Papers

We present an LLM-driven, datasheet-aware framework for early-stage hardware compatibility verification that identifies documentation-level interface incompatibilities based on hardware datasheets and high-level component connectivity descriptions. It does not require, and can therefore be used, before detailed schematic simulation and implementation. We view trustworthy LLM-assisted design automation not as directly generating answers from documents, but as transforming engineering information through traceable verification stages. Given hardware datasheets and high-level component connectivity descriptions, the framework constructs a design graph that captures device connectivity and shared interaction domains, retrieves only the engineering properties required by explicit, domain-oriented verification criteria , and generates deterministic scripts for compatibility evaluation. By decomposing compatibility analysis into modular stages and preserving intermediate results, the framework reduces context overhead, improves transparency and tractability, enables scaling, and avoids reliance on LLMs for numerical computation. Evaluated on seven embedded-system designs comprising 34 datasheets, our framework achieves 97.5% compatibility-verification accuracy and an 8.6 times reduction in input context size compared with “upload-and-query” workflows. These results demonstrate the feasibility of LLM-assisted, specification-based hardware compatibility verification at an early design stage, as well as the need for, and substantial benefits of, modular task decomposition, formalized verification criteria, and task-aware compact context construction.

The proliferation of distributed energy resources (DERs) in distribution grids enables the active coordination of these assets to reduce costs and enable cleaner operations. Realizing this potential requires solving multiphase AC optimal power flow (AC-OPF) quickly across varying loads, DER availabilities, and topology reconfigurations, at much greater speed and scale than conventional nonlinear solvers. Learning-based surrogates can offer millisecond inference, yet existing methods target largely balanced transmission systems and do not scale to the multiphase, unbalanced, and reconfigurable nature of distribution feeders at utility scale. We present the Penalty + Sequential Linearized Feasibility Seeking (SLFS) algorithm, a self-supervised learning framework for multiphase distribution AC-OPF under switch-induced topology changes. Penalty+SLFS requires no labeled optimal solutions and trains directly from the AC-OPF objective and constraints through a differentiable fixed-point power flow solver, avoiding expensive label generation and admitting robust training procedures. Topology changes are handled efficiently using Sherman-Morrison-Woodbury updates of the admittance-matrix inverse, while an M-step Jacobian approximation accelerates differentiation through the power flow solver. At inference, SLFS repairs any infeasible predictions, providing feasibility guarantees with low computational overhead. On IEEE feeders ranging from 13 to 8,500 nodes, Penalty+SLFS achieves negligible optimality gaps and near-zero constraint violations, delivers up to three orders of magnitude speedups over IPOPT, and remains robust under large distributional shifts, demonstrating a viable path toward real-time, topology-aware AC-OPF for large-scale distribution grids.

The transition toward Open Radio Access Networks (O-RANs) is reshaping how cellular infrastructure is deployed, managed, and optimized. This paper investigates the energy-aware joint placement and migration of cloud-native functions (CNFs) in an O-RAN edge cloud. We consider both a Single-CU-UP association model and a slice-aware Multi-CU-UP relaxation, in which distinct slice-flow groups of the same distributed unit (DU) may be assigned to different Centralized Unit User Plane (CU-UP) processing targets under one Centralized Unit Control Plane (CU-CP). For brevity, these scenarios are referred to as Single-CU and Multi-CU, respectively; Multi-CU never denotes multiple CU-CP associations. We formulate the problem as a Mixed-Integer Linear Program (MILP) that minimizes server, transmission, wake-up, and migration energy while satisfying server-resource capacities and one-way delay requirements over the F1 user-plane interface (F1-U) between each DU and its selected CU-UP in a fat-tree edge data center. To improve computational scalability, we also develop a deterministic k-means-based heuristic that approximates the MILP decisions without requiring repeated exact optimization. Over the evaluated 24-hour workload, the theoretical Multi-CU relaxation reduces modeled energy consumption by 5.7% relative to the Single-CU baseline. For the Multi-CU case, the proposed heuristic remains within approximately 9.7% of the proposed MILP, demonstrating a favorable trade-off between energy efficiency and computational tractability.

Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant relaxation gaps. While the completely positive program (CPP) formulation closes this gap, it is NP-hard to solve. Its cheapest tractable relaxation, the doubly non-negative program (DNN), retains critical constraints as an SDP, but one whose size exceeds the reach of interior-point methods at practical scale. While Burer-Monteiro (BM) factorization has been applied to make SDP-based verification scalable, no such result exists for the strictly tighter DNN formulation. A key obstacle is that additional non-negativity constraints in the DNN cause dual multipliers for optimality certification to be non-unique, making standard certification methods inapplicable. We propose a novel eigenvalue maximization procedure that searches the non-unique multiplier space for a valid certificate, i.e. a global optimality guarantee. Experiments demonstrate that our approach $(\text{DNN})^2$ produces bounds consistently tighter than the standard SDP method, often matching the exact solution, and that our certification procedure confirms global optimality when a valid certificate exists. These results are a key step toward providing tight, certifiable, and computationally scalable verification guarantees needed to deploy neural network controllers and perception modules in safety-critical autonomous systems.

Self-improving LLM agents refine answers, not the process that produces those answers. Systems that add a meta-level hold that level fixed, and those that edit themselves must leave part of their own editing machinery untouched to stay stable, capping the meta-depth they realize at roughly two. We present Meta$^n$, which keeps the meta-operation fixed and recurses on its input instead. That operation, $\Omega$, is applied repeatedly to its own products, reading the traces of the solver stack below together with the code that produced them, then writing the next layer as a strategic pre-process and a library of callable helpers. Because $\Omega$ never changes, it cannot destabilize the system, and because its input strictly grows, each layer reasons from a higher vantage than the last. Depth is set by convergence rather than fixed in advance, and an evolutionary archive searches over layer chains. Across two backbones, Meta$^n$ outperforms prior self-improving agents on all eight benchmark families. The sharpest case is ARC-AGI-2, built to resist skill memorization, where it alone scores above zero. Ablations indicate that most of the gain from recursion comes from the conditioning each layer passes to the next, and distinct layer roles emerge with depth although no prompt prescribes them. Code available at https://github.com/minnesotanlp/meta-n

Linear programming (LP) formulations offer a conceptually elegant approach to infinite-horizon, model-free nonlinear optimal control in continuous spaces. However, in addition to the curse of dimensionality, their practical use is limited by the difficulty of consistently obtaining bounded solutions. In this work, we use moment-matching techniques to derive sufficient boundedness conditions in terms of the available dataset and the cost vector of the LP. Moreover, we discuss practical design methods for nonlinear systems and polynomial features.

This paper presents a neural operator-based approach for the output feedback boundary stabilization of reaction diffusion PDEs. The classical output feedback backstepping design requires solving control and observer kernel equations for each reaction coefficient. To avoid computing these kernel functions, the output feedback control law is reformulated as a causal boundary operator that maps the reaction coefficient and the boundary measurement to the boundary control input. A hybrid DeepONet-LSTM neural operator is proposed to approximate this causal operator, where DeepONet encodes the spatial coefficient and LSTM captures the temporal dependence of the measurement history. We analyze the Lipschitz continuity of the boundary operator and prove the closed-loop practical stability with the learned controller. A modified loss is also introduced to improve the temporal regularity of the learned boundary input. Numerical results illustrate that the proposed neural operator controller effectively stabilizes the system.

This paper presents a wideband power amplifier (PA) designed and implemented in Infineon Technologies' 130-nm SiGe BiCMOS process for upper W-band and lower D-band applications. A complete load-pull simulation methodology is carried out, and a band pass filter (BPF)-based matching strategy is employed for the design of the output and inter-stage matching networks. The fabricated PA prototype achieves a small-signal gain 3-dB bandwidth of 71-133 GHz. Moreover, it maintains a relatively flat gain of approximately 15.7 dB over 75-128 GHz, with less than 1-dB fluctuation. The measured saturated output power is 8.8-11.7 dBm, while the measured peak power-added efficiency (PAE) is 7.2-11.1%. These results demonstrate the potential of SiGe BiCMOS technology for wideband and integrated transmitter front ends operating across the W-/D-band frequency range.

