Pedestrian tracking systems implemented in regular smartphones may provide a convenient mechanism for wayfinding and backtracking for people who are blind. However, virtually all existing studies only considered sighted participants, whose gait pattern may be different from that of blind walkers using a long cane or a dog guide. In this contribution, we present a comparative assessment of several algorithms using inertial sensors for pedestrian tracking, as applied to data from WeAllWalk, the only published inertial sensor dataset collected indoors from blind walkers. We consider two situations of interest. In the first situation, a map of the building is not available, in which case we assume that users walk in a network of corridors intersecting at 45° or 90°. We propose a new two-stage turn detector that, combined with an LSTM-based step counter, can robustly reconstruct the path traversed. We compare this with RoNIN, a state-of-the-art algorithm based on deep learning. In the second situation, a map is available, which provides a strong prior on the possible trajectories. For these situations, we experiment with particle filtering, with an additional clustering stage based on mean shift. Our results highlight the importance of training and testing inertial odometry systems for assisted navigation with data from blind walkers.

We describe two iOS apps designed to support blind travelers navigating in indoor building environments. The Wayfinding app provides guidance to a blind user while following a certain route. The Backtracking app records the route taken by the walker towards a certain destination and then provides guidance while re-tracing the same trajectory in the opposite direction. Our apps only use the inertial and magnetic sensors of the smartphone, and thus require no infrastructure modification (e.g., installation and support of BLE beacons). Unlike systems that use the phone’s camera, users of our apps can conveniently keep their phone tucked inside their pocket while interacting with the apps using a smartwatch. Routing directions are given via speech. Both apps were tested in a user study with seven blind participants who used them while navigating a campus building. Participants were able to successfully use the Wayfinding app to complete the prescribed paths (three paths each), although the app had to be restarted for the first three participants in one path due to incorrect step length measurements (the app was later modified to track the users’ step length). The Backtracking app worked well in most cases, although in 6 trials (out of 21), the app lost track of the participant’s location.

Pedestrian dead reckoning (PDR) relies on the estimation of the length of each step taken by the walker in a path from inertial data (e.g. as recorded by a smartphone). Existing algorithms either estimate step lengths directly, or predict walking speed, which can then be integrated over a step period to obtain step length. We present an analysis, using a common architecture formed by an LSTM followed by four fully connected layers, of the quality of reconstruction when predicting step length vs. walking speed. Our experiments, conducted on a data set collected by twelve participants, strongly suggest that step length can be predicted more reliably than average walking speed over each step.

We introduce two iOS apps that have been designed to support wayfinding and backtracking for blind travelers navigating in indoor building environments. Wayfinding involves determining and following a route through the building's corridors to reach a destination, and assumes that the app has access to the floor plan of the building. Backtracking one's route, on the other hand, requires no map knowledge. Our apps only use the inertial and magnetic sensors of the smartphone, and thus require no infrastructure modification (e.g., installation and support of BLE beacons). Unlike systems that use the phone's camera, users of our apps can conveniently keep their phone tucked inside a pocket, while interacting with the apps using a smartwatch. Routing directions are given via speech. Both apps were tested in a user study with seven blind participants, who used them while navigating a campus building.