Autonomous marine systems, such as autonomous ships and autonomous underwater vehicles, gain increased interest in industry and academia. Expected benefits of autonomous marine system in comparison to conventional marine systems are reduced cost, reduced risk to operators, and increased efficiency of such systems. Autonomous underwater vehicles are applied in scientific, commercial, and military applications for surveys and inspections of the sea floor, the water column, marine structures, and objects of interest. Autonomous underwater vehicles are costly vehicles and may carry expensive payloads. Hence, risk models are needed to assess the mission success before a mission and adapt the mission plan if necessary. The operators prepare and interact with autonomous underwater vehicles to carry out a mission successfully. Risk models need to reflect these interactions. This article presents a Bayesian belief network to assess the human–autonomy collaboration performance, as part of a risk model for autonomous underwater vehicle operation. Human–autonomy collaboration represents the joint performance of the human operators in conjunction with an autonomous system to achieve a mission aim. A case study shows that the human–autonomy collaboration can be improved in two ways: (1) through better training and inclusion of experienced operators and (2) through improved reliability of autonomous functions and situation awareness of vehicles. It is believed that the human–autonomy collaboration Bayesian belief network can improve autonomous underwater vehicle design and autonomous underwater vehicle operations by clarifying relationships between technical, human, and organizational factors and their influence on mission risk. The article focuses on autonomous underwater vehicle, but the results should be applicable to other types of autonomous marine systems.
United States Department of the Navy. The Navy Unmanned Undersea Vehicle (UUV) master plan. Washington, DC: United States Department of the Navy, 2004.
2.
United States Department of the Navy. The Navy Unmanned Surface Vehicle (USV) master plan. 1st ed. Washington, DC: United States Department of the Navy, 2007.
3.
HuntsbergerTWoodwardG. Intelligent autonomy for unmanned surface and underwater vehicles. In: Proceedings of the OCEANS 2011, Kona, HI, 19–22 September 2011. New York: IEEE.
4.
MartinsRDe SousaJBCarvalho AfonsoCC. REP10 AUV: shallow water operations with heterogeneous autonomous vehicles. In: Proceedings of the OCEANS 2011 IEEE—Spain, Santander, 6–9 June 2011. New York: IEEE Computer Society.
5.
FariaMPintoJPyF. Coordinating UAVs and AUVs for oceanographic field experiments: challenges and lessons learned. In: Proceedings of the IEEE international conference on robotics and automation, Hong Kong, China, 31 May–7 June 2014, pp.6606–6611. New York: IEEE.
6.
BertramV. Autonomous ship technology -smart for sure, unmanned maybe. In: MorganG (ed.) Smart ship technology. London: The Royal Institute of Naval Architects, 2016, pp.5–112.
ManleyJE. Unmanned surface vehicles, 15 years of development. In: Proceedings of the OCEANS 2008, Quebec City, QC, Canada, 15–18 September 2008, vols 1–4, pp.1707–1710. New York: IEEE.
14.
YanRPangSSunH. Development and missions of unmanned surface vehicle. J Mar Sci Appl2010; 9: 451–457.
NiuHAdamsSLeeK. Applications of autonomous underwater vehicles in offshore petroleum industry environmental effects monitoring. J Can Petrol Technol2009; 48: 12–16.
17.
HaugenJImslandLLøsetS. Ice observer system for ice management operations. In: Proceedings of the 21st international offshore (Ocean) and polar engineering conference (eds ChungJSHongSYLangenI.), Maui, HI, 19–24 June 2011, pp.1120–1127. Cupertino, CA: ISOPE.
18.
GriffithsGBoseNFergusonJ. Insurance for autonomous underwater vehicles. Underwater Technol2007; 27: 43–48.
19.
HarrisCAPhillipsABDopico-GonzalezC. Risk and reliability modelling for multi-vehicle marine domains. In: Proceedings of the 2016 IEEE/OES autonomous underwater vehicles (AUV), Tokyo, Japan, 6–9 November 2016, pp.286–293. New York: IEEE.
20.
VagiaMTransethAAFjerdingenSA. A literature review on the levels of automation during the years. What are the different taxonomies that have been proposed?Appl Ergon2016; 53(part A): 190–202.
21.
InsaurraldeCCLaneDM. Autonomy-assessment criteria for underwater vehicles. In: Proceedings of the 2012 IEEE/OES autonomous underwater vehicles (AUV), Southampton, 24–27 September 2012, pp.1–8. New York: IEEE.
22.
WangYCLiuJG. Evaluation methods for the autonomy of unmanned systems. Chinese Sci Bull2012; 57: 3409–3418.
23.
