Influencing Actions-Related Decisions Using Soft Computing Approaches

Influencing Actions-Related Decisions Using Soft Computing Approaches

Frederick E. Petry (Naval Research Lab, Stennis Space Center, USA) and Ronald R. Yager (Machine Intelligence Institute, Iona College, USA)
DOI: 10.4018/978-1-4666-6639-9.ch007


This chapter describes soft computing approaches for human-agent communications in the context of influencing decision-making behavior for health-related actions. Several methods are illustrated including using a person's predispositions and generalization techniques that allow issues to be viewed in a more favorable light with social interaction persuasion tendencies modeled with soft computing. The context of a robotic assistant for the elderly is used to illustrate the various communication techniques. Hierarchical generalization is introduced as a technique for generating potential alternatives in choices that might be more broadly acceptable to an individual who is being motivated towards a better choice. Finally, the related topic of negotiations using some the developed techniques is presented.
Chapter Preview


Robotic Elder Care

Robotic aids for the disabled and elderly is a growing area of research (Goth, 2011; Jacobs & Graf, 2012). This is strongly motivated by the rapidly increasing population in this age group. Japan has several active research programs (Kanda, Nabe, Hiraki, Ishiguro & Hagita, 2008; Severinson-Eklundh, Green & Huutenrauch, 2003) as 22% of their population is 65 or older and quickly expanding in the coming decades. In the United States the National Science Foundation has established the Quality of Life Technology Center at Carnegie Mellon and University of Pittsburgh.

For this paper we will illustrate our approach using a scenario in which a robotic assistant (RA) in the future can provide various forms of assistance in rehabilitation and even daily living requirements of the elderly. Often elderly residents of a nursing home may be somewhat addled or recalcitrant. So it is very important that a robotic assistant be able to communicate to persons with whom they are trying to persuade about issues such as medications or rehab activities. In particular social aspects of the assistants' interaction have to be considered (Bemelmans, Gelderblom, Jonker & de Witte, 2012; Klein, Gaedt & Cook, 2013). We will describe how this communication can be modeled with soft computing techniques and recognize the social aspects of such interactions.

Complete Chapter List

Search this Book: