Blog

AI in Games: Use Case for Intelligent Autonomous Test Agents

December 05, 2022

iv4XR consortium members Angelo Susi (left) from FBK, and Pedro Fernandes (center) from INESC

GoodAI showcased results of a pilot for automated testing tools at VRday Europe’s Immersive Tech Week. Carried out under the auspices of EU grant project iv4XR, the use case aimed to develop artificial intelligence agents to support the automation of extended reality (XR) systems testing.

“Extended Reality” (XR) systems are advanced interactive systems such as Virtual Reality (VR) and Augmented Reality (AR) systems. They have emerged in various domains, ranging from entertainment, cultural heritage, to combat training and mission critical applications.

Testing of XR systems is currently done manually, which entails a lot of human time and effort. The process is overly expensive, slow and difficult to scale, and can impede development when new functionalities are added to software. 

IV4XR’s solution is an agent-based framework. Systems under test are connected to the framework to provide the interface for the AI agents to work within. A testing task is formulated as a set of goals for a test-agent to achieve and a set of tactics guide the performance.

GoodAI’s pilot utilized Space Engineers (SE) for its test bed. In this experimental integration of SE to the iv4XR framework, a plugin was developed to assist testers learning how to create agents for their cases. Preliminary findings indicated notable time savings: 28 testing hours saved, with another 68 hours to save after all cases are implemented.  

iv4XR is an EU grant project made up of large and SMEs representing the XR industry, universities, and research institutes. The consortium combines decades of expertise in advanced interactive systems, AI, and software engineering. 

Members include INESC-ID (Portugal), the University of Utrecht (Netherlands), Fondazione Bruno Kessler (Italy), the Universitat Politècnica de València (Spain), GoodAI (Czech Republic), Gameware Europe Limited (UK), Thales SIX GTS (France), Thales AVS France, and Umeå University (Sweden).

 


To date, most of what we consider general AI research is done in academia and inside big corporations. GoodAI strives to combine the best of both cultures, academic rigor and fast-paced innovation. We aim to create the right conditions to collaborate and cooperate across boundaries. Our goal is to accelerate the progress towards general AI in a safe manner by putting emphasis on community-driven research, which in the future might play a key role in preventing the monopolization of AI technology (see AI race).

If you are interested in Badger Architecture and the work GoodAI does and would like to collaborate, check out our GoodAI Grants opportunities or our Jobs page for open positions!

For the latest from our blog sign up for our newsletter.

Leave a comment

Join GoodAI

Are you keen on making a meaningful impact? Interested in joining the GoodAI team?

View open positions