Abstract
Testing augmented or virtual reality (AR/VR) products entails the integration of numerous disparate devices that generate performance indicators that require specialized sub-domain knowledge to interpret. Developers working on specific modules may not fully understand the entire workflow, leading to inefficient and inaccurate testing. This disclosure describes artificial intelligence (AI) techniques that parse test descriptions and configurations specified in natural language to convert them into prompts that invoke AI models. The techniques also enable AI-powered analysis of KPIs generated by the testing platform by leveraging present and previous test results. The techniques accelerate the integration of a testing platform into a testing workflow; invoke tests via natural language; create/modify workflow to customize the KPIs and tasks in execution; parse the generated KPI to identify and seek root causes for anomalies; etc. Testing is made intuitive, automatic, and accurate.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Chen, Yang; Guo, Chao; Yuan, Sean; Lu, Chen; and Jia, Luke, "Artificial Intelligence Driven Automated Device Testing Using a Robotic Platform", Technical Disclosure Commons, (January 17, 2025)
https://www.tdcommons.org/dpubs_series/7737