Developing a Flexible System for a Friendly Robot to Ease Dementia (FRED) Using Cloud Technologies and Software Design Patterns

In this work, we designed two prototypes for a friendly robot to ease dementia (FRED). This affordable social robot is designed to provide company to older adults with cognitive decline, create reminders for important events and tasks, like taking medication, and providing cognitive stimulus through games. This project combines several cloud technologies including speech-to-text, cloud data storage, and chat generation in order to provide high level interactions with a social robot. Software design patterns were employed in the creation of the software to produce flexible code base that can sustain platform changes easily, including the framework used for the graphical user interface (GUI) and the database platform being used to store user data. The first prototype was developed on an Android-based system with an Arduino. This system was found to be expensive, unreliable, and difficult to develop on. The second prototype was therefore developed for a Raspberry Pi programmed using Python. Multiple tests with potential users were conducted in order to assess the capabilities and usability of the software created. These user tests showed overall satisfaction with the usability, and provided useful feedback for improving the software and expanding the capabilities of FRED.