This paper presents an AI-powered navigation support system designed to assist visually impaired individuals in moving independently. The system integrates speech recognition, geographic information technologies, and machine learning to enable hands-free navigation. It uses OpenAI’s Whisper for accurate speech-to-text transcription and interprets user voice commands to generate accessible routes through Open Route Service. Navigation instructions are delivered through the Web Speech API, while camera-based object detection using TensorFlow.js identifies obstacles and provides real-time alerts. The system follows a client–server architecture using Python Flask and JavaScript, where intensive AI processing occurs on the server while the browser manages lightweight tasks. This approach enhances safety, independence, and social inclusion for visually impaired users and supports the goals of sustainable development.
K et al. (Sun,) studied this question.