Akshara Pande

The purpose of designing machines is to serve humans and assist them in completing their work on time. A machine, such as a social robot, can be particularly supportive for older individuals who may have reduced strength and be more susceptible to various health issues. The present paper proposes a scenario in which elderly health is monitored by a social robot. As an observer, a social robot, through perceiving its environment, can capture several moments (including daily activities or falls) of an older adult and can provide timely reminders and alerts to the elderly and their caregivers, ensuring the elderly's well-being. Therefore, validation of the machine's health (functioning) is necessary. To accomplish this, the current paper suggests utilization of Prognosis and Health Management (PHM) for the elderly-centric robot system. Furthermore, a PHM-enabled elderly-centric robot system has two main entities: an older adult and a robot, hence it is important to analyze the sustainability dimensions from various perspectives. There are two main objectives of this paper: (i) to develop a comprehensive list of sustainability topics under various dimensions achieved from the examination of three sustainable frameworks: the Triple Bottom Line, Responsible Research and Innovation, Sustainable Assessment and Sustainability Awareness Framework (SuSAF). (ii) to apply the comprehensive list of sustainability dimensions to the proposed case of PHM-enabled elderly-centric social robot system. The results suggest that SuSAF is the most comprehensive and suitable framework for the sustainability assessment of the proposed system. Furthermore, the use of sustainable dimensions can ensure improved robot health and, hence, the health of the elderly.

Speech comprehension can be challenging due to multiple factors, causing inconvenience for both the speaker and the listener. In such situations, using a humanoid robot, Pepper, can be beneficial as it can display the corresponding text on its screen. However, prior to that, it is essential to carefully assess the accuracy of the audio recordings captured by Pepper. Therefore, in this study, an experiment is conducted with eight participants with the primary objective of examining Pepper’s speech recognition system with the help of audio features such as Mel-Frequency Cepstral Coefficients, spectral centroid, spectral flatness, the Zero-Crossing Rate, pitch, and energy. Furthermore, the K-means algorithm was employed to create clusters based on these features with the aim of selecting the most suitable cluster with the help of the speech-to-text conversion tool Whisper. The selection of the best cluster is accomplished by finding the maximum accuracy data points lying in a cluster. A criterion of discarding data points with values of WER above 0.3 is imposed to achieve this. The findings of this study suggest that a distance of up to one meter from the humanoid robot Pepper is suitable for capturing the best speech recordings. In contrast, age and gender do not influence the accuracy of recorded speech. The proposed system will provide a significant strength in settings where subtitles are required to improve the comprehension of spoken statements.