WATCHER: Machine Learning and Defect Analysis for Detection of Latent Errors in Combat System Software Navy SBIR FY2018.1 Sol No.: Navy SBIR FY2018.1 Topic No.: N181-068 Topic Title: WATCHER: Machine Learning and Defect Analysis for Detection of Latent Errors in Combat System Software Proposal No.: N181-068-0860 Firm: Edge Case Research, LLC 100 43rd St, Suite 208 Pittsburgh, Pennsylvania 15201 Contact: Michael Wagner Phone: (412) 606-3842 Abstract: The opportunity for programs like AEGIS is not only in their voluminous test data, but also the vast amounts of data from prior software quality assurance (SQA) activities. By applying machine learning, these data will allow AEGIS and other programs to: 1. Detect latent errors in combat systems based on extremely complex software, 2. Develop meaningful test coverage metrics for MIL-STD-882E risk analysis, 3. Proactively target automated robustness testing to address residual risks, 4. And, ultimately, to improve cost effectiveness of Navy integration efforts. Phase I of our project will define pattern-recognition algorithms inspired by machine-learning techniques from natural-language processing, deep learning, and defect analysis. We will determine the feasibility of these algorithms based on representative data sets provided by the AEGIS program office and available via open source repositories, identified in collaboration with AEGIS program personnel at Lockheed Martin Rotary and Mission Systems (LM RMS). These data sets may be augmented with test data already available to the Switchboard automated-testing platform maintained by Edge Case Research. In collaboration with LM RMS, we will produce a capabilities description document and a roadmap showing how AEGIS SQA processes can adopt our technology starting with prototypes in Phase II. Benefits: The need for more cost-effective technologies for software quality assurance and verification is widespread and growing. As an ever-increasing number of large-scale Navy integration efforts are planned and underway on AEGIS and beyond, costs will rise dramatically if automated capabilities are not deployed to multiply the expertise of engineers, developers, and testers. Unfortunately, many automated capabilities are limited in scope (e.g., focusing only on source-code analysis) and prone to false positives. A capability like WATCHER holds the promise of providing substantial cost savings and making more even more complex reliable systems possible. Combining the DoD�?Ts focus on Third Offset capability with rapid innovation in the commercial sector, the growth in tactical unmanned systems over the next decade will be substantial. Automation provided by tools such as WATCHER are essential to achieving this level of growth: the complexity and risk involved is too great for conventional manual SQA processes. The encompassing functionality of WATCHER �?" it�?Ts not just a test-analysis tool, it�?Ts an SQA platform �?" positions ECR with an opportunity build an intelligent development platform in which all DoD innovation can take place. Like this defense-focused strategy, a comprehensive, intelligent, and automated SQA platform for commercial markets such as autonomous vehicles can address a huge potential market. Return