Predicting Human Operator’s Decisions Based on Prospect Theory

Paulo Eduardo Ubaldino de Souza (1) , Caroline Ponzoni Carvalho Chanel (1) , Melody Maillez (1) , Frédéric Dehais (1)

1 DCAS - Département Conception et conduite des véhicules Aéronautiques et Spatiaux

The aim of this work is to predict human operator's decisions in a specific operational context, such as a cooperative human-robots mission, by approximating her utility function based on Prospect Theory. To this aim, a within-subject experiment was designed in which the human operator has to decide with limited time and incomplete information. This experiment also involved a framing effect paradigm, a typical cognitive bias causing people to react differently depending on the context. Such an experiment allowed to acquire data concerning the human operator's decisions in two different mission scenarios: search and rescue and Mars rock sampling. The framing was manipulated (e.g. positive vs. negative) and the probability of the outcomes causing people to react differently depending on the context. Statistical results observed for this experiment supported the hypothesis that the way the problem was presented (positively or negatively framed) and the emotional commitment affected the human operator's decisions. Thus, based on the collected data, the present work is willed to propose: (i) a formal approximation of the human operator's utility function founded on the Prospect Theory; and (ii) a model used to predict the human operator's decisions based on the economics approach of multi-dimensional consumption bundle and Prospect Theory. The obtained results, in terms of utility function fit and prediction accuracy, are promising and show that similar modeling and prediction method should be taken into account when an intelligent cybernetic system drives human-robots interaction. The advantage of predicting the human operator's decision, in this operational context, is to anticipate her decision, given the way a question is framed to the human operator. Such a predictor lays the foundation for the development of a decision-making system capable of choosing how to present the information to the operator while expecting to align her decision with the given operational guideline.

Mots clés: Human-computer interaction (HCI)- Human-robot(s) interaction (HRI); Model-based predictor design; Prospect theory; Cognitive bias; Framing effect

Domaines: Neurosciences

Paulo Eduardo Ubaldino de Souza, Caroline Ponzoni Carvalho Chanel, Melody Maillez, Frédéric Dehais. Predicting Human Operator’s Decisions Based on Prospect Theory. Interacting with Computers, 2020, pp.1-16. ⟨10.1093/iwcomp/iwaa016⟩. ⟨hal-02923113⟩