The quality of AI-based extended reality software applications

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

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/metavers, the training of medical personnel or astronauts to acquire knowledge on operation, industrial manufacturing and purchasing applications, among others.

According to Beatriz Marín, scientist at the VRAIN Institute of the UPV, there can be a fundamental aspect to XR systems: it is essential to ensure that all the elements of these virtual worlds work correctly so that users can have the best possible immersive and interactive experience, without any failures occurring during the execution of the program or the game. This requires the development of robust testing tools, which do not yet exist.

In the industry, XR developers today face a challenge: XR is very complex and user interaction is almost unpredictable; the level of interactivity and realism of these systems increases, 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 Marine. Researcher, VRAIN Institute, Universitat Politècnica de València

Marine said:So, our goal is to automate this analysis, with an advanced testing tool that can address 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 form the VRAIN team in this European project with Marín.

The IV4XR platform is built on artificial intelligence techniques and automatically provides an advanced tool to evaluate and explore all parameters/agents of virtual worlds generated by XR developers. It also integrates socio-emotional AI algorithms to assess the effectiveness of user experience through test agents.

IV4XR allows testing with three levels of agents: exploratory, socio-emotional and functional objectives. The platform is responsible for issuing the instructions to the agents for the tests. The developer can create an interface with the framework of his application and, with this, perform the tests automatically.

Beatriz Marine. 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 the developers can correct possible failures before the XR system/program reaches the market.adds Beatriz Marín.

Utrecht University (Netherlands), Gameware Europe (UK), Thales Six GTS (France), Thales AVS (France), 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 Computer Systems and Engineering in Portugal.

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


Comments are closed.