The Difference Matters: Benchmarking Visual Performance of a Cognitive Pilot Model

摘要

In this paper we introduce an approach to objectively validate visual performance of a cognitive pilot model using benchmarks of human performance. A study with 16 human airline pilots and two competing models has been conducted in order to validate visual performance of the models applying these benchmarks. The study shows that human performance benchmarks can support analysts with a powerful and easy to use method for validation of human performance models. The benchmark is part of a larger-scale method, which will be developed in order to evaluate human factors issues of future HCI-concepts in early stages of system design.