Browsing by Author "Sandbrook, Ben"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Immersive Cross-platform X3D Training: Elevating Construction Safety Education
    Roofigari-Esfahan, Nazila; Polys, Nicholas F.; Johnson, Ashley; Ogle, J. Todd; Sandbrook, Ben (ACM, 2023-10-09)
    A multi-platform Virtual Reality (VR) approach is proposed to complement the traditional approaches for construction safety training. Visual simulations of a highway construction project were developed and presented through the developed platforms, aiming at giving students immersive experience of actual construction environments. The simulated worksite scenarios included active traffic, multiple worker roles and heavy equipment, and was rendered at different times of day and weather conditions. We used this material in an undergraduate class activity with 50 students. During a session in our visualization lab, students experienced the scenarios presenting day shift, afternoon shift with adverse weather and night shift and were asked to develop daily report of their job site observation. The scenrios were presented via the following platforms: TV projection, Mobile Phone, Head-Mounted Display (HMD), and CAVE projection room. The results demonstrates that the multi-platform immersive experience has the potential to significantly improve hazard recognition skill of construction students.
  • Thumbnail Image
    Prompt Engineering for X3D Object Creation with LLMs
    Polys, Nicholas; Mohammed, Ayat; Sandbrook, Ben (ACM, 2024-09-25)
    Large Language Models (LLMs) are a new class of knowledge embodied in a computer and trained on massive amounts of human text, image, and video examples. As the result of a user prompt, these LLMs can generate generally coherent responses in several kinds of media and languages. Can LLMs write X3D code? In this paper we explore the ability of several leading LLMs to generate valid and sensible code for interactive X3D scenes. We compare the prompt results from three different LLMs to examine the quality of the generated X3D. We setup an experimental framework that uses a within-subjects repeated-measures design to create X3D from text prompts. We vary our prompt strategies and give the LLMs increasingly challenging and increasingly detailed scene requests.We assess the quality of the resulting X3D scenes including geometry, appearances, animations, and interactions. Our results provide a comparison of different prompt strategies and their outcomes. Such results provide early probes into the limited epistemology and fluency of contemporary LLMs in composing multi-part, animate-able 3D objects.