System Safety

System safety research focuses on ensuring the reliable and safe operation of complex systems, particularly those employing artificial intelligence (AI), by mitigating risks and preventing harm. Current research emphasizes developing robust safety monitoring mechanisms, often utilizing reinforcement learning, probabilistic forecasting (e.g., with Temporal Fusion Transformers), and deep learning for hazard detection and risk assessment across diverse applications like autonomous vehicles and robotics. This work is crucial for building trust and enabling the safe deployment of AI in safety-critical domains, impacting both the development of rigorous safety standards and the responsible integration of AI into society.