Intent Detection for Virtual Reality Architectural Design

Abstract

In the context of optimization and reduction of cycles of product design in indus-try, digital collaborative tools have a major impact allowing an early-stage integra-tion of multidisciplinary challenges and oftentimes the search of global optimum rather than domain specific improvements. This paper presents a methodology for improving participants’ implication and performance during collaborative design sessions through virtual reality (VR) tools thanks to intention detection through body language interpretation and thus, reduction of cognitive workload. A proto-type of the methodology is being implemented based on an existing VR aided de-sign tool called DragonFly developed by Airbus. We will first discuss the choice of the different biological inputs to choose for our purpose, and how to merge these multimodal inputs in a meaningful way in order to ease further evolution and maintenance of our solution. Then, we will focus on the extraction of these inputs, their preprocessing, and the inference of intent and associated parameters. Finally, we will show the beginning of the application of this methodology to our specific use case of aircraft system installation.