Research Projects

Today a usual technique is to make a program and then to test it. But: program testing can be a very effective way to show the presence of bugs, but is hopelessly inadequate for showing their absence. (Edsger W. Dijkstra). The project idea is: Develop a methodology for resource efficient testing that does not sacrifice performance through the use of a combined model-free (RL) and model-based (AL) approach. In this project we will focus on the case of robotics, in particular, on autonomous mobile robots (AMRs). While the underlying project idea is not use case specific, focusing on AMRs gives us a concrete setting in which to develop and demonstrate the methodology. In the case of AMRs defining a test scenario involves defining the environment (e.g. obstacles and barriers) and how the robot interacts with the environment. This includes both static aspects (e.g. where barriers are located) and dynamic aspects (e.g. time dynamics of obstacles, how the robot moves through the environment). In addition, such test scenarios can have stochastic elements, for example, sensor values can have stochastic errors.