Artificial Intelligence (AI) Voice Module for Robotic Service Dog

Acquiring a traditional service dog for visually impaired persons is expensive with long waitlist times, complicated training programs, and the responsibility of caring for a living creature. A robotic service dog alternative could be a significantly more accessible and practical option for many members of the visually impaired community. Another benefit of a robotic service dog is the ability to imbue the dog with the ability to converse with their companion in human language. This will allow human users to gather more information about their environment and make specific commands to the service dog. The focus of this project is to create a voice module that takes commands and gives verbal replies by incorporating hardware and software components as a module. This module will ultimately be installed on a Unitree Go1 robotic dog using a Raspberry Pi, microphone, speaker, and several python libraries such as PyAudio and SpeechRecognition for voice recognition and pyttsx3 for speech synthesis. These libraries rely on the Hidden Markov Model, voice activity detectors, and preinstalled TTS engines. A working prototype will be demonstrated with functional speech and audio input capabilities in English to report on the environment and to receive voice commands. Testing and validation results will also include metrics like speaking range, rate of speaking, and volume of speech synthesis. The outcomes of our research contribute to the advancement of assistive technologies for visually impaired individuals, ultimately improving their quality of life and independence.