Do I remember you? Memory and identity in multiple embodiments

Abstract

-This paper investigates user perceptions of continuous identity as agents migrate between different embodiments. It reports an experiment seeking to establish whether migrating or not migrating the interaction memory of the agent would affect the user's perception of consistent agent identity over different embodiments. The experiment involved a treasure hunt in which a virtual agent migrated from a screen to a mobile phone in order to accompany a user while they searched for clues. A total of 45 subjects took part in three different conditions with 15 subjects in each. The outcome showed that the presence of memory affected the competence users ascribed to the virtual agent but had no significant effect on a strong perception of consistent identity across multiple embodiments.

A Review of Virtual Assistants’ Characteristics: Recommendations for Designing an Optimal Human–Machine Cooperation

“…The results showed that in general iconic signals help to better understand that the migration occurred while time signals were more frequently associated with the communication between the robots. Another study [83] showed that being able to keep a memory of past interactions with the user affected the virtual agent's perceived level of competence, but did not have a significant effect on the perception of a coherent identity between the different media where the agent could migrate. In this evaluation, the agent could migrate among a robot, a virtual agent on a computer screen, and a virtual agent on a smartphone screen.…”

Relationship Development with Humanoid Social Robots: Applying Interpersonal Theories to Human–Robot Interaction

“…6,24,26 One major issue is that modern HSRs lack the ability to attend to, recall, and apply relevant information from previous interactions with a human user, which diminishes social perceptions. 26,27 Robot memory lacks persistence and sufficiently refined searchability for sensible ongoing social interactions: most do not maintain a memory of previous interactions, and if they do, retrieval is constrained to a few task-relevant queries. Modern HSRs cannot make sense of interactional history in the same way that humans do, and they are limited in their ability to apply such knowledge to novel social situations.…”

On designing migrating agents

“…The ultimate goal of LIREC project is to move beyond the novelty effect of both social robots and ECAs towards social companions that can play an acceptable long term role. It is reported that user studies suggest the success of this architecture [Kriegel et al 2011;Aylett et al 2013]. Sarah is a LIREC-based companion that can be embodied in a robot, on a large graphical screen or in a handheld device.…”