[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Performance optimization of autonomous driving control under end-to-end deadlines

  • Published:
Real-Time Systems Aims and scope Submit manuscript

Abstract

The rapid growth of autonomous driving in recent years has posed some new research challenges to the traditional vehicle control system. For example, in order to flexibly change the yaw rate and moving speed of a vehicle based on the detected road conditions, autonomous driving control often needs to dynamically tune its control parameters for better trajectory tracking and vehicle stability. Consequently, the execution time of driving control can increase significantly, resulting in missing the end-to-end (E2E) deadline from detection to computation and actuation, and thus possible accidents. In this paper, we propose AutoE2E, a two-tier real-time scheduling framework that helps the automotive OS meet the E2E deadlines of all the tasks despite execution time variations, while achieving the maximum possible computing precision for driving control. The inner loop of AutoE2E dynamically controls the CPU utilizations of all the on-board processors to stay below their respective schedulable utilization bounds, by adjusting the invocation rates of the vehicle control tasks running on those processors. The outer loop is designed to adapt the computation time of driving control and minimize the precision loss, when the inner loop loses its control capability due to rate saturation caused by vehicle speed changes. In particular, the outer loop features driver-oriented weight assignment and piecewise approximation for computing precision optimization of vehicle control tasks. Our evaluations, both on a hardware testbed with scaled cars and in larger-scale simulation, show that AutoE2E can effectively reduce the deadline miss ratio by 35.4% on average, compared to well-designed baselines, while having smaller precision loss and tracking errors.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Bai Y, Wang Z, Wang X, Wang J (2020) AutoE2E: end-to-end real-time middleware for autonomous driving control. In: IEEE international conference on distributed computing systems

  • Becker M, Dasari D, Mubeen S, Behnam M, Nolte T (2017) End-to-end timing analysis of cause-effect chains in automotive embedded systems. J Syst Arch 80:104–113

  • Biondi A, Melani A, Marinoni M, Di Natale M, Buttazzo G (2014) Exact interference of adaptive variable-rate tasks under fixed-priority scheduling. In: 2014 26th euromicro conference on real-time systems, pp 165–174. IEEE

  • Biondi A, Di Natale M, Buttazzo G (2016) Performance-driven design of engine control tasks. In: 2016 ACM/IEEE 7th international conference on cyber-physical systems (ICCPS), pp 1–10. IEEE

  • Buttazzo GC, Lipari G, Abeni L (1998) Elastic task model for adaptive rate control. In: RTSS

  • Buttazzo GC, Lipari G, Caccamo M, Abeni L (2002) Elastic scheduling for flexible workload management. IEEE Trans. Comput. 51(3):289–302

    Article  Google Scholar 

  • Buttazzo GC, Bini E, Buttle D (2014) Rate-adaptive tasks: model, analysis, and design issues. In: DATE

  • Chang W, Chakraborty S, et al (2016) Resource-aware automotive control systems design: a cyber-physical systems approach. Found Trends Electron Des Autom 10(4): 249–369

  • Chen YL (2016) A forward collision probability index based on the driving behavior. In: VTC-Fall

  • Chen Y, Lu C, Koutsoukos X (2007) Optimal discrete rate adaptation for distributed real-time systems. In: RTSS

  • Chen M, Nolan C, Wang X, Adhikari S, Li F, Qi H (2009) Hierarchical utilization control for real-time and resilient power grid. In: ECRTS

  • Davare A, Zhu Q, Di Natale M, Pinello C, Kanajan S, Sangiovanni-Vincentelli A (2007) Period optimization for hard real-time distributed automotive systems. In: DAC

  • Davis RI, Burns A, Bril RJ, Lukkien JJ (2007) Controller area network (can) schedulability analysis: refuted, revisited and revised. Real-Time Syst 35(3):239–272

  • Ebert C, Jones C (2009) Embedded software: facts, figures, and future. Computer 42(4):42–52

  • Explanation of application in-terfaces of the chassis do-main. https://www.autosar.org/fileadmin/user_upload/standards/classic/4-3/AUTOSAR_EXP_AIChassis.pdf

  • Feiertag N, Richter K, Nordlander J, Jonsson J (2009) A framework for end-to-end path delay calculation of automotive systems under different path semantics. In: RTSS

  • Feld T, Biondi A, Davis RI, Buttazzo G, Slomka F (2018) A survey of schedulability analysis techniques for rate-dependent tasks. J Syst Softw 138:100–107

    Article  Google Scholar 

  • Gill C, Orr J, Harris S (2018) Supporting graceful degradation through elasticity in mixed-criticality federated scheduling. In: Proceedings of 6th workshop on mixed criticality systems (WMC), RTSS, pp 19–24

  • Giogio C, Buttazzo EB, Buttle D (2014) Rate-adaptive tasks: model, analysis, and design issues. In: Design, automation test in Europe conference exhibition. IEEE

  • Girault A, Prévot C, Quinton S, Henia R, Sordon N (2018) Improving and estimating the precision of bounds on the worst-case latency of task chains. In: IEEE transactions on computer-aided design of integrated circuits and systems

  • Goodrich MT, Tamassia R (2006) Algorithm design: foundation, analysis and internet examples. Wiley, New York

  • Greco L, Fontanelli D, Bicchi A (2010) Design and stability analysis for anytime control via stochastic scheduling. In: IEEE transactions on automatic control

  • Kim JE, Rogalla O, Kramer S, Hamann A (2009) Extracting, specifying and predicting software system properties in component based real-time embedded software development. In: ICSE

  • Kim J, Lakshmanan K, Rajkumar R (2012) Rhythmic tasks: a new task model with continually varying periods for cyber-physical systems. In: 2012 IEEE/ACM third international conference on cyber-physical systems, pp 55–64. IEEE

  • Liu JWS (2000) Real-time systems. Prentice Hall, Hoboken

  • Liu CL, Layland JW (1973) Scheduling algorithms for multiprogramming in a hard-real-time environment. J ACM

  • Lu C, Wang X, Koutsoukos X (2004) End-to-end utilization control in distributed real-time systems. In: ICDCS

  • Lu C, Wang X, Koutsoukos X (2005) Feedback utilization control in distributed real-time systems with end-to-end tasks. In: IEEE transactions on parallel and distributed systems

  • Markkula, G, et al (2012) A review of near-collision driver behavior models. Hum Factors 54(6):1117–1143

  • Mattingley J, Boyd S (2012) Cvxgen: a code generator for embedded convex optimization. Optim Eng 13(1):1–27

    Article  MathSciNet  MATH  Google Scholar 

  • Mehmed A (2020) Runtime monitoring for safe automated driving systems. dissertation, Malardalen University. http://mdh.diva-portal.org/smash/get/diva2:1479230/FULLTEXT02.pdf

  • Orr J, Uribe JC, Gill C, Baruah S, Agrawal K, Dyke S, Prakash A, Bate I, Wong C, Adhikari S (2020) Elastic scheduling of parallel real-time tasks with discrete utilizations. In: Proceedings of the 28th international conference on real-time networks and systems, pp 117–127

  • Rajeev A, Mohalik S, Dixit MG, Chokshi DB, Ramesh S (2010) Schedulability and end-to-end latency in distributed ecu networks: modeling and precise estimation. In: EMSOFT

  • Schnelle S, et al (2018) A feedforward and feedback integrated lateral and longitudinal driver model for personalized advanced driver assistance systems. Mechatronics

  • Steere DC, Goel A, Gruenberg J, McNamee D, Pu C, Walpole J (1999) A feedback-driven proportion allocator for real-rate scheduling. In: OSDI

  • Svensson L (2021) Motion planning and control of automated vehicles in critical situations. dissertation, Kth Royal Institute of Technology. http://kth.diva-portal.org/smash/get/diva2:1554346/FULLTEXT01.pdf

  • Utkin, V, Lee, H (2006) Chattering problem in sliding mode control systems. In: VSS

  • Verma R, Del Vecchio D, Fathy HK (2008) Development of a scaled vehicle with longitudinal dynamics of an HMMWV for an its testbed. In: IEEE/ASME transactions on mechatronics

  • Wang Z, Wang J (2020) Personalized ground vehicle collision avoidance system: From a computational resource re-allocation perspective. In: 2020 IEEE intelligent vehicles symposium

  • Wang X, Jia D, Lu C, Koutsoukos X (2007) DEUCON: decentralized end-to-end utilization control for distributed real-time systems. IEEE Trans Parallel Distrib Syst 18(7): 996–1009

  • Wang X, Chen Y, Lu C, Koutsoukos XD (2009a) Towards controllable distributed real-time systems with feasible utilization control. IEEE Trans Comput 58(8):1095–1110

  • Wang X, Fu X, Liu X, Gu Z (2009b) Power-aware cpu utilization control for distributed systems. In: RTAS

  • Wang Z, Bai Y, Wang J, Wang X (2018) Parameter selection of an ltv-mpc controller for vehicle path tracking considering cpu computational load. In: ASME

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA

    Yunhao Bai & Xiaorui Wang

  2. Department of Computer and Information Science, IOTSC, University of Macau, Taipa, China

    Li Li

  3. Department of Mechanical Engineering, University of Texas at Austin, Austin, TX, USA

    Zejiang Wang & Junmin Wang

Authors
  1. Yunhao Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Li Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zejiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaorui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junmin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaorui Wang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bai, Y., Li, L., Wang, Z. et al. Performance optimization of autonomous driving control under end-to-end deadlines. Real-Time Syst 58, 509–547 (2022). https://doi.org/10.1007/s11241-022-09379-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11241-022-09379-6

Keywords

Search

Navigation