Constructing a Real-Time Cognitive Map for Visually Impaired Individuals

Vision is the most important sense for perceiving and building a mental representation of physical spaces or environmental features, leading to guide human actions. Visually impaired individuals face several daily challenges due to their loss of sight. This project aims to integrate simultaneous localization and mapping (SLAM) with deep learning techniques to assist visually impaired people to construct a reliable and real-time spatial knowledge about surroundings, and move through environment independently and safely.

Main Contributors

Primary Research Issues

  • Deep Learning Neural Network
  • Localisation
  • Mapping
  • Obstacle Avoidance
  • Path Planning