Inference in the Wild: A Framework for Human Situation Assessment and a Case Study of Air Combat

Abstract

Situation awareness is a key construct in human factors and arises from a process of situation assessment (SA). SA comprises the perception of information, its integration with existing knowledge, the search for new information, and the prediction of the future state of the world, including the consequences of planned actions. Causal models implemented as Bayesian networks (BNs) are attractive for modeling all of these processes within a single, unified framework. We elicited declarative knowledge from two Royal Australian Air Force (RAAF) fighter pilots about the information sources used in the identification (ID) of airborne entities and the causal relationships between these sources. This knowledge was represented in a BN (the declarative model) that was evaluated against the performance of 19 RAAF fighter pilots in a low-fidelity simulation. Pilot behavior was well predicted by a simple associative model (the behavioral model) with only three attributes of ID. Search for information by pilots was largely compensatory and was near-optimal with respect to the behavioral model. The average revision of beliefs in response to evidence was close to Bayesian, but there was substantial variability. Together, these results demonstrate the value of BNs for modeling human SA.

Situation assessment in air combat considering incomplete frame of discernment in the generalized evidence theory

“…A fuzzy logic-based situation assessment system is developed to help the pilot make the right decision in complex air scenario where there may be multiple friendly aircrafts and/ or enemy aircrafts 12 . The situation assessment knowledge of fighter pilots in air combat is applied to model the human situation assessment model in Bayesian networks, which is a new perspective to improve the performance of fighter pilots in air combat 8 . In 13 , the confidence of classification on the air combat data are modelled based on a new algorithm using the naive Bayes theory.…”

“…Situation assessment in air combat environment is a key issue for successful defence and attack 7 . However, there are challenges in situation assessment of air combat such as the uncertainty 8 , and the coupled factors 9 . To address these issues, there are many studies focusing on improving the efficiency and accuracy of situation assessment in air combat.…”

NLP-Based Approach for Predicting HMI State Sequences Towards Monitoring Operator Situational Awareness

“…Operator mental awareness of the current process state and being able to anticipate future process states based on past experience and training is the highest SA an operator can possibly maintain at all times. Numerous SA cognitive models have been suggested from the widely accepted three-level Endsley model [8] (perception, comprehension, and projection stages of SA), to more recent Holistic framework [9] and Causal model [10]. However, as per Endsley model, SA is related to the task workload, information rate, system design, and complexity of tasks, requiring multivariate analysis.…”

A Novel Uncertainty Management Approach for Air Combat Situation Assessment Based on Improved Belief Entropy

“…A fuzzy logic-based situation assessment system is developed to help the pilot make the right decision in complex air scenarios where there may be multiple friendly aircrafts and/or enemy aircrafts [ 9 ]. In [ 10 ], the situation assessment knowledge of fighter pilots in air combat is applied to model a human situation assessment model in Bayesian networks, which is a new perspective to improve the performance of fighter pilots in air combat.…”