scholarly journals Intention modelling and inference for autonomous collision avoidance at sea

2021 ◽  
Author(s):  
Sverre Velten Rothmund ◽  
Trym Tengesdal ◽  
Edmund Førland Brekke ◽  
Tor Arne Johansen
Keyword(s):  
Bayesian Network ◽  
Real Time ◽  
Collision Avoidance ◽  
Probability Distributions ◽  
Dynamic Bayesian Network ◽  
Current Situation ◽  
Time Behavior ◽  
Behavioral Rules ◽  
Autonomous Ship ◽  
Traffic Rules

The open wording of the traffic rules of the sea, COLREGS, and the existence of unwritten rules, make it essential for an autonomous ship to understand the intentions of meeting traffic. This article uses a dynamic Bayesian network (DBN) to model and infer the intentions of other ships based on their observed real-time behavior. Multiple intention nodes are included to describe the different ways a ship can interpret and conflict with the behavioral rules outlined in CORLEGS. The prior distributions of the intention nodes are adapted to the current situation based on observable characteristics such as location and relative ship size. When a new observation is made, the probability distributions of the intention variables are updated by excluding all combinations of intention states that conflict with the observed behavior. This way of modeling makes the intention probabilities independent of how often observations are made. The resulting model is able to identify situations that are prone to cause misunderstandings and infer the state of multiple intention variables that describe the behavior. Different collision avoidance algorithms can use the resulting intention information to better know if, when, and how to act.

scholarly journals Intention modelling and inference for autonomous collision avoidance at sea

2021 ◽  
Author(s):  
Sverre Velten Rothmund ◽  
Trym Tengesdal ◽  
Edmund Førland Brekke ◽  
Tor Arne Johansen
Keyword(s):  
Bayesian Network ◽  
Real Time ◽  
Collision Avoidance ◽  
Probability Distributions ◽  
Dynamic Bayesian Network ◽  
Current Situation ◽  
Time Behavior ◽  
Behavioral Rules ◽  
Autonomous Ship ◽  
Traffic Rules

The open wording of the traffic rules of the sea, COLREGS, and the existence of unwritten rules, make it essential for an autonomous ship to understand the intentions of meeting traffic. This article uses a dynamic Bayesian network (DBN) to model and infer the intentions of other ships based on their observed real-time behavior. Multiple intention nodes are included to describe the different ways a ship can interpret and conflict with the behavioral rules outlined in CORLEGS. The prior distributions of the intention nodes are adapted to the current situation based on observable characteristics such as location and relative ship size. When a new observation is made, the probability distributions of the intention variables are updated by excluding all combinations of intention states that conflict with the observed behavior. This way of modeling makes the intention probabilities independent of how often observations are made. The resulting model is able to identify situations that are prone to cause misunderstandings and infer the state of multiple intention variables that describe the behavior. Different collision avoidance algorithms can use the resulting intention information to better know if, when, and how to act.

scholarly journals Semantic Modelling of Ship Behavior in Harbor Based on Ontology and Dynamic Bayesian Network

2019 ◽  
Vol 8 (3) ◽  
pp. 107 ◽  
Author(s):  
Yuanqiao Wen ◽  
Yimeng Zhang ◽  
Liang Huang ◽  
Chunhui Zhou ◽  
Changshi Xiao ◽  
...  
Keyword(s):  
Bayesian Network ◽  
Situation Awareness ◽  
Semantic Network ◽  
Dynamic Bayesian Network ◽  
Detection Methods ◽  
Trajectory Data ◽  
Semantic Query ◽  
Traffic Lane ◽  
Ship Behavior ◽  
Traffic Rules

Recognizing ship behavior is important for maritime situation awareness and intelligent transportation management. Some scholars extracted ship behaviors from massive trajectory data by statistical analysis. However, the meaning of the behaviors, i.e., semantic meanings of behaviors and their relationships, are not explicit. Ship behaviors are affected by navigational area and traffic rules, so their meanings can be obtained only in specific maritime situations. The work establishes the semantic model of ship behavior (SMSB) to represent and reason the meaning of the behaviors. Firstly, a semantic network is built based on maritime traffic rules and good seamanship. The corresponding detection methods are then proposed to identify basic ship behaviors in various maritime scenes, including dock, anchorage, traffic lane, and general scenes. After that, dynamic Bayesian network (DBN) is used to reason potential ship behaviors. Finally, trajectory annotation and semantic query of the model are validated in the different scenes of harbor. The basic behaviors and potential behaviors in all typical scenes of any harbor can be obtained accurately and expressed conveniently using the proposed model. The model facilitates the ships behavior research, contributing to the semantic trajectory analysis.

scholarly journals A sequential dynamic Bayesian network for pore-pressure estimation with uncertainty quantification

Geophysics ◽  
2018 ◽  
Vol 83 (2) ◽  
pp. D27-D39 ◽  
Author(s):  
Rachel H. Oughton ◽  
David A. Wooff ◽  
Richard W. Hobbs ◽  
Richard E. Swarbrick ◽  
Stephen A. O’Connor
Keyword(s):  
Bayesian Network ◽  
Pore Pressure ◽  
Probability Distributions ◽  
Dynamic Bayesian Network ◽  
Pressure System ◽  
Log Data ◽  
Sources Of Uncertainty ◽  
Pressure Estimation ◽  
The Many ◽  
Many Sources

Pore-pressure estimation is an important part of oil-well drilling because drilling into unexpected highly pressured fluids can be costly and dangerous. However, standard estimation methods rarely account for the many sources of uncertainty, or for the multivariate nature of the system. We have developed the pore-pressure sequential dynamic Bayesian network (PP SDBN) as an appropriate solution to both these issues. The PP SDBN models the relationships between quantities in the pore-pressure system, such as pressures, porosity, lithology, and wireline-log data, using conditional probability distributions based on geophysical relationships to capture our uncertainty about these variables and the relationships between them. When wireline log data are given to the PP SDBN, the probability distributions are updated, providing an estimate of pore pressure along with a probabilistic measure of uncertainty that reflects the data acquired and our understanding of the system. This is the advantage of a Bayesian approach. Our model provides a coherent statistical framework for modeling the pore-pressure system. The specific geophysical relationships used can be changed to better suit a particular setting, or reflect geoscientists’ knowledge. We determine the PP SDBN on an offshore well from West Africa. We also perform a sensitivity analysis, demonstrating how this can be used to better understand the working of the model and which parameters are the most influential. The dynamic nature of the model makes it suitable for real-time estimation during logging while drilling. The PP SDBN models the shale pore pressure in shale-rich formations with mechanical compaction as the overriding source of overpressure. The PP SDBN improves on existing methods because it produces a probabilistic estimate that reflects the many sources of uncertainty present.

Sign in / Sign up

Export Citation Format

Share Document