Cognitive-Flexible Control via Latent Model Reorganization with Predictive Safety Guarantees

TL;DR

This paper introduces a control framework that adaptively reorganizes latent representations in real-time to maintain safety and performance in systems experiencing abrupt changes, using a Bayesian MPC scheme with formal guarantees.

Contribution

It proposes a novel cognitive-flexible control framework with an adaptive latent model and safety guarantees, addressing limitations of fixed representations under distributional shifts.

Findings

Demonstrates safe adaptation of latent representations during abrupt system changes

Provides formal guarantees on stability, feasibility, and bounded posterior drift

Shows rapid performance recovery in simulation scenarios

Abstract

Learning-enabled control systems must maintain safety when system dynamics and sensing conditions change abruptly. Although stochastic latent-state models enable uncertainty-aware control, most existing approaches rely on fixed internal representations and can degrade significantly under distributional shift. This letter proposes a \emph{cognitive-flexible control} framework in which latent belief representations adapt online, while the control law remains explicit and safety-certified. We introduce a Cognitive-Flexible Deep Stochastic State-Space Model (CF--DeepSSSM) that reorganizes latent representations subject to a bounded \emph{Cognitive Flexibility Index} (CFI), and embeds the adapted model within a Bayesian model predictive control (MPC) scheme. We establish guarantees on bounded posterior drift, recursive feasibility, and closed-loop stability. Simulation results under abrupt changes in system dynamics and observations demonstrate safe representation adaptation with rapid performance recovery, highlighting the benefits of learning-enabled, rather than learning-based, control for nonstationary cyber--physical systems.