The field of control systems is moving towards developing more robust and safe control methods, particularly in the context of neural network-controlled cyber-physical systems. Researchers are exploring new approaches to ensure the safety and reliability of these systems, including the development of safety governors and robust control synthesis frameworks. One of the key challenges being addressed is the issue of finite precision and its impact on the safety guarantees of these systems. Noteworthy papers in this area include:

• A safety governor for learning explicit MPC controllers from data, which proposes a novel learning-based explicit MPC structure and constructs a safety governor to ensure that learning-based explicit MPC satisfies all state and input constraints.
• Of Good Demons and Bad Angels: Guaranteeing Safe Control under Finite Precision, which bridges the gap between theoretical guarantees and real-world implementations by incorporating robustness under finite-precision perturbations into the safety verification.