L.I.S.A. : um modo de voz interativo para um robô humanoide

Saved in:
Bibliographic Details
Main Author: Chagas, Artur D'Angelo
Publication Date: 2025
Format: Master thesis
Language: por
Source: Repositório Institucional da UPF
Download full: https://repositorio.upf.br/handle/123456789/9628
Summary: This work presents the development and validation of the voice module L.I.S.A. (Interactive Language for Automatic Support), integrated into the humanoid robot S.A.R.A.H., aimed at interacting with elderly people. The research was divided into three stages: systematic review, system development, and user validation. The literature review exhibited that most existing solutions prioritize technical aspects, with little adaptation for the elderly. L.I.S.A. was developed in Python and executed by a Raspberry Pi, using voice recognition and synthesis libraries, in addition to functions such as reminders and voice interaction. Validation was conducted with ten elderly participants across two rounds of data collection, using questionnaires and observation. Results showed good acceptance of the system, especially due to the usefulness of the reminders and ease of use. However, limitations were observed, such as difficulty in interrupting speech and limited flexibility in understanding commands. Findings indicate that factors such as voice tone, robot aesthetics, and prior familiarity with technology influence user acceptance. Despite positive feedback, broader use of L.I.S.A. dependsonadjustmentsaccording to the context of application, such as physical environment and user profile. This research contributes to the field of assistive robotics by proposing an accessible and aging-adapted solution, with potential for use in domestic or institutional settings.