Verify, Augment, Improve: Self-Adaptation Repair via Automated Knowledge Augmentation from Mistakes

Abstract

Cyber–Physical Systems (CPSs) operate under uncertainty and cannot always guarantee the satisfaction of dependability requirements. Proactive self-adaptation mitigates violations by planning corrective actions, often leveraging predictive models. These models can be inaccurate in underrepresented regions of the operational space, leading to ineffective or unsafe adaptations. We present Verify, Augment, and Improve (VAI), a framework that extends a standard MAPE–K architecture with an asynchronous self-improving loop. VAI intercepts ineffective adaptation actions and turns explanations from a descriptive aid into a mechanism for continual improvement of the self-adaptation process. Specifically, each ineffective adaptation is verified against a ground truth (e.g., a high-fidelity simulator); when a drift between surrogate and ground truth is detected, VAI explains the failure, augments the training data near the drift, and retrains the surrogate. We instantiate VAI on a human–machine teaming benchmark and two study subjects adopting alternative ground truths. Experimental results show that VAI consistently reduces the relative error of adaptation decisions and increases the success rate of meeting requirements, with average gains of \(6.89\%\) and \(10.88\%\) across the two selected subjects.