An Affordance-based Model of Human Action Selection in a Human-Machine Interaction System with Cognitive Interpretations

International Journal og Human-Computer Interaction (2016)

Hokyoung Ryu, Namhun Kim, Jangsun Lee & Dongmin Shin

hdr_img

Abstract: Current technology is not sufficient to automate all desired tasks. Human-machine interaction (HMI) has thus become a key control and design factor for tasks requiring human-level decision-making or information synthesis. Such processes require a formal representation of human actions (including decision-making) when modeling HMI systems; however, successful prescriptive approaches to this end have still been elusive. This paper extends the affordance-based finite state automata (FSA) model, conditioning human prior experience and natural loss of task knowledge. The new model draws upon both reinforcement learning and natural memory decay for decision-making on action choice. An empirical study is carried out to specify how action choice is affected or updated by reinforcement learning based on past experience, and Wickelren’s decay function is jointly employed to predict human decision-making behavior

The model considers two critical factors in the semantic condition that plays an important role in interpreting the human operator’s action choice behaviors. The basic activation rate is associated with the initial activation of task knowledge and reflects the human operator’s past experience, and the memory decay corresponds to the natural failure to recall adequate task knowledge as time elapses. By incorporating the two components, the extended model contributes to investigate how a human operator is attracted to a particular action, which is not considered in the previous affordance-based FSA model.