Tailoring a cognitive model for situation awareness using machine learning

Koopmanschap, Richard; Hoogendoorn, Mark; Roessingh, Jan Joris

doi:10.1007/s10489-014-0584-3

Cited by 12 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature shows that the automation of the SABDM model using machine learning techniques presents good results in model parameter configuration [8], [13] and in the model's goal selection [9]. This study extends this knowledge by proposing automating the initial model parameter adjustments and evolutionary maintenance under environmentally changing conditions using reinforcement learning techniques.…”

Section: Introductionmentioning

confidence: 80%

“…Gini et al [13] employed genetic algorithms to automatically learn the situation awareness model's mental or cognitive map (belief network) parameters. Koopmanschap et al [8] evaluated hill climbing and evolutionary genetic algorithms. Both studies showed promising results in tailoring the belief network parameters on simulated air-force combat operations.…”

Section: E Related Workmentioning

confidence: 99%

“…Machine learning (ML) techniques such as hill climbing, evolutionary genetics, and reinforcement learning (RL) are used as automation methods to reduce the expert work in the parameter configuration and adjustments of situationawareness (SA) mental model belief network implementations [8], [9]. They automate the treatment of experimental and simulated data captured by techniques such as Situation Awareness Global Assessment Technique (SAGAT) [10] and Simulation Awareness Rating Technique (SART) [11] on the SA model's parameter adjustments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comparative Study of Situation Awareness-Based Decision-Making Model Reinforcement Learning Adaptive Automation in Evolving Conditions

2023

View full text Add to dashboard Cite

Situation-awareness-based decision-making (SABDM) models constructed using cognitive maps and goal-direct task analysis techniques have been successfully used in decision support systems in safety-critical and mission-critical environments such as air traffic control and electrical energy distribution. Reinforcement learning (RL) and other machine learning techniques are used to automate situational awareness mental model parameter adjustments, reducing the expert work on the initial configuration and long-term maintenance without affecting the mental model's structure and maintaining the situationawareness-based decision-making model's cognitive and explainability characteristics. Real-world models should evolve to cope with changes in the environmental conditions. This study evaluates the application of reinforcement learning as an online adaptive technique to adjust the situational-awareness mental model's parameters under evolving conditions. We conducted evaluation experiments using real-world public datasets to compare the performance of the SABDM model with that of the reinforcement learning adaptation technique (SABDM/RL) and other adaptive machine learning methods under distinct concept drift evolving conditions. We measured the techniques' overall and dynamic performance to understand how well they adapt to evolving environmental conditions. The experiments show that SABDM/RL performs similarly to modern online adaptive machine learning classification methods with the support of concept drift detection techniques while maintaining the mental model strength of the situation awarenessbased systems.

show abstract

Section: Introductionmentioning

confidence: 80%

Section: E Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Situation Awareness-Based Decision-Making Model Reinforcement Learning Adaptive Automation in Evolving Conditions

2023

View full text Add to dashboard Cite

show abstract

“…In the research literature, a few studies have developed SA models and demonstrated the application of modelling techniques including fuzzy cognitive maps, used to predict SA in military decision making [28]; machine learning, used in aviation games [29]; granular computing methods, used for automated air surveillance applications [30]; and probabilistic models of visual scanning (attention-situation awareness model), and used in aviation [31]. These techniques, however, are limited in terms of full operationalization of SA modelling.…”

Section: Research Problemsmentioning

confidence: 99%

Modelling level 1 situation awareness in driving: A cognitive architecture approach

Rehman,

Cao,

MacGregor

2024

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

“…As said, the DS technique is based on the prioritization of rules depending on their appropriateness for the situation at hand. An alternative approach that has been proposed is to tailor a cognitive model to the situation at hand by means of adapting the parameters of the model, also allowing for a form of adaptation [9]. Although these techniques provide ways to adapt existing behavior to new scenarios, they do so in a relatively limited way as they are based on existing rules.…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Dynamic Scripting: Adaptation of Expert Rule Bases for Serious Games

Kop

Toubman

Hoogendoorn

et al. 2015

Current Approaches in Applied Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Automatically generating behavior for Non-Player Characters (NPCs) in serious games can be problematic as the specification of their behavior heavily relies on the availability of domain expertise. This expertise can be difficult and costly to extract, and the specified behavior usually does not allow for generalization to new scenarios or users. Alternatively, behavior can be generated using a pure machine learning approach. However, such NPCs may quickly develop static, non-adaptive behavior by exploiting the environment without proper constraints. In this paper, an approach called Evolutionary Dynamic Scripting (EDS) is presented to effectively cope with the disadvantages of the two extremes sketched above. This technique combines the generative characteristics of an evolutionary approach with an adaptive reinforcement learning method called Dynamic Scripting. Dynamic Scripting essentially learns how to prioritize rules from a fixed rule-base specified by domain experts. EDS was tested in an air combat simulation in which agents co-evolve their tactics using EDS. EDS was able to generate improved behavioral rules over the original Dynamic Scripting approach, given the same initial rule-bases. Both generalization to new situations and specialization into roles for the agents were observed.

show abstract

Tailoring a cognitive model for situation awareness using machine learning

Cited by 12 publications

References 15 publications

A Comparative Study of Situation Awareness-Based Decision-Making Model Reinforcement Learning Adaptive Automation in Evolving Conditions

A Comparative Study of Situation Awareness-Based Decision-Making Model Reinforcement Learning Adaptive Automation in Evolving Conditions

Modelling level 1 situation awareness in driving: A cognitive architecture approach

Evolutionary Dynamic Scripting: Adaptation of Expert Rule Bases for Serious Games

Contact Info

Product

Resources

About