Model Learning for Adjusting the Level of Automation in HCPS

2025-11-18

AI Summary

To address safety and controllability challenges arising from increasing automation levels in human–machine collaborative systems, this paper proposes a model-based learning framework for exploring safety-aware shared control policies during design. Methodologically, it integrates active automata learning—extracting finite-state abstractions of human behavior from simulations—with reactive synthesis via game-theoretic reasoning, implemented and formally verified in UPPAAL, enabling iterative refinement of human models and dynamic adjustment of automation levels. Its key contribution is the first integration of active learning with reactive synthesis to establish a closed-loop co-design of human behavioral modeling and control policy generation. Experimental evaluation in a simplified driving scenario demonstrates that the framework automatically identifies safe control strategies or pinpoints deficiencies in human models and bottlenecks in system action constraints, thereby significantly enhancing the verifiability and adaptability of human–machine cooperative driving systems.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Behavior Learning & Control

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

The steadily increasing level of automation in human-centred systems demands rigorous design methods for analysing and controlling interactions between humans and automated components, especially in safety-critical applications. The variability of human behaviour poses particular challenges for formal verification and synthesis. We present a model-based framework that enables design-time exploration of safe shared-control strategies in human-automation systems. The approach combines active automata learning -- to derive coarse, finite-state abstractions of human behaviour from simulations -- with game-theoretic reactive synthesis to determine whether a controller can guarantee safety when interacting with these models. If no such strategy exists, the framework supports iterative refinement of the human model or adjustment of the automation's controllable actions. A driving case study, integrating automata learning with reactive synthesis in UPPAAL, illustrates the applicability of the framework on a simplified driving scenario and its potential for analysing shared-control strategies in human-centred cyber-physical systems.

Problem

• Designing safe human-automation interactions in cyber-physical systems
• Addressing human behavior variability for formal verification challenges
• Developing shared-control strategies through automata learning and reactive synthesis

Innovation

• Combines automata learning with game-theoretic synthesis
• Derives human behavior models from simulation data
• Iteratively refines models for safety guarantees