scholarly journals Promotion of active ageing through interactive artificial agents in a smart environment

2021 ◽  
Vol 3 (5) ◽  
Author(s):  
Paulo Menezes ◽  
Rui P. Rocha

Abstract Societies in the most developed countries have witnessed a significant ageing of the population in recent decades, which increases the demand for healthcare services and caregivers. The development of technologies to help the elderly, so that they can remain active and independent for a longer time, helps to mitigate the sustainability problem posed in care services. This article follows this new trend, proposing a multi-agent system composed of a smart camera network, centralised planning agent, a virtual coach, and robotic exercise buddy, designed to promote regular physical activity habits among the elderly. The proposed system not only persuades the users to perform exercise routines, but also guides and accompanies them during exercises in order to provide effective training and engagement to the user. The different agents are combined in the system to exploit their complementary features in the quest for an effective and engaging training system. Three variants of the system, involving either a partial set of those agents or the full proposed system, were evaluated and compared through a pilot study conducted with 12 elderly users. The results demonstrate that all variants are able to guide the user in an exercise routine, but the most complete system that includes a robotic exercise buddy was the best scored by the participants. Article Highlights Proposal of a multi-agent system to help elderly adopting regular physical activity habits. A virtual coach and a robotic exercise buddy provide both guidance and companionship during the exercise. A pilot study conducted with 12 elderly users demonstrated an effective and engaging training system.

2019 ◽  
Vol 9 (6) ◽  
pp. 1089 ◽  
Author(s):  
Wei Han ◽  
Bing Zhang ◽  
Qianyi Wang ◽  
Jun Luo ◽  
Weizhi Ran ◽  
...  

The modeling and design of multi-agent systems is imperative for applications in the evolving intelligence of unmanned systems. In this paper, we propose a multi-agent system design that is used to build a system for training a team of unmanned surface vehicles (USVs) where no historical data concerning the behavior is available. In this approach, agents are built as the physical controller of each USV and their cooperative decisions used for the USVs’ group coordination. To make our multi-agent system intelligently coordinate USVs, we built a multi-agent-based learning system. First, an agent-based data collection platform is deployed to gather competition data from agents’ observation for on-line learning tasks. Second, we design a genetic-based fuzzy rule training algorithm that is capable of optimizing agents’ coordination decisions in an accumulated manner. The simulation results of this study demonstrate that our proposed training approach is feasible and able to converge to a stable action selection policy towards efficient multi-USVs’ cooperative decision making.


2009 ◽  
Vol 2 (4) ◽  
pp. 61-70
Author(s):  
Ravi Babu Pallikonda ◽  
◽  
K. Prapoorna ◽  
N.V. Prashanth ◽  
A. Shruti ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document