KirkwoodWJ. AUV incidents and outcomes. In: Proceedings of the MTS/IEEE Biloxi—marine technology for our future: global and local challenges OCEANS 2009, Biloxi, MS, 26–29 October 2009, pp.1–5. New York: IEEE.
24.
BritoMPGriffithsG. A Markov chain state transition approach to establishing critical phases for AUV reliability. IEEE J Oceanic Eng2011; 36: 139–149.
25.
UtneIBSchjølbergI. A systematic approach to risk assessment: focusing on autonomous underwater vehicles and operations in Arctic areas. In: Proceedings of the ASME 2014 33rd international conference on ocean, offshore and arctic engineering, San Francisco, CA, 8–13 June 2014. New York: ASME.
26.
HoGPavlovicNArrabitoR. Human factors issues with operating unmanned underwater vehicles. Proc Hum Factors Ergon Soc Annu Meet2011; 55: 429–433.
27.
GriffithsGMillardNWMcPhailSD. On the reliability of the Autosub autonomous underwater vehicle. Underwater Technol2003; 25: 175–184.
28.
GriffithsGBritoM. Predicting risk in missions under sea ice with autonomous underwater vehicles. In: Proceedings of the 2008 IEEE/OES autonomous underwater vehicles (AUV 2008), Woods Hole, MA, 13–14 October 2008, pp.1–7. New York: IEEE.
29.
BritoMPGriffithsG. Results of expert judgments on the faults and risks with Autosub3 and an analysis of its campaign to Pine Island Bay, Antarctica, 2009. In: Proceedings of the international symposium on unmanned untethered submersible technology (UUST 2009), Durham, NH, 23–26 August 2009, p.14. Lee, NH: Autonomous Undersea Systems Institute (AUSI).
30.
BritoMPGriffithsGChallenorP. Risk analysis for autonomous underwater vehicle operations in extreme environments. Risk Anal2010; 30: 1771–1788.
31.
BritoMGriffithsG. A Bayesian approach for predicting risk of autonomous underwater vehicle loss during their missions. Reliab Eng Syst Safe2016; 146: 55–67.
32.
GriffithsGBritoMRobbinsI. Reliability of two REMUS-100 AUVs based on fault log analysis and elicited expert judgment. In: Proceedings of the international symposium on unmanned untethered submersible technology (UUST 2009), Durham, NH, 23–26 August 2009, p.12. Durham, NH: Autonomous Undersea Systems Institute (AUSI).
33.
RødsethØJTjoraÅ. A risk based approach to the design of unmanned ship control systems. In: EhlersSAsbjornslettBERødsethØJ. (eds) Maritime-port technology and development. Boca Raton, FL: CRC Press, 2014, pp.153–161.
34.
RødsethØJBurmeisterH-C. Risk assessment for an unmanned merchant ship. TransNav2015; 9: 357–364.
OnoMQuadrelliMHuntsbergerTL. Safe maritime autonomous path planning in a high sea state. In: Proceedings of the 2014 American control conference (ACC 2014), Portland, OR, 4–6 June 2014, pp.4727–4734. Piscataway, NJ: IEEE.
38.
LiZBachmayerRVardyA. Risk analysis of an autonomous surface craft for operation in harsh ocean environments. In: Proceedings of the 2016 IEEE/OES autonomous underwater vehicles (AUV 2016), Tokyo, Japan, 6–9 November 2016, pp.294–300. New York: IEEE.
39.
ThiemeCAUtneIBSchjølbergI. A risk management framework for unmanned underwater vehicles focusing on human and organizational factors. In: Proceedings of the ASME 2015 34th international conference on ocean, offshore and arctic engineering (OMAE2015), St. John’s, NL, Canada, 31 May–5 June 2015. New York: ASME.
40.
ThiemeCAUtneIBSchjølbergI. Risk modeling of autonomous underwater vehicle operation focusing on the human operator. In: Proceedings of the 25th European safety and reliability conference (ESREL 2015) (ed PodofilliniLSudretBStojadinovicB), Zürich, 7–10 September 2015, pp.3653–3660. Boca Raton, FL: CRC Press, Taylor & Francis Group.
41.
CummingsM. Man versus machine or man plus machine?IEEE Intell Syst2014; 29: 62–69.
42.
HollnagelE. Human reliability assessment in context. Nucl Eng Technol2005; 37: 159–166.
43.
KjærulffUBMadsenAL. Bayesian networks and influence diagrams: a guide to construction and analysis. 2nd ed.New York: Springer Science + Business Media, 2013.
44.
MartinsMRMaturanaMC. The application of the Bayesian networks in the human reliability analysis. In: Proceedings of the ASME 2009 international mechanical engineering congress and exposition, Lake Buena Vista, FL, 13–19 November 2009, pp.341–348. New York: IEEE.
