomous Model Update Scheme for Deep Learning Based Network Traffic Classifiers. In Proc. IEEE Global Communications Conference (GLOBECOM). 1–6.
[42]
H. Zhou, S. Bateni, and C. Liu. 2018. S3DNN: Supervised Streaming and Scheduling for GPU-Accelerated Real-Time DNN Workloads. In Proc. IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS). 190–201.
Recommendations
Integrated safety analysis of software-controlled critical systems
Software for safety-critical systems must deal with the hazards identified by safety analysis in order to make the system safe, risk-free and fail-safe. Certain faults in critical systems can result in catastrophic consequences such as death, injury or ...
A Comparative Safety Assessment Approach for Safety Critical Systems
2018 Annual Reliability and Maintainability Symposium (RAMS)Safety critical systems are designed to be extremely safe. Accidents in safety critical systems rarely occur and hence are often inadequate to expose safety patterns nor to quantify the system's immediate safety performances. During system ...
The Quantitative Safety Assessment and Evaluation for Safety-Critical Computer Systems
The rapid increase in computer-related technologies puts greater demands on the software-controlled systems. These demands place the software in total control over safety-critical systems. A fault in such a Safety-Critical Computer Systems (SCCS) can ...
Comments
Information & Contributors
Information
Published In
June 2022
241 pages
ISBN:9781450396509
DOI:10.1145/3534879
Copyright © 2022 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 07 June 2022
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- National Science Foundation
Conference
RTNS 2022
RTNS 2022: The 30th International Conference on Real-Time Networks and Systems
June 7 - 8, 2022
Paris, France
Acceptance Rates
Overall Acceptance Rate 119 of 255 submissions, 47%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 516Total Downloads
- Downloads (Last 12 months)164
- Downloads (Last 6 weeks)15
Reflects downloads up to 25 Jan 2025
Other Metrics
Citations
Cited By
View allView Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in