Abstract:
Quantum batteries promise ultrafast energy storage but are highly sensitive to noise, drift, and hardware constraints, making safe high-performance charging a central challenge for noisy intermediate-scale quantum devices. We propose a measurement-informed safe control framework that couples harmonic-spectrum-based syndrome diagnostics—H2/H1, H3/H1, and frequency drift—with a battery management system (BMS)-constrained curriculum reinforcement learning (RL) policy. Spectral features are compressed into a three-level syndrome code (s∈{0,1,2}) that serves as a real-time hardware risk proxy for the controller. Our digital-twin simulator incorporates T1/Tϕ relaxation, crosstalk, collective effects, and terminal-voltage dynamics, while safety risks are explicitly encoded as BMS-related penalties (state-of-health, voltage limits, and high-risk operation ratio) in the RL reward. Across staged curricula of increasing system complexity, the learned policy empirically traces a strictly improved Pareto frontier between final ergotropy and high-risk ratio compared to baseline and threshold-grid control strategies, with gains confirmed by multiseed statistical confidence intervals. To support near-term deployment, we position the current work as a digital-twin stage and outline a concrete simulation-to-real protocol: fix receiver-operating-characteristic-calibrated thresholds, retune (τw,τh) on a small hardware calibration split, and validate a one-step voltage shield. We further demonstrate the framework on a benchtop transmon setup with N=1–2, reporting shield trigger/violation rates, sim-to-real drift of spectral features Kullback–Leibler divergence/earth mover’s distance (KL)/(EMD), and an end-to-end latency within 20 μ s, indicating that harmonic-syndrome-informed safe RL is a viable route toward practical quantum battery charging control.