On Using Formal Methods For Safe and Robust Robot Autonomy (Karen Leung, PhD Defense) скачать в хорошем качестве

On Using Formal Methods For Safe and Robust Robot Autonomy (Karen Leung, PhD Defense)

Karen Leung PhD Defense (7/22/2021) Advances in the fields of artificial intelligence and machine learning have unlocked a new generation of robotic systems—“learning-enabled” robots that are designed to operate in unstructured, uncertain, and unforgiving environments, especially settings where robots are required to interact in close proximity with humans. However, as learning-enabled methods, especially “deep” learning, continue to become more pervasive throughout the autonomy stack, it also becomes increasingly difficult to ascertain the performance and safety of these robotic systems and explain their behavior, necessary prerequisites for their deployment in safety-critical settings. In this talk, I will discuss how we can leverage techniques from the field of formal methods, namely Hamilton-Jacobi (HJ) reachability and Signal Temporal Logic (STL), to complement a learning-enabled robot autonomy stack, thereby leading to safer and more robust robot behavior. First, I will discuss how to leverage HJ reachability theory to produce minimally interventional safe control strategies for the robot whenever it is near safety violation. The approach is validated through human-in-the-loop simulation as well as on an experimental vehicle platform, demonstrating clear connections between theory and practice. Second, I will demonstrate how the language of STL may be utilized to incorporate designers’ domain expertise into a learning-enabled autonomy stack, thus providing a level of transparency and interpretability to otherwise opaque learned components.