计算机科学

计算机科学 ›› 2021, Vol. 48 ›› Issue (11A): 147-153.doi: 10.11896/jsjkx.210300050

• 智能计算 • 上一篇    下一篇

基于吸收态马尔可夫链的智能无人车系统实时性能分析

吴培培1, 吴兆贤1, 唐文兵2   

  1. 1 浙江理工大学信息学院 杭州310018
    2 华东师范大学软件工程学院 上海200062
  • 出版日期:2021-11-10 发布日期:2021-11-12
  • 通讯作者: 吴培培(peipeiwu@126.com)
  • 基金资助:
    国家自然科学基金项目(61210004,61170015)

Real-time Performance Analysis of Intelligent Unmanned Vehicle System Based on Absorbing Markov Chain

WU Pei-pei1, WU Zhao-xian1, TANG Wen-bing2   

  1. 1 School of Information Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China
    2 Software Engineering Institute,East China Normal University,Shanghai 200062,China
  • Online:2021-11-10 Published:2021-11-12
  • About author:WU Pei-pei,born in 1994,postgra-duate.Her main research interests include intelligent information processing and intelligent software performance evaluation.
  • Supported by:
    National Natural Science Foundation of China(61210004,61170015).

PDF (PC)

529

摘要： 随着人工智能技术的进步和人机物融合系统的发展,智能无人车系统成为了新一代人工智能研究的前沿。智能无人车系统根据车辆和环境数据进行实时决策以控制无人车运行,因而该系统具有较高的实时性能要求,对系统实时性的分析是保障系统安全可靠的方法之一。为了对智能无人车系统的实时性能进行分析,以智能无人车变道系统为例,首先使用MARTE模型对智能无人车变道系统进行建模,在系统设计早期就引入性能需求参数;然后,通过模型转换将MARTE模型转化为吸收态马尔可夫链;最后,利用吸收态马尔可夫链的相关理论和公式综合估算了智能无人车系统的实时性能指标,并针对影响整个系统实时性的关键模块进行了分析。实验结果表明,文中所提模型和分析方法可以较好地分析智能无人车系统的实时性能。分析发现系统中智能模块的准确率与响应时间相互制约,在不同的运行场景下需要找到二者之间的平衡点以获得更优的实时性能。

关键词: MARTE模型, 实时性能分析, 吸收态马尔可夫链, 智能无人车系统

Abstract: With the advancements of artificial intelligence technology and the development of human-cyber-physical systems,intelligent unmanned vehicle systems are becoming the forefront of the new generation of artificial intelligence research.The intelligent unmanned vehicle system performs real-time decision based on vehicle and environmental data to control the unmanned vehicle.Therefore,the intelligent unmanned vehicle system has high real-time performance requirements.Analysis of the real-time performance of the system is one of the methods to ensure the safety and reliability of this kind of system.In order to analyze the real-time performance of the intelligent unmanned vehicle system,this paper takes the intelligent unmanned vehicle lane changing system as a scenario.First,the MARTE model is used to model the intelligent unmanned vehicle lane changing system,and the performance requirements parameters are added in the early system design.Then,through model transformation,the MARTE model is transformed into an absorption Markov chain.Finally,the relevant theories and formulas of the absorption Markov chain are used to comprehensively estimate the real-time performance indicators of the intelligent unmanned vehicle system,and analyze the key modules that affect the real-time performance of the entire system.The experimental results show that the model and analysis method proposed in the article can better analyze the real-time performance of the intelligent unmanned vehicle system.The analysis found that the accuracy and response time of the intelligent modules in the system restrict each other,and it is necessary to find a balance between the two in different operating scenarios to obtain better real-time performance.

Key words: Absorbing Markov chain, Intelligent unmanned vehicle system, MARTE model, Real-time performance analysis

中图分类号: 

