Publication Type

Journal Article

Version

acceptedVersion

Publication Date

2-2019

Abstract

Assistive agents have been used to give advices to the users regarding activities in daily lives. Although adviser bots are getting smarter and gaining more popularity these days they are usually developed and deployed independent from each other. When several agents operate together in the same context, their advices may no longer be effective since they may instead overwhelm or confuse the user if not properly arranged. Only little attentions have been paid to coordinating different agents to give different advices to a user within the same environment. However, aligning the advices on-the-fly with the appropriate presentation timing at the right context still remains a great challenge. In this paper, a coordination framework for advice giving and persuasive agents is presented. Apart from preventing overwhelming messages, the adaptation enables cooperation among the agents to make their advices more impactful. In contrast to conventional models that rely on natural language contents or direct multi-modal cues to align the dialogs, the proposed framework is built to be more practical allowing the agents to actively share their observation, goals, and plans to each other. This allows them to adapt the schedules, strategies, and contents of their scheduled advices or reminders at runtime with respect to each other’s objectives. Challenges and issues in multi-agent adviser systems are identified and defined in this paper supported by a survey study about perceived usefulness and user comprehensibility of advices delivered by multiple agents. The coordination among the advice giving agents are investigated and exemplified with a simulation of activity of daily living in the context of aging in place.

Keywords

Persuasive agent, Virtual companion, Multi-agent systems, Coordination

Discipline

Computer and Systems Architecture | Databases and Information Systems | OS and Networks

Research Areas

Data Science and Engineering

Publication

Expert Systems with Applications

Volume

116

First Page

31

Last Page

51

ISSN

0957-4174

Identifier

10.1016/j.eswa.2018.08.030

Publisher

Elsevier

Additional URL

https://doi.org/10.1016/j.eswa.2018.08.030

Download

Share

COinS