Path Finder is a new app developed to help users navigate through public environments and all the unknowns surrounding them. Leveraging the machine learning capabilities of Android, Path Finder helps people with visual impairments by identifying and calculating the trajectories of objects moving in their path. Custom alerts then inform the user of how to avoid these obstacles and what actions they can safely make.
The app came out of the Android Challenge last December to the developer community to create helpful innovations powered by on-device machine learning (ML). “What started as a simple idea among Rocketeers was selected as one in a handful of finalists out of over 500 applicants,” says Colin Shelton, lead Android engineer at Bottle Rocket, a digital experience consultancy that provides businesses with strategy, product, design and technology services. “Our ML club is always looking for new opportunities to flex our technical chops and experiment with technology in new ways and this challenge was the perfect opportunity to do just that while also doing something good for the world.”
The app brings together object detection and depth mapping and uses TensorFlow Lite to calculate distances of surrounding objects. It is designed to augment the user’s experience, share information and give support, not overwhelm them in difficult situations. Both audible and haptic feedback are part of alert system, while a range of pitches and frequencies communicate each object’s distance and direction. Audio patterns, like Morse Code, are then layered and combined for sharing further information. The app helps visually impaired users gain the advantage of foresight, making public environments easier to navigate.
The Path Finder app is currently featured among other finalists in a curated ML collection by Google.