Synthetic data augmentation for robotic mobility aids to support blind and low vision people
This work addresses a critical data scarcity problem for developers of assistive technologies for blind and low-vision people, though it is incremental in optimizing synthetic data generation.
The study tackled the limited availability of real-world datasets for training deep learning vision models in robotic mobility aids for blind and low-vision individuals by investigating synthetic data generation using Unreal Engine 4, finding that it enhances model performance across multiple tasks while highlighting its limitations compared to real data.
Robotic mobility aids for blind and low-vision (BLV) individuals rely heavily on deep learning-based vision models specialized for various navigational tasks. However, the performance of these models is often constrained by the availability and diversity of real-world datasets, which are challenging to collect in sufficient quantities for different tasks. In this study, we investigate the effectiveness of synthetic data, generated using Unreal Engine 4, for training robust vision models for this safety-critical application. Our findings demonstrate that synthetic data can enhance model performance across multiple tasks, showcasing both its potential and its limitations when compared to real-world data. We offer valuable insights into optimizing synthetic data generation for developing robotic mobility aids. Additionally, we publicly release our generated synthetic dataset to support ongoing research in assistive technologies for BLV individuals, available at https://hchlhwang.github.io/SToP.