A Formal Model of Train Control with AI-Based Obstacle Detection

被引：1
|
作者：
Gruteser, Jan [1 ]
Gelessus, David [1 ]
Leuschel, Michael [1 ]
Rossbach, Jan [1 ]
Vu, Fabian [1 ]
机构：
[1] Univ Dusseldorf, Inst Informat, Univ Str 1, D-40225 Dusseldorf, Germany
来源：
RELIABILITY, SAFETY, AND SECURITY OF RAILWAY SYSTEMS, RSSRAIL 2023 | 2023年 / 14198卷
关键词：
Railway System; AI; B method; Validation; Verification;
D O I：
10.1007/978-3-031-43366-5_8
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
The research project KI-LOK aims to develop a certification methodology for incorporating AI components into rail vehicles. In this work, we study how to safely incorporate an AI for obstacle detection into an ATO (automatic train operation) system for shunting movements. To analyse the safety of our system we present a formal B model comprising the steering and AI perceptions subsystems as well as the shunting yard environment. Classical model checking is applied to ensure that the complete system is safe under certain assumptions. We use SIMB to simulate various scenarios and estimate the likelihood of certain errors when the AI makes mistakes.
引用
收藏
页码：128 / 145
页数：18
相关论文
共 50 条
  • [1] AI-Based Security Surveillance and Hazard Detection for Train Platform Safety
    Serna, Alvaro Aparicio
    Yu, Xinrui
    Saniie, Jafar
    2024 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY, EIT 2024, 2024, : 185 - 190
  • [2] AI-BASED MEASUREMENT AND CONTROL
    不详
    IEEE EXPERT-INTELLIGENT SYSTEMS & THEIR APPLICATIONS, 1992, 7 (01): : 71 - 72
  • [3] Automated ai-based leak detection
    Dierolf C.
    Sauer A.
    WT Werkstattstechnik, 2021, 111 (03): : 152 - 158
  • [4] AI-Based Cancer Detection Model for Contrast-Enhanced Mammography
    Jailin, Clement
    Mohamed, Sara
    Iordache, Razvan
    De Carvalho, Pablo Milioni
    Ahmed, Salwa Yehia
    Sattar, Engy Abdullah Abdel
    Moustafa, Amr Farouk Ibrahim
    Gomaa, Mohammed Mohammed
    Kamal, Rashaa Mohammed
    Vancamberg, Laurence
    BIOENGINEERING-BASEL, 2023, 10 (08):
  • [5] Explainable AI-based innovative hybrid ensemble model for intrusion detection
    Ahmed, Usman
    Jiangbin, Zheng
    Almogren, Ahmad
    Khan, Sheharyar
    Sadiq, Muhammad Tariq
    Altameem, Ayman
    Rehman, Ateeq Ur
    Journal of Cloud Computing, 2024, 13 (01)
  • [6] Formal Verification for Safe AI-based Flight Planning for UAVs
    Bouchekir, R.
    Guzman, M.
    Cook, A.
    Haindl, J.
    Woolnough, R.
    2023 53RD ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS WORKSHOPS, DSN-W, 2023, : 275 - 282
  • [7] AI-based Cavitation Detection in Process Valves
    Ehemann, Marisa
    Trankle, Frank
    Stache, Nicolaj C.
    2023 IEEE 21ST INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS, INDIN, 2023,
  • [8] AI-Based Ransomware Detection: A Comprehensive Review
    Ferdous, Jannatul
    Islam, Rafiqul
    Mahboubi, Arash
    Zahidul Islam, Md
    IEEE Access, 2024, 12 : 136666 - 136695
  • [9] AI-BASED HAZARD DETECTION FOR RAILWAY CROSSINGS
    Espinoza, Darren
    Ali, Gasser Galal
    Tarawneh, Constantine
    PROCEEDINGS OF 2024 JOINT RAIL CONFERENCE, JRC, 2024,
  • [10] Case Study: AI-Based Autonomous Control
    Kanokogi, Hiroaki
    InTech, 2022, 69 (05) : 23 - 25
12345