Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

Semantically Enabled Assessment in Virtual Environments (SAVE)

Principal Investigators:  Christian Greuel , Karen Myers

Mailing address:
AI Center
SRI International
333 Ravenswood Avenue
Menlo Park, CA 94025-3493

AIC Program:  Impact Group

   Project Description

Virtual environments (VEs) provide an appealing vehicle for acquiring procedural skills, particularly in domains where real-world training incurs significant time, expense, or risk. Taking full advantage of VEs, however, requires mechanisms to assess learner performance. SRI International is developing a framework for Semantically Enabled Automated Assessment in Virtual Environments (SAVE), which can observe a learner operating within an instrumented VE, assess learner performance, and provide helpful feedback to improve learner skills. The key to enabling automated assessment is understanding what the user is doing. Our approach to achieving such understanding of learner activity involves a semantic characterization of the VE and operations performed within it. The 3D models used in current-generation VEs lack such semantic information, being limited to geometric meshes that define the basic spatial structure and visual appearance of objects. Within SAVE, we draw on ontologies to augment this core visual information with properties and relations among objects. This ontological grounding provides the means to bridge the gap between the graphical components of the VE and the instructional models used to drive assessment. The assessment component analyzes semantic traces of learner actions within the VE to provide contextually relevant feedback. In contrast to assessment tools that address “algorithmic” skills, which have a single or small number of acceptable responses, our capability is designed to accommodate more open-ended procedural skills for which there can be a range of acceptable solutions with significant variation among them. Deploying SAVE for a given training domain requires creation of background models and content: semantic overlays for 3D models and scene graphs (at the VE level) as well as characterizations of solutions to training exercises (at the instructional level). SAVE plans to include tools that enable developers to create this material, leveraging the visual nature of the VE to provide a natural, easy-to-use authoring environment.


Name Title E-mail
Denker, Grit Senior Computer Scientist
Gervasio, Melinda Principal Scientist
Jones, Chris Sr. Software Engineer
Wessel, Michael A Computer Scientist

  • Christian Greuel and Karen Myers and Grit Denker and Melinda Gervasio. Assessment and Content Authoring in Semantic Virtual Environments. Proceedings of the Interservice/Industry Training, Simulation and Education Conference (I/ITSEC), 2016.  [PDF, Details]

SRI International
©2017 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy