Navatar: Navigating Blind Users in Indoor Spaces using Tactile Landmarks
Indoor navigation systems for users who are visually impaired typically rely upon expensive physical augmentation of the environment or expensive sensing equipment; consequently few systems have been implemented. We present an indoor navigation system called Navatar that allows for localization and navigation by exploiting the physical characteristics of indoor environments, taking advantage of the unique sensing abilities of users with visual impairments, and minimalistic sensing achievable with low cost accelerometers available in smartphones.
How it works
user confirming landmarks
For outdoor navigation localization with high precision is required as users are more likely to veer whereas in indoor environments navigation is constrained by physical infrastructure such as walls and doors and veering is less likely.
Precise localization comes at a significant higher cost; as augmenting indoor environments with RFID tags is often prohibitively expensive. To facilitate large-scale deployment of an indoor navigation system, less precise but less expensive localization solutions need to be explored.
Dead reckoning localization is cheap and can be achieved using sensors (accelerometer/compass) already present in current mobile devices.
Dead reckoning is relative accurate for short distances but inaccurate for longer distances as errors accumulate of time.
Particle filters are used to estimate the user's location based on the sensor data as well as the user confirming the presence of tactile landmarks along the provided path that are extracted from a virtual representation of the environment, which allows for mitigating the error of dead reckoning.
This type of interaction seamlessly integrates with how users with visual impairments navigate familiar spaces as this includes the identification of known tactile landmarks.
Navatar has a high possibility of large-scale deployment, as it only requires an annotated virtual representation of an indoor environment, for example, created in Google Sketchup. A user study with 12 blindfolded and six blind users demonstrates the feasibility of our approach and shows we can locate the user with 1.85 meter accuracy. We identify several areas for improvement.
Landmarks used for navigation, can be annotated on a 3D model by harnessing crowdsourcing efforts.