45.
AkhtarMJUtneIB. Human fatigue’s effect on the risk of maritime groundings—a Bayesian network modeling approach. Safety Sci2014; 62: 427–440.
46.
MazaheriAMontewkaJKujalaP. Towards an evidence-based probabilistic risk model for ship-grounding accidents. Safety Sci2016; 86: 195–210.
47.
VinnemJEByeRGranBA. Risk modelling of maintenance work on major process equipment on offshore petroleum installations. J Loss Prevent Proc2012; 25: 274–292.
48.
GranBAByeRNyheimOM. Evaluation of the Risk OMT model for maintenance work on major offshore process equipment. J Loss Prevent Proc2012; 25: 582–593.
49.
TruccoPCagnoERuggeriF. A Bayesian belief network modelling of organisational factors in risk analysis: a case study in maritime transportation. Reliab Eng Syst Safe2008; 93: 845–856.
50.
JensenFVNielsenTD. Bayesian networks and decision graphs. New York: Springer Science & Business Media, 2009.
51.
Decision Systems Laboratory of the University of Pittsburgh. GeNIe modeling environment (GeNIe software 2.0). Pittsburgh, PA: University of Pittsburgh, 2013.
52.
McKendrickRShawTSaqerH. Team performance and communication within networked supervisory control human-machine systems. Proc Hum Factors Ergon Soc Annu Meet2011; 55: 262–266.
53.
ChenJYCBarnesMJHarper-SciariniM. Supervisory control of multiple robots: human-performance issues and user-interface design. IEEE T Syst Man Cy C2011; 41: 435–454.
54.
FouseSChampionMCookeNJ. The effects of vehicle number and function on performance and workload in human-robot teaming. Proc Hum Factors Ergon Soc Annu Meet2012; 56: 398–402.
55.
ParasuramanRMillerCA. Trust and etiquette in high-criticality automated systems. Commun ACM2004; 47: 51–55.
WienerELCurryRE. Flight-deck automation: promises and problems. Ergonomics1980; 23: 995–1011.
59.
JohnsonRCSaboeKNPrewettMS. Autonomy and automation reliability in human-robot interaction: a qualitative review. In: Proceedings of the 53rd human factors and ergonomics society annual meeting 2009 (HFES 2009), San Antonio, TX, 19–23 October 2009, pp.1398–1402. Santa Monica, CA: Human Factors an Ergonomics Society.
60.
GanderPHartleyLPowellD. Fatigue risk management: organizational factors at the regulatory and industry/company level. Accident Anal Prev2011; 43: 573–590.
61.
FincannonTJentschFSellersB. Best practices in human operation of robotic/unmanned vehicles: a technical review of recommendations regarding the human-to-robot ratio. In: Proceedings of the 57th human factors and ergonomics society annual meeting (HFES 2013), San Diego, CA, 30 September–4 October 2013, pp.1268–1272. Santa Monica, CA: Human Factors an Ergonomics Society.
62.
De VisserEShawTMohamed-AmeenA. Modeling human-automation team performance in networked systems: individual differences in working memory count. Proc Hum Factors Ergon Soc Annu Meet2010; 54: 1087–1091.
63.
BaxterGDBassEJ. Human error revisited: some lessons for situation awareness. In: Proceedings of the 1998 4th annual symposium on human interaction with complex systems, Dayton, OH, 22–25 March 1998, pp.81–87. New York: IEEE.
64.
RuffHANarayananSDraperMH. Human interaction with levels of automation and decision-aid fidelity in the supervisory control of multiple simulated unmanned air vehicles. Presence: Teleop Virt2002; 11: 335–351.
65.
LeeJDSeeKA. Trust in automation: designing for appropriate reliance. Hum Factors2004; 46: 50–80.
66.
EndsleyMRKaberDB. Level of automation effects on performance, situation awareness and workload in a dynamic control task. Ergonomics1999; 42: 462–492.
67.
SchusterDJentschFFincannonT. The impact of type and level of automation on situation awareness and performance in human-robot interaction. In: HarrisD (ed.) Engineering psychology and cognitive ergonomics understanding human cognition. Berlin; Heidelberg: Springer, 2013, pp.252–260.
68.
GrothKMSwilerLP. Bridging the gap between HRA research and HRA practice: a Bayesian network version of SPAR-H. Reliab Eng Syst Safe2013; 115: 33–42.
69.
GarciaJCFernandezJJSanzPJ. Increasing autonomy within underwater intervention scenarios: the user interface approach. In: Proceedings of the 2010 4th annual IEEE systems conference, San Diego, CA, 5–8 April 2010, pp.71–75. New York: IEEE.
70.
DonmezBNehmeCCummingsML. Modeling workload impact in multiple unmanned vehicle supervisory control. IEEE T Syst Man Cy A2010; 40: 1180–1190.
71.
SquirePNParasuramanR. Effects of automation and task load on task switching during human supervision of multiple semi-autonomous robots in a dynamic environment. Ergonomics2010; 53: 951–961.
72.
OakleyBMoulouaMHancockP. Effects of automation reliability on human monitoring performance. Proc Hum Factors Ergon Soc Annu Meet2003; 47: 188–190.
73.
CummingsMLClareAHartC. The role of human-automation consensus in multiple unmanned vehicle scheduling. Hum Factors2010; 52: 17–27.
74.
CummingsMLBertucelliLFMacbethJ. Task versus vehicle-based control paradigms in multiple unmanned vehicle supervision by a single operator. IEEE T Hum-Mach Syst2014; 44: 353–361.
75.
GieseSCarrDChahlJ. Implications for unmanned systems research of military UAV mishap statistics. In: Proceedings of the IEEE intelligent vehicles symposium, Gold Coast, QLD, Australia, 23–26 June 2013, pp.1191–1196. New York: IEEE.
76.
EndsleyMR. Toward a theory of situation awareness in dynamic-systems. Hum Factors1995; 37: 32–64.
77.
GehrkeJD. Evaluating situation awareness of autonomous systems. In: MadhavanRTunstelEMessinaE (eds) Performance evaluation and benchmarking of intelligent systems. New York: Springer, 2009, pp.93–111.
78.
RileyV. A general model of mixed-initiative human-machine systems. In: Proceedings of the human factors society 33rd annual meeting perspectives, Denver, CO, 16–20 October 1989, pp.124–128. Santa Monica, CA: Human Factors Society.
79.
HanninenM. Bayesian networks for maritime traffic accident prevention: benefits and challenges. Accident Anal Prev2014; 73: 305–312.
80.
MkrtchyanLPodofilliniLDangVN. A survey of Bayesian belief network applications in human reliability analysis. In: NowakowskiTMłyńczakMJodejko-PietruczukA. (eds) Safety and reliability: methodology and applications—proceedings of the European safety and reliability conference (ESREL 2014). Boca Raton, FL: CRC Press, 2015, pp.1073–1081.
81.
GertmanDBlackmanHMarbleJ. The SPAR-H human-reliability analysis method. NUREG/CR-6883, August2005. Washington, DC: NUREG, U.S. Nuclear Regulatory Commission.
82.
StruttJE. Report of the inquiry into the loss of Autosub2 under the Fimbulisen. Southampton: National Oceanography Centre Southampton, 2006.
83.
MkrtchyanLPodofilliniLDangVN. Overview of methods to build conditional probability tables with partial expert information for Bayesian belief networks. In: PodofilliniLSudretBStojadinovicB. (eds) Safety and reliability of complex engineered systems—proceedings of the 25th European safety and reliability conference (ESREL 2015). Boca Raton, FL: CRC Press, 2015, pp.1973–1981.
84.
PitchforthJMengersenK. A proposed validation framework for expert elicited Bayesian Networks. Expert Syst Appl2013; 40: 162–167.
85.
PitchforthJWuPMengersenK. Applying a validation framework to a working airport terminal model. Expert Syst Appl2014; 41: 4388–4400.
86.
The Applied Underwater Robotics Laboratory (AUR Lab), 2015, http://www.ntnu.edu/aur-lab (accessed 2 February 2015).
87.
ThiemeCA. Development of a risk management process for NTNU’s REMUS 100 AUV. Master’s Thesis, Department of Marine Technology, Norwegian University of Science and Technology, Trondheim, 2014, p.105.
HoGPavlovicNJArrabitoR. Human factors issues when operating unmanned underwater vehicles. Ottawa, ON, Canada: Defence R&D Canada, 2011.
91.
ParasuramanRWickensCD. Humans: still vital after all these years of automation. Hum Factors2008; 50: 511–520.
92.
ThiemeCAUtneIB. Safety performance monitoring of autonomous marine systems. Reliab Eng Syst Safe2017; 159: 264–275.
93.
HartSGStavelandLE. Development of NASA-TLX (Task Load Index): results of empirical and theoretical research. In: HancockPAMeshkatiN (eds) Human mental workload. Amsterdam: Elsevier, 1988, pp.139–183.
94.
KozineI. Simulation of human performance in time-pressured scenarios. Proc IMechE, Part O: J Risk and Reliability2007; 221: 141–151.
