Posted in | News | Machine-Vision

Study Analyze the Quality of AI-Based Extended Reality Software Applications

The Universitat Politècnica de València is a partner in IV4XR (Intelligent Verification/Validation for Extended Reality-Based Systems), a multinational initiative whose major goal is to ensure the quality of Extended Reality (XR) software and applications, through its VRAIN Institute.

Study Analyze the Quality of AI-Based Extended Reality Software Applications.

Image Credit: Universitat Politècnica de València.

XR encompasses enhanced and mixed virtual reality; they are robust interactive systems in which the physical barrier between the user and the system is removed, and whose applications range from entertainment — two paradigmatic examples would be the games Pokemon Go and Star Wars: Squadrons — to virtual worlds/metaverse, training medical personnel or astronauts to gain knowledge on how to operate, industrial manufacturing, and shopping applications, among many others.

According to Beatriz Marín, a scientist at the UPV’s VRAIN Institute, there may be a fundamental aspect to XR systems: it is essential to ensure that all elements of these virtual worlds run properly so that users can have the best immersive and interactive experience possible, with no failures occurring during the program or game’s execution. This necessitates the development of robust testing tools, which do not yet exist.

In the industry, XR developers face a challenge today: XR is very complex and the interaction with the user is almost unpredictable; the level of interactivity and realism of these systems is increasing, which makes them very difficult and expensive to test. Normally, the evaluation and analysis of these systems is done manually, with tools that only work for simple test scenarios.

Beatriz Marín. Researcher, VRAIN Institute, Universitat Politècnica de València

Marín stated, “Thus, our goal is to automate this analysis, with an advanced testing tool that can respond to these challenges and help ensure the best possible user experience.” Tanja Vos, the main researcher at the UPV in IV4XR, Fernando Pastor, and Borja Davó make up the VRAIN team in this European project with Marín.

The IV4XR platform is built on Artificial Intelligence techniques and automatically provides an advanced tool for evaluating and exploring all of the parameters/agents of the virtual worlds generated by XR developers. It also incorporates socio-emotional AI algorithms for assessing the efficacy of the user experience via test agents.

IV4XR allows testing with three levels of agents: exploratory, socioemotional and functional goals. The platform is in charge of delivering the instructions to the agents for testing. The developer can create an interface with the framework of his application and, with this, carry out the testing automatically.

Beatriz Marín. Researcher, VRAIN Institute, Universitat Politècnica de València

At the end of the testing process, the platform provides the results of each of the agents, so that developers can correct possible failures before the XR system/program reaches the market,” adds Beatriz Marín.

The University of Utrecht (Netherlands), Gameware Europe (UK), Thales Six GTS (France), Thales AVS (France), the Bruno Kessler Foundation (Italy), Goodai Research Sro (Czech Republic), and the University of Umea (Sweden) are all part of the IV4XR project, which is led by the Institute of Systems and Computer Engineering of Portugal.

The project will be completed by the end of this year, thanks to funding from the European Union’s H2020 initiative.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.