Luo, Liangyi and Ogawa, Kohei and Peebles, Graham and Ishiguro, Hiroshi (2022) Towards a Personality AI for Robots: Potential Colony Capacity of a Goal-Shaped Generative Personality Model When Used for Expressing Personalities via Non-Verbal Behaviour of Humanoid Robots. Frontiers in Robotics and AI, 9. ISSN 2296-9144
pubmed-zip/versions/3/package-entries/frobt-09-728776-r2/frobt-09-728776.pdf - Published Version
Download (2MB)
Abstract
Engineering robot personalities is a challenge of multiple folds. Every robot that interacts with humans is an individual physical presence that may require their own personality. Thus, robot personalities engineers face a problem that is the reverse of that of personality psychologists: robot personalities engineers need to make batches of identical robots into individual personalities, as oppose to formulating comprehensive yet parsimonious descriptions of individual personalities that already exist. The robot personality research so far has been fruitful in demonstrating the positive effects of robot personality but unfruitful in insights into how robot personalities can be engineered in significant quantities. To engineer robot personalities for mass-produced robots we need a generative personality model with a structure to encode a robot’s individual characteristics as personality traits and generate behaviour with inter- and intra-individual differences that reflect those characteristics. We propose a generative personality model shaped by goals as part of a personality AI for robots towards which we have been working, and we conducted tests to investigate how many individual personalities the model can practically support when it is used for expressing personalities via non-verbal behaviour on the heads of humanoid robots.
Item Type: | Article |
---|---|
Subjects: | STM Academic > Mathematical Science |
Depositing User: | Unnamed user with email support@stmacademic.com |
Date Deposited: | 22 Jun 2023 08:43 |
Last Modified: | 31 Oct 2023 06:35 |
URI: | http://article.researchpromo.com/id/eprint/1136 |