  • TP242.6
[1]ZHANG T,LI Q,ZHANG C S,et al.Current trends in the development of intelligent unmanned autonomous systems[J].Frontiers of Information Technology&Electronic Engineering,2017,18(1):68-85.
[2]BALSAMO S,MARCO A D,INVERARDI P,et al.Model-based performance prediction in software development:a survey[J].IEEE Transactions on Software Engineering,2004,30(5):295-310.
[3]DENARO G,POLINI A,EMMERICH W.Early performancetesting of distributed software applications[C]//Proceedings of the 4th International Workshop on Software and Performance.2004:94-103.
[4]WOODSIDE M,PETRIU D C,MERSEGUER J,et al.Transformation challenges:from software models to performance models[J].Software & Systems Modeling,2014,13(4):1529-1552.
[5]QUADRI I,BAGNATO A,BROSSE E,et al.Modeling metho-dologies for Cyber-Physical Systems:Research field study on inherent and future challenges[J].Ada User Journal,2015,36(4):246-253.
[6]FAUGERE M,BOURBEAU T,DE SIMONE R,et al.Marte:Also an uml profile for modeling aadl applications[C]//12th IEEE International Conference on Engineering Complex Computer Systems (ICECCS 2007).IEEE,2007:359-364.
[7]BRUGALI D.Modeling and Analysis of safety requirements in robot navigation with an extension of UML MARTE[C]//2018 IEEE International Conference on Real-time Computing and Robotics (RCAR).IEEE,2018:439-444.
[8]XIA H,JIAO J,DONG J.Extend UML based timeliness mode-ling approach for complex system[C]//2018 International Conference on Mathematics,Modeling,Simulation and Statistics Application (MMSSA 2018).Atlantis Press,2019:1-6.
[9]BECKER S,KOZIOLEK H,REUSSNER R.Model-Based performance prediction with the palladio component model[C]//Proceedings of the 6th International Workshop on Software and Performance.ACM,2007:54-65.
[10]PETRIU D C,ALHAJ M,TAWHID R.Software performance modeling[C]//International School on Formal Methods for the Design of Computer,Communication and Software Systems.Berlin:Springer,2012:219-262.
[11]BALSAMO S,PERSONE VDN,INVERARDI P.A review on queueing network models with finite capacity queues for software architectures performance prediction[J].Performance Evaluation,2003,51(2/3/4):269-288.
[12]BALSAMO S,MARZOLLA M.Performance evaluation ofUML software architectures with multiclass queueing network models[C]//Proceedings of the 5th international workshop on Software and performance.2005:37-42.
[13]ARCAINI P,INVERSO O,TRUBIANIC.Automated model-based performance analysis of software product lines under uncertainty[J].Information and Software Technology,2020,127:106371.
[14]HU X,JIAO L,CHAI Y S.Transforming UML to GSPN for Performance Analysis[J].Computer Science,2016,43(11):49-54.
[15]SHAILESH T,NAYAK A,PRASAD D.An UML Based Performance Evaluation of Real-Time Systems Using Timed Petri Net[J].Computers,2020,9(4):94.
[16]GILMORE S,HILLSTON J,KLOUL L,et al.Software per-formance modelling using PEPA nets[J].ACM SIGSOFT Software Engineering Notes,2004,29(1):13-23.
[17]LV H,WANG H,ZHAO Q,et al.Modeling and Analysis of Self-Reflection Based on Continuous State-Space Approximation of PEPA[C]//2009 Eighth IEEE International Conference on Dependable,Autonomic and Secure Computing.IEEE,2009:84-89.
[18]SHIN J,SUNWOO M.Vehicle speed prediction using a Markov chain with speed constraints[J].IEEE Transactions on Intelligent Transportation Systems,2018,20(9):3201-3211.
[19]PEREZ J F,SILVA D F,GOEZ J C,et al.Algorithm 972:jMarkov:An integrated framework for Markov chain modeling[J].ACM Transactions on Mathematical Software (TOMS),2017,43(3):1-22.
[20]SHEPERO M,MUNKHAMMAR J.Spatial Markov chainmodel for electric vehicle charging in cities using geographical information system (GIS) data[J].Applied energy,2018,231:1089-1099.
[21]CHEN M,WANG T,OTA K,et al.Intelligent resource allocation management for vehicles network:An A3C learning approach[J].Computer Communications,2020,151:485-494.
[22]SU S,MUELLING K,DOLAN J,et al.Learning vehicle surrounding-aware lane-changing behavior from observed trajectories[C]//2018 IEEE Intelligent Vehicles Symposium (IV).IEEE,2018:1412-1417.
[23]BERTSEKAS D P,TSITSIKLIS J N.Introduction to probability[M].Belmont,MA:Athena Scientific,2002:339-380.
[24]CHAI Y S,ZHU X Y,YAN R J,et al.MARTE Models Based System Reliability Prediction[J].Computer Science,2015,42(12):82-86.
[25]BAUMS A,GORDYUSHIN A.Response time of a mobile robot[J].Automatic Control and Computer Sciences,2013,47(6):352-358.
[1] 柴叶生,朱雪阳,晏荣杰,张广泉.
基于MARTE模型的系统可靠性预测
MARTE Models Based System Reliability Prediction
计算机科学, 2015, 42(12): 82-86.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发