Verifiable Self-Certifying Autonomous Systems

Autonomous systems are increasingly being used in safety-and mission-critical domains, including aviation, manufacturing, healthcare and the automotive industry. Systems for such domains are often verified with respect to essential requirements set by a regulator, as part of a process called certification. In principle, autonomous systems can be deployed if they can be certified for use. However, certification is especially challenging as the condition of both the system and its environment will surely change, limiting the effective use of the system. In this paper we discuss the technological and regulatory background for such systems, and introduce an architectural framework that supports verifiably-correct dynamic self-certification by the system, potentially allowing deployed systems to operate more safely and effectively.

[1]  Sandra Bedaf,et al.  What Should a Robot do for you? - Evaluating the Needs of the Elderly in the UK , 2013, ACHI 2013.

[2]  Pieter van Dokkum,et al.  The nature of , 2006 .

[3]  Darren D. Cofer,et al.  DO-333 Certification Case Studies , 2014, NASA Formal Methods.

[4]  Stephan Merz,et al.  Model Checking , 2000 .

[5]  Alessio Lomuscio,et al.  Automatic verification of multi-agent systems by model checking via ordered binary decision diagrams , 2007, J. Appl. Log..

[6]  Michael Fisher,et al.  Generating Certification Evidence for Autonomous Unmanned Aircraft Using Model Checking and Simulation , 2014, J. Aerosp. Inf. Syst..

[7]  Wei Shyy,et al.  Encyclopedia of Aerospace Engineering, 9 Volume Set , 2010 .

[8]  Rajeev Alur,et al.  Counterexample-guided predicate abstraction of hybrid systems , 2006, Theor. Comput. Sci..

[9]  Anthony G. Pipe,et al.  Coverage-Driven Verification - An approach to verify code for robots that directly interact with humans , 2015, Haifa Verification Conference.

[10]  Kerstin Eder,et al.  A Corroborative Approach to Verification and Validation of Human–Robot Teams: Data from Simulations and Experiments , 2019 .

[11]  Costandinos Visvikis.  Evolution in electric vehicle safety legislation and global harmonisation activities , 2013, 2013 World Electric Vehicle Symposium and Exhibition (EVS27).

[12]  Bruce Edmonds,et al.  The insufficiency of formal design methods - the necessity of an experimental approach for the understanding and control of complex MAS , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[13]  Calin Belta,et al.  Time window temporal logic , 2017, Theor. Comput. Sci..

[14]  Michael Fisher,et al.  Practical verification of decision-making in agent-based autonomous systems , 2013, Automated Software Engineering.

[15]  Anneliese Andrews,et al.  Bridging the gap between testing and safety certification , 2018, 2018 IEEE Aerospace Conference.

[16]  Wamberto Weber Vasconcelos,et al.  Scrutable plan enactment via argumentation and natural language generation , 2014, AAMAS.

[17]  Ruth Breu,et al.  Arguing on Software-Level Verification Techniques Appropriateness , 2017, SAFECOMP.

[18]  David E. Kieras,et al.  The GOMS family of user interface analysis techniques: comparison and contrast , 1996, TCHI.

[19]  Joël Ouaknine,et al.  Recent Developments in FDR , 2012, CAV.

[20]  Fanny Dufossé,et al.  Specifying Safety Monitors for Autonomous Systems Using Model-Checking , 2014, SAFECOMP.

[21]  Rafael H. Bordini,et al.  Model checking agent programming languages , 2012, Automated Software Engineering.

[22]  Grigore Rosu,et al.  Rewriting-Based Techniques for Runtime Verification , 2005, Automated Software Engineering.

[23]  Christian Blum,et al.  Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection , 2014, TAROS.

[24]  Jérémie Guiochet,et al.  Safety-critical advanced robots: A survey , 2017, Robotics Auton. Syst..

[25]  Brian A. Weiss,et al.  Accuracy Degradation Analysis for Industrial Robot Systems , 2017 .

[26]  Michael Fisher,et al.  Certification of Safe and Trusted Robotic Inspection of Assets , 2018, 2018 Prognostics and System Health Management Conference (PHM-Chongqing).

[27]  Cynthia Breazeal,et al.  Social Robotics , 2016, Springer Handbook of Robotics, 2nd Ed..

[28]  Giuseppe Lami,et al.  Challenges in Certification of Autonomous Driving Systems , 2017, 2017 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW).

[29]  Barbara Gallina,et al.  Deriving verification-related means of compliance for a model-based testing process , 2016, 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC).

[30]  Brian A. Weiss,et al.  Quick positional health assessment for industrial robot prognostics and health management (PHM) , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[31]  Michael Anderson,et al.  Machine Ethics , 2011 .

[32]  Rafael Heitor Bordini,et al.  Verifying Multi-agent Programs by Model Checking , 2006, Autonomous Agents and Multi-Agent Systems.

[33]  Matthieu Roy,et al.  SMOF: A Safety Monitoring Framework for Autonomous Systems , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[34]  Michael Fisher,et al.  Formal verification of ethical choices in autonomous systems , 2016, Robotics Auton. Syst..

[35]  Klaus Havelund,et al.  A Tutorial on Runtime Verification , 2013, Engineering Dependable Software Systems.

[36]  Nick Hawes,et al.  Optimal Policy Generation for Partially Satisfiable Co-Safe LTL Specifications , 2015, IJCAI.

[37]  Maria Fox,et al.  PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains , 2003, J. Artif. Intell. Res..

[38]  Michael Fisher,et al.  Verifying autonomous systems , 2013, CACM.

[39]  Affan Shaukat,et al.  Reconfigurable Autonomy , 2014, KI - Künstliche Intelligenz.

[40]  Barbara Messing,et al.  An Introduction to MultiAgent Systems , 2002, Künstliche Intell..

[41]  Michael Pecht,et al.  Reliability Engineering , 2014 .