Inclusive guide: An innovative system designed to provide affordable internal navigation for people with visual impairments

Indoor navigation for individuals with visual impairments remains a persistent and complex technological challenge, especially in environments where GPS coverage is unavailable and specialized infrastructure is absent. This paper presents the development and evaluation of the Inclusive Guide, an innovative, cost-effective, and fully portable indoor navigation system designed to operate autonomously using onboard processing. The proposed system integrates multiple technologies, including LiDAR-based obstacle detection for real-time spatial awareness, QR code-based localization for environmental referencing, and the A* algorithm for optimal path planning. User interaction is facilitated through multimodal channels, combining voice commands, auditory feedback, and haptic signals to accommodate a range of sensory needs. All components are implemented on a Raspberry Pi 5 platform, ensuring compactness and low power consumption, and rely entirely on open-source software for transparency and scalability. To validate the system’s functionality, extensive testing was conducted across several indoor environments, such as academic corridors and public institution hallways. Results indicated high navigation accuracy, effective and timely obstacle avoidance, and stable system responsiveness. A pilot study involving five visually impaired users demonstrated that participants could successfully perform navigation tasks with minimal assistance, reporting positive feedback regarding usability, comfort, and reliability. The system’s strengths lie in its infrastructure-free deployment, affordability, and the integration of efficient sensor fusion techniques. Nonetheless, limitations such as sensitivity to lighting conditions for QR code recognition and minor latency in speech processing were identified. Future development will address these issues and incorporate semantic scene understanding to further enhance navigation intelligence. This study confirms the practicality of deploying inclusive, fully offline navigation solutions using accessible hardware platforms.