DogSurf: Quadruped Robot Capable of GRU-based Surface Recognition for Blind Person Navigation
This addresses navigation safety for blind individuals, but it is incremental as it applies an existing neural network method to a new robotic application.
The paper tackles the problem of helping visually impaired people navigate by enabling a quadruped robot to detect slippery surfaces with 99.925% accuracy using a GRU-based neural network, providing audio and haptic feedback to warn users.
This paper introduces DogSurf - a newapproach of using quadruped robots to help visually impaired people navigate in real world. The presented method allows the quadruped robot to detect slippery surfaces, and to use audio and haptic feedback to inform the user when to stop. A state-of-the-art GRU-based neural network architecture with mean accuracy of 99.925% was proposed for the task of multiclass surface classification for quadruped robots. A dataset was collected on a Unitree Go1 Edu robot. The dataset and code have been posted to the public domain.