This paper presents a compact, fully differential, two-stage millimeter-wave (mm-wave) cascode power amplifier (PA) designed and implemented in a 22nm FD-SOI CMOS process (22FDX+). The PA employs the newly introduced extended-drain MOS (EDMOS) device in 22FDX+, together with a carefully engineered device core and transformer baluns. At 50 GHz, the prototype achieves 18.8 dBm saturated output power (PSAT), 18.1 dBm 1-dB compression output power P1dB, and 21% power-added efficiency (PAE) at P1dB. To the best of our knowledge, this work achieves the highest reported power density of 2.6 W/mm2 among single-way, two-stage CMOS cascode PAs.

Approximate Linear Programming (ALP) is widely used for large-scale Markov Decision Processes (MDPs), but its performance can be sensitive to the choice of state-relevance weights, which are typically selected heuristically. Performance bounds suggest aligning these weights with the discounted occupancy measure of the induced policy, and existing primal approaches address this through repeated greedy-policy construction. Nonetheless, they lack convergence guarantees and are computationally expensive. We propose a dual-based method that uses projected occupancy information from the ALP dual solution to construct a smooth stochastic policy and update the state-relevance weights, which avoids separate greedy-action calculations. We establish conditions under which the weights match the discounted occupancy of the induced policy and prove uniqueness and global convergence under appropriate smoothing. We also derive an a posteriori policy-loss bound that separates error from the weighted Bellman residual, occupancy mismatch, and stochastic-versus-greedy disagreement. Experiments on classical queueing and multi-priority scheduling problems show that the proposed approach reduces sensitivity to fixed weights and achieves comparable or better policy quality than primal updates at lower computational cost. Finally, we show that adaptive weighting is most valuable when the basis functions are sufficiently expressive for occupancy information to influence the resulting policy.

Control invariance validates that dynamical systems have a control input that preserves a given property at all times. This paper introduces a set of sound axioms and proof rules in differential dynamic logic (dL) that enable verification of control invariance. First, the scalar and vector comparison principles, relating a system of differential equations to a comparison system such that invariance properties can be established more easily, are axiomatized in dL. This axiomatization primarily utilizes differential ghosts, which are proof-theoretic generalizations of comparison systems. Next, with the comparison principles serving as the basis, comparison invariants are introduced, and sound axioms and proof rules are derived. Comparison invariants reduce the question of control invariance to a functional inequality on its Lie derivative for a suitable class of functions, moreover, the right choice of function can result in decidable arithmetic. Furthermore, the perennially popular control barrier functions (CBFs) used in safety-critical control are shown to be a special instance of comparison invariants. This yields an axiomatization of CBFs that leads to a dedicated set of proof rules. The rules allow for the verification of CBFs, which are traditionally used for synthesizing safe controllers without verification. Lastly, comparison invariants are shown to unify several other safety verification techniques, including Darboux invariants and differential invariants, further cementing their versatility.

This paper theoretically analyzes how system model mismatch displaces finite-horizon maximum a posteriori (MAP) initial-state estimates in controlled dynamical systems under partial observation. From pathwise sensitivity analysis, the initial-state nominal-oracle displacement called MAP shift is decomposed into a model-side mismatch injection and an estimator-side curvature resistance to identify a sensor-dependent information-curvature margin as the amplification bottleneck. The margin is governed by the weakest posterior-curvature direction, so that sensor configurations that maximize aggregate information can still be fragile to mismatches. We connect the margin to nominal Gauss-Newton curvature and to the Bayesian Fisher information matrix, distinguishing instance-wise mismatch robustness from design-time inferability. The margin admits a computable nominal proxy in nonlinear systems, becomes explicit in the linear time-invariant case, and is validated through two numerical examples.

Predictive control based on an informative system trajectory, instead of a physics-based model, has received significant attention in recent years. This paper investigates the potential of using such data-driven control for vehicle dynamics control and autonomous path following. By considering the path following problem in the error space, the underlying system is approximately linear and existing results for data-driven predictive control can be applied. Also, scheduling based on longitudinal speed can be readily included. The proposed control algorithm was tested on two different lane change maneuvers in a high-fidelity simulation environment.

This paper describes the electricity markets and operational processes in the Irish power system and translates them into a Mixed Integer Linear Programming (MILP) model. The model is designed to estimate renewable generation Curtailment and Constraint. A full mathematical formulation is presented and tested on both a simple example and a realistic model of the Irish transmission network. The results show that the proposed formulation works as intended, capturing curtailment and constraint effects, while also highlighting model limitations and directions for future improvement.

We prove the rank-one Lyapunov spectral identity recorded as Problem 9.1 in the 2004 collection of unsolved problems in mathematical systems and control theory. Let $P,Q,R$ solve the coupled discrete Lyapunov and Sylvester equations associated with $A$ and its rank-one update $A_2=A+vw^\top$. When the displayed inverses exist, we show that $P^{-1}RQ^{-1}R^\top$ and $(I+PQ)^{-1}$ have the same characteristic polynomial. A rank-one determinant factorization of the equation for $Q$ produces a scalar bilinear kernel. Evaluating it at the eigenvalues of $A$ and at their reciprocals gives $RQ^{-1}R^\top=BQ^{-1}B=P-BPB$, after which the two target matrices are the same two factors in opposite order. Polynomial continuation extends the identity from a nonempty open set of admissible systems to the full admissible domain and yields a determinant corollary without stability assumptions; when the spectra of $A$ and $A_2$ are disjoint, $Z=b(A)^{-1}P$ gives an explicit similarity. In the Schur-stable realization setting, the result recovers the associated principal-angle and past/future canonical-correlation spectra.

The rapidly expanding scale of electric vehicle (EV) fleets and continuously decreasing battery costs are making vehicle-to-grid services a reality. In this paper, we study the interaction between the problems of an EV aggregator's bidding in the regulation market and power allocation (i.e., determining the (dis)charging powers of the EVs in regulation deployment). Although the two problems are coupled, they are often regarded as decoupled and optimized separately for complexity issues. However, failing to consider the coupling of bidding and power allocation can lead to a decline in the profit of the EV aggregator (EVA). In this paper, we propose a framework for co-optimizing EVA bidding and power allocation in the regulation market. The bidding model is formulated as a stochastic programming problem with embedded power allocation in discretized regulation signal scenarios. To meet the solution time requirement for regulation deployment, we further propose a power allocation model that can be solved online. It utilizes the Lagrange multipliers from the bidding problem to ensure that the allocation results correspond to the optimal solution of the bidding problem. The effect of the proposed framework on improving EVA profits and reducing degradation costs is verified in the case study.

The intricate mixed-integer constraints in industrial load models not only pose challenges for their direct integration into economic dispatch or market clearing processes but also render current analytical dimension-reduction methods ineffective. We propose a novel data-driven dimension-reduction approach for industrial load modeling, which uses the optimal energy usage data from industrial loads to train a dimension-reduced model that best fits the original constraints. Our approach, implemented by the adjustable load fleet model, outperformed analytical methods across three industrial load datasets.

An intelligent system does not merely reason: it governs its own reasoning - how much to compute, when to stop, which module to activate. Can that role be played by a dynamic internal field - a low-dimensional homeostatic state with explicit physics and certified stability - that modulates cognition without performing it? Ours is a field on the module graph governed by a family of PDEs on the graph Laplacian, advancing with an adaptive-depth reasoner. We certify the stability of the integrator of the whole family - an integrator certificate, not a closed-loop one. New, and proved here: a discrete Schur-Cohn criterion for Verlet with velocity coupling, necessary and sufficient per latent root, with no commutation hypothesis. The answer is threefold: substance no, structure only in part, certifiability yes. The type of the field's physics is irrelevant for accuracy: wave, diffusion, gated mixtures and a 2D Navier-Stokes substrate tie. A twenty-seed preregistered deconfounding campaign bounds the structural claim: at equalized caps the second-order effect is strong in one family (+0.087 [+0.042, +0.132], t=4.0) but is not detected in the other (+0.014 [-0.013, +0.040], n.s.), so part of the original contrast was capacity, not order; and a matched-interface GRU is indistinguishable in the first and nominally exceeds the field in the second (-0.035 [-0.067, -0.002]). What distinguishes the field is not capability but that its one-step operator admits an exact runtime stability check - a difference of kind, not of existence: learned recurrences carry certificates too, sufficient and conservative ones. A kill-gate with a positive control finds no evidence for the field as evidence accumulator (Delta AUC +0.0007 [-0.0065, +0.0079] vs a 0.03 threshold). A dynamic internal field is a viable, certifiable compute governor, but not an enhancer of cognition: it modulates, it does not think.

With the increasing penetration of electric vehicles (EVs), uncoordinated EV charging and the resulting chaos, disorder, and long waiting times at EV charging stations (EVCSs) will no longer be tolerable. An EV charging right (CR) is the right to reserve a predefined charging service. By purchasing CRs, EVs can reduce their charging waiting time, and the price of CRs can guide EVs toward optimized charging behaviors. In this article, we define CR, propose the CR trading mechanism (CRM), and analyze the effect of CRM on reducing waiting times and mitigating congestion in EV charging. In the proposed CRM, EVs can purchase CRs in advance, and the CRs are used to estimate the waiting time and update the price of charging. Queue theory is utilized in the waiting time estimation, in which the impact of disclosing queue states at EVCSs is considered for the first time. The simulation results verify the accuracy of the waiting time estimation and the effect of the proposed mechanism.

Modern energy management systems, even within advanced energy internet (EI) infrastructures, remain fundamentally reactive, optimization-bound, and incapable of reasoning about context, intent, or uncertainty. While the EI paradigm has established a powerful cyber-physical architecture for interconnecting distributed energy resources via software-defined packetized networks, the question of how such systems should think, adapt, and govern energy decisions intelligently remains an open challenge. This paper introduces cognitive energy management (CEM); a new conceptual framework that addresses this gap by redefining how energy systems perceive, reason, learn, and act within complex operational environments. Grounded in the EI cyber-physical foundation, CEM extends beyond conventional optimization by embedding goal-directed reasoning and continuous adaptation into the energy management loop, positioning itself as the cognitive governance layer of EI-based infrastructures. We formally define CEM, distinguish it from rule-based and optimization-based paradigms through structured comparison, and articulate its core architectural layers. To demonstrate the framework's practical value, we develop a toy problem grounded in smart port energy management; one of the most operationally demanding EI node environments in modern infrastructure. Specifically, we model a predictive vessel turnaround scenario in which a CEM-enabled system plans energy procurement, storage pre-charging, and load scheduling across a six-hour operational horizon. The demonstration illustrates how CEM moves the EI beyond feasibility-seeking toward intelligent, anticipatory energy governance.

The widespread idealization of road surfaces as horizontal planes can introduce significant inaccuracies into vehicle dynamics simulations, a phenomenon termed the “Flat Earth Error.” This article provides an expository guide to the use of classical differential geometry to model vehicular motion on curved surfaces. The influence of road curvature is characterized using the metric tensor, the second fundamental form, the shape operator, and the Christoffel symbols. Reproducible MATLAB scripts using an elliptic cone as a benchmark example illustrate the construction of geodesic curves and the simulation of particle dynamics on curved surfaces. The resulting geometric structures are integrated into a single-track vehicle-and-track model within a pseudospectral optimal control framework. Trajectory optimization results over a high-density mobile LiDAR profile of Darlington Raceway are used to generate a high-fidelity road-surface model. This model is used within an hp-adaptive collocation framework to investigate minimum lap time optimal control vehicular trajectories. These computations capture the non-smooth traction saturation limits of the tyres alongside position-dependent variations in gravitational forcing. Integrating differential geometry, multibody mechanics, and optimal control is essential for high-fidelity driven and autonomous vehicle-dynamics simulations. The optimized velocity and tyre slip profiles show that real-world racing track geometries induce dynamically significant three-dimensional effects. These results are particularly relevant to performance-limited simulations on highly banked track surfaces such as NASCAR ovals.

Industrial actor–critic methods usually represent continuous actions as anonymous numerical coordinates. They must therefore learn from limited interactions which process variables each action affects, in which direction, and after what delay. Fixed industrial documents already describe part of these relations, but their open-text statements neither represent the current operating condition nor directly fit a numerical policy. This article presents LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes (LCAE), which uses a large language model before training to normalize fixed documents into a frozen action–observation–direction–delay relation basis. Recent numerical action–response history then modulates the current strength of each relation, while the evaluated action forms a state-conditioned nonlinear action-effect field in the same basis. The critic evaluates actions through this field, and the actor uses the same relation gains to generate actions, making document semantics part of maximum-entropy policy learning. Neither the LLM nor the embedding model runs online during training or deployment; the deployed policy uses only frozen semantic artifacts and visible numerical history. The method states a falsifiable hypothesis: when documented relations are correct and recent history reflects their contextual strength, this action representation should provide a more useful decision bias than raw action coordinates.

This paper investigates the stabilization of complex networks via event-triggered pinning impulsive control in the presence of actuation delays. Unlike existing event-triggered impulsive control schemes that assume instantaneous implementation, the proposed framework explicitly accounts for the delay between event detection and impulse execution. By constructing suitable Lyapunov functions and analyzing the network dynamics during the delay intervals, explicit delay-dependent sufficient conditions are derived to guarantee asymptotic stability. The obtained conditions characterize the interplay among network topology, actuation delays, impulsive control gains, and triggering parameters. In addition, a strictly positive lower bound on inter-event times is established, which excludes Zeno behavior and ensures practical implementability. A topology-based criterion for selecting pinned nodes is also developed through a spectral condition on the network Laplacian. Numerical simulations on a network of coupled Chua circuits illustrate the design procedure and verify the effectiveness of the proposed method.

Controllability of nonlinear systems has been extensively studied by using the Lie algebra methods. Although local controllability can be proved, global controllability is in general hard to obtain even for bilinear systems. Recently, a new approach is developed to study controllability of bilinear systems by checking whether the reduced rank points corresponding to the bilinear terms form hyperplanes or hypersurfaces, so that near-controllability, in the global sense, can be algebraically verified once no hypersurface exists. In this paper, we show that there is a flaw in the algorithm for checking the reduced rank hypersurface germ condition (RRHGC) that some special cases are overlooked. We thus propose a new algorithm for testing the RRHGC based on a Darboux-polynomial characterization, which can be used to deal with all cases. An example is provided to demonstrate the proposed new algorithm.

Underactuated systems pose a challenge for convex motion planning because their dynamically feasible motions lie on a manifold of trajectories in function space. Building on our earlier formulation of polytopic action sets (PAS), this paper presents a method for rapidly generating, online, trusted convex sets of short-horizon actions for underactuated and potentially nonlinear systems. Around a nominal trajectory, we construct local finite-dimensional action coordinates in which each parameter vector encodes a complete nearby motion through an affine trajectory map, rendering collision-avoidance and control bounds linear. To remain consistent with the nonlinear dynamics, we introduce a dynamics-violation metric and extract a trusted convex inner approximation using an IRIS-inspired inflation procedure directly in action space. The resulting PAS are reusable convex families of actions that can be queried and composed with linear programs, and a PAS-guided tree expansion treats nodes as composed reachable families rather than single trajectories, coupling local nonlinear fidelity with convex