SBIR Phase I: MuukTest Artificial Intelligence Powered Software Testing

Award ID: 2016187

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project will enable non-technical users to create complete and comprehensive software test automation. Additionally, it will enable growing software companies to ship their products faster with higher quality at a reasonable cost. Currently, these companies spend up to 50% of their resources on quality assurance (QA) and testing. This project will develop an automated process for testing software. This Small Business Innovation Research (SBIR) Phase I project will combine symbolic reasoning algorithms, deep learning, and reinforcement learning models to automate software quality assurance testing. The two problems being addressed by this project are (1) software development teams spend up to 50% of their time testing software, and (2) they have to hire skilled software engineers to automate these tests. The objective of this research is to use artificial intelligence (AI) to make software quality assurance testing faster and enable non-technical workers to create sophisticated tests without the need to code. The proposed research aims to create an AI prototype by (i) building a baseline of manual test scenarios, (ii) building tests using symbolic reasoning (SR), (iii) incorporating deep learning, and (iv) adding reinforcement learning to generate tests. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Peter Atherton