Quantitative Predictive Monitoring and Control for Safe Human-Machine Interaction
This addresses safety-critical issues in domains like healthcare and transportation, though it appears incremental as it builds on existing predictive monitoring and control frameworks.
The paper tackles the problem of unsafe human-machine interaction by proposing a quantitative predictive monitoring and control approach that accounts for human uncertainty, using Signal Temporal Logic with Uncertainty (STL-U) to compute robustness intervals and adaptive control methods. Experiments on Type 1 Diabetes management and semi-autonomous driving show improvements in safety and effectiveness.
There is a growing trend toward AI systems interacting with humans to revolutionize a range of application domains such as healthcare and transportation. However, unsafe human-machine interaction can lead to catastrophic failures. We propose a novel approach that predicts future states by accounting for the uncertainty of human interaction, monitors whether predictions satisfy or violate safety requirements, and adapts control actions based on the predictive monitoring results. Specifically, we develop a new quantitative predictive monitor based on Signal Temporal Logic with Uncertainty (STL-U) to compute a robustness degree interval, which indicates the extent to which a sequence of uncertain predictions satisfies or violates an STL-U requirement. We also develop a new loss function to guide the uncertainty calibration of Bayesian deep learning and a new adaptive control method, both of which leverage STL-U quantitative predictive monitoring results. We apply the proposed approach to two case studies: Type 1 Diabetes management and semi-autonomous driving. Experiments show that the proposed approach improves safety and effectiveness in both case studies.