Automatic Synthesis of Virtual Wheelchair Training Scenarios
Wanwan Li, Javier Talavera, Amilcar Gomez Samayoa, Jyh‐Ming Lien, Lap-Fai Yu
Abstract
In this paper, we propose an optimization-based approach for automatically generating virtual scenarios for wheelchair training in virtual reality. To generate a virtual training scenario, our approach automatically generates a realistic furniture layout for a scene as well as a training path that the user needs to go through by controlling a simulated wheelchair. The training properties of the path, namely, its desired length, the extent of rotation, and narrowness, are optimized so as to deliver the desired training effects. We conducted an evaluation to validate the efficacy of the proposed virtual reality training approach. Users showed improvement in wheelchair control skills in terms of proficiency and precision after receiving the proposed virtual reality training.