Operational Safety in Human-in-the-loop Human-in-the-plant Autonomous Systems

TL;DR

This paper develops a unified human-in-the-loop and human-in-the-plant framework for ensuring safety in autonomous systems, integrating control theory, probabilistic models, and neural learning to handle human actions and real-world interactions.

Contribution

It introduces a novel HIL-HIP modeling approach combining control Lyapunov functions, Markov chains, fuzzy inference, and neural networks for safety-critical autonomous systems.

Findings

HIL-HIP controller successfully ensures safety in insulin delivery for Type 1 Diabetes.

The integrated model effectively handles human actions and real-world feedback.

Neural architectures can learn safety certificates in complex human-in-the-loop systems.

Abstract

Control affine assumptions, human inputs are external disturbances, in certified safe controller synthesis approaches are frequently violated in operational deployment under causal human actions. This paper takes a human-in-the-loop human-in-the-plant (HIL-HIP) approach towards ensuring operational safety of safety critical autonomous systems: human and real world controller (RWC) are modeled as a unified system. A three-way interaction is considered: a) through personalized inputs and biological feedback processes between HIP and HIL, b) through sensors and actuators between RWC and HIP, and c) through personalized configuration changes and data feedback between HIL and RWC. We extend control Lyapunov theory by generating barrier function (CLBF) under human action plans, model the HIL as a combination of Markov Chain for spontaneous events and Fuzzy inference system for event responses, the RWC as a black box, and integrate the HIL-HIP model with neural architectures that can learn CLBF certificates. We show that synthesized HIL-HIP controller for automated insulin delivery in Type 1 Diabetes is the only controller to meet safety requirements for human action inputs.