A Bayesian Approach to Supervisory Risk Control of AUVs Applied to Under-Ice Operations

Abstract

Autonomous underwater vehicles (AUVs) are efficient sensor-carrying platforms for mapping and monitoring undersea ice. However, under-ice operations impose demanding requirements to the system, as it must deal with uncertain and unstructured environments, harsh environmental conditions, and reduced capabilities of the navigational sensors. This paper proposes a Bayesian approach to supervisory risk control, with the objective of providing risk management capabilities to the control system. First, an altitude guidance law for following a contour of an ice surface via pitch control using measurements from a Doppler velocity log (DVL) is proposed. Furthermore, a Bayesian network (BN) for probabilistic reasoning over the current state of risk during the operation is developed. This is then extended to a decision network (DN) for autonomously adapting the behavior of the AUV in order to maximize the mission utility, subject to a constraint on the predicted risk from the risk model. The vehicle is thus able to autonomously adapt its behavior in response to its current belief about the risk. The goal of this work is to improve the AUV performance and likelihood of mission success. Results from a simulation study are presented in order to demonstrate the performance of the proposed method.

Supervisory Risk Control with Application to Industrial Drone Inspection

“…The contribution of this article is to further develop the method proposed in [2], and to apply and experimentally test it on an industrial inspection drone case study. This work extends the methods proposed in [2], [27], [28] by modeling the relationship between causal factors and the available measurements, and by extending the BBN used in these works to a Dynamic Decision Network (DDN). These changes enable the system to identify the state of causal factors by combining information from different measurements over time, thereby increasing the situation awareness of the system.…”

“…Both [27] and [28] continue the work in [2] by developing supervisory risk controllers for different case studies with the proposed method. [27] controls the machinery mode of a MASS by considering, amongst others, the risk evaluated with a BBN during operation.…”

“…Their work uses an STPA as the basis for making the BBN, as in [2], but extends the method to also consider consequences. [28] uses the same general idea but uses a hazard identification (HAZID) as the basis for making the BBN instead. The resulting supervisory risk controller decides on an adequate distance to the ice sheet for under-ice autonomous underwater vehicle operations.…”

A Bayesian Approach to Risk-Based Autonomy for a Robotic System Executing a Sequence of Independent Tasks

“…The ability to proactively avoid failures (R4) has been demonstrated by Bremnes et al [20]. They use a Bayesian belief network (BBN) to evaluate the collision risk during an under-ice operation with an autonomous underwater vehicle.…”

“…Nevertheless, the previously presented literature demonstrates that Bayesian methods are a promising tool for achieving this article's goal. Using risk for making decisions during operation was shown in [20], [21] to be a feasible approach. This further strengthens the case for Bayesian models, such as BBN, DBN (the dynamic counterpart of BBNs), and DDN (DBNs that include the decisions made by the system), as these model probabilistic relationships making them suitable to model risk [24].…”