A risk model for autonomous marine systems and operation focusing on human–autonomy collaboration

Abstract

Autonomous Marine Systems, such as autonomous ships and autonomous underwater vehicles (AUVs), gain increased interest in industry and academia. Expected benefits of AMS in comparison to conventional marine systems are reduced cost, reduced risk to operators, and increased efficiency of such systems. AUVs 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. AUVs 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 AUVs, in order to carry out a mission successfully. Risk models need to reflect these interactions. This article presents a Bayesian Belief Network (BBN) to assess the Human Autonomy Collaboration Performance (HAC), as part of a risk model for AUV operation. HAC 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 HAC can be improved in two ways; (i) through better training and inclusion of experienced operators, and (ii) through improved reliability of autonomous functions and situation awareness of vehicles. It is believed that the HAC BBN can improve AUV design and AUV operations by clarifying relationships between technical, human and organizational factors and their influence on mission risk. The article focuses on AUV, but the results should be applicable to other types of AMS.

Fuzzy System Dynamics Risk Analysis (FuSDRA) of Autonomous Underwater Vehicle Operations in the Antarctic

“…It may also be relevant to similar complex technological systems, such as the budding field of autonomous cars, unmanned aerial vehicles, and unmanned vessels. The commonalities that they share is the apparent lack of data and the potential for low probabilities and high consequences accidents (Ancel, Capristan, Foster, & Condotta, 2017;Pagallo, 2017;Thieme & Utne, 2017). The only foreseeable difference between application of the FuSDRA approach to AUV and other technological systems lies in the risk variables being considered.…”

Analysis of maritime transport accidents using Bayesian networks

“…6,11,[40][41][42][43] It is proved to be powerful to model maritime accidents since it enables quantitative analysis of human and organisational factors (HOFs). 33,44,45 It explicitly reveals probabilistic dependencies between factors and their causal relationships. Moreover, the feature that BN can take advantage of experts' knowledge makes it suitable for maritime risk modelling, in case of that failure data in the relevant investigations are incomplete.…”

Autonomous ships for container shipping in the Arctic routes

“…Meanwhile, interest and investment in autonomous ship technologies have also increased noticeably [28]. The catalyst for this dynamic is a prospective combination of reduced operational costs [29] and increased safety by reduced human involvement [30]. Increased safety [31] and positive environmental impact [32] are two of the primary benefits of autonomous shipping.…”