Interpretable Run-Time Monitoring and Replanning for Safe Autonomous Systems Operations

被引:6
|
作者
Di Franco, Carmelo [1 ,2 ,3 ]
Bezzo, Nicola [1 ,2 ,3 ]
机构
[1] Univ Virginia, Dept Syst Engn, Charlottesville, VA 22903 USA
[2] Univ Virginia, Dept Environm, Charlottesville, VA 22903 USA
[3] Univ Virginia, Dept Comp Engn, Charlottesville, VA 22903 USA
来源
IEEE ROBOTICS AND AUTOMATION LETTERS | 2020年 / 5卷 / 02期
关键词
Motion and path planning; aerial systems; applications; collision avoidance;
D O I
10.1109/LRA.2020.2972828
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Autonomous robots, especially aerial vehicles, when subject to disturbances, uncertainties, and noises may experience variations from their desired states and deviations from the planned trajectory which may lead them into an unsafe state (e.g., a collision). It is thus necessary to monitor their states at run-time when operating in uncertain and cluttered environments and intervene to guarantee their and the surrounding's safety. While Reachability Analysis (RA) has been successfully used to provide safety guarantees, it doesn't provide explanations on why a system is predicted to be unsafe and what type of corrective actions to perform to change the decision. In this work we propose a novel approach for run-time monitoring that leverages a library of previously observed trajectories together with decision tree theory to predict if the system will be safe/unsafe and provide an explanation to understand the causes of the prediction. We design an interpretable monitor that checks at run-time if the vehicle may become unsafe and plan safe corrective actions if found unsafe. For each prediction, we provide a logical explanation - a decision rule - that includes information about the causes that lead to the predicted safety decision. The explanation also includes a set of counterfactual rules that shows what system variables may bring the system to the opposite safety decision, if changed. We leverage such an explanation to plan corrective actions that always keep the vehicle safe. Our technique is validated both with simulations and experiments on a quadrotor UAV in cluttered environments under the effect of previously untrained disturbances.
引用
收藏
页码:2427 / 2434
页数:8
相关论文
共 50 条
  • [1] Fast Run-time Monitoring, Replanning, and Recovery for Safe Autonomous System Operations
    Yel, Esen
    Bezzo, Nicola
    2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 1661 - 1667
  • [2] Identifying Run-Time Monitoring Requirements for Autonomous Systems Through the Analysis of Safety Arguments
    Hawkins, Richard
    Conmy, Philippa Ryan
    COMPUTER SAFETY, RELIABILITY, AND SECURITY, SAFECOMP 2023, 2023, 14181 : 11 - 24
  • [3] A Reliable, Safe, and Secure Run-Time Platform for Cyber Physical Systems
    Lim, Sung-Soo
    Im, Eun-Jin
    Dutt, Nikil
    Lee, Kyung Woo
    Shin, Insik
    Lee, Chang-Gun
    Lee, Insup
    2013 IEEE SIXTH INTERNATIONAL CONFERENCE ON SERVICE-ORIENTED COMPUTING AND APPLICATIONS (SOCA), 2013, : 268 - 274
  • [4] Run-time monitoring for dependable systems: an approach and a case study
    Rota, SR
    de Almeida, JR
    23RD IEEE INTERNATIONAL SYMPOSIUM ON RELIABLE DISTRIBUTED SYSTEMS, PROCEEDINGS, 2004, : 41 - 49
  • [5] Rule systems for run-time monitoring: From EAGLE to RULER
    Barringer, Howard
    Rydeheard, David
    Havelund, Klaus
    RUNTIME VERIFICATION, 2007, 4839 : 111 - +
  • [6] Rule Systems for Run-time Monitoring: from EAGLE to RULER
    Barringer, Howard
    Rydeheard, David
    Havelund, Klaus
    JOURNAL OF LOGIC AND COMPUTATION, 2010, 20 (03) : 675 - 706
  • [7] Run-time monitoring of distributed applications
    Logean, X
    Dietrich, F
    Karamyan, H
    Koppenhöfer, S
    MIDDLEWARE'98: IFIP INTERNATIONAL CONFERENCE ON DISTRIBUTED SYSTEMS PLATFORMS AND OPEN DISTRIBUTED PROCESSING, 1998, : 459 - 474
  • [8] Run-Time Monitoring of Electronic Contracts
    Kyas, Marcel
    Prisacariu, Cristian
    Schneider, Gerardo
    AUTOMATED TECHNOLOGY FOR VERIFICATION AND ANALYSIS, PROCEEDINGS, 2008, 5311 : 397 - 407
  • [9] Integrated monitoring solution to start-up and run-time operations for continuous casting
    Zhang, Yale
    Dudzic, Michael
    Vaculik, Vit
    Annual Reviews in Control, 2003, 27 II : 141 - 149
  • [10] Foundations for the run-time monitoring of reactive systems - Fundamentals of the MaC language
    Viswanathan, M
    Kim, M
    THEORETICAL ASPECTS OF COMPUTING - ICTAC 2004, 2005, 3407 : 543 - 556