The gaming industry is an important part of today’s economy. Statistically, many quality issues are found by users in released products or updates. One reason for this is that testing methods from general software development cannot be transferred to test visual outputs without significant human effort. This work focuses on a major problem in this area, namely testing the correctness of the images displayed by cameras in relation to the content of the environment they are intended to see. The techniques used are a combination of state-of-the-art computer vision methods adapted to our specific use cases. Evaluation is performed in a well-known soccer game engine and shows that the proposed methods have the potential to significantly reduce manual work and development costs while improving product quality.

By using Robotic Process Automation (RPA), repetitive processes in companies can be automated and executed with intelligent software agents. These agents are able to run such processes without human effort and with less error-proneness. RPA has gained significant traction in recent years and is being used by many companies to reduce internal costs and achieve a higher return on investment (ROI). In our literature review, we found that there is a gap in the testability of RPA workflows. In this paper, we focus on addressing this gap using concolic execution (also referred to as online symbolic execution in the literature). First, we explore how previous work in the literature on concolic execution can be reused for the RPA domain and we implement a prototype. Then, we evaluate our open source solution for adapting concolic execution to the RPA context, using real-world use cases and best practices.