Towards a Human-Centred Cognitive Model of Visuospatial Complexity in Everyday Driving
This work addresses the need for better human-factors understanding in driving scenarios, though it appears incremental as it builds on existing cognitive modeling approaches.
The authors tackled the problem of modeling visuospatial complexity in everyday driving by developing a human-centred cognitive model based on visual perception and behavioral evaluation with human subjects, reporting preliminary applications for dataset creation and explainable computational analysis.
We develop a human-centred, cognitive model of visuospatial complexity in everyday, naturalistic driving conditions. With a focus on visual perception, the model incorporates quantitative, structural, and dynamic attributes identifiable in the chosen context; the human-centred basis of the model lies in its behavioural evaluation with human subjects with respect to psychophysical measures pertaining to embodied visuoauditory attention. We report preliminary steps to apply the developed cognitive model of visuospatial complexity for human-factors guided dataset creation and benchmarking, and for its use as a semantic template for the (explainable) computational analysis of visuospatial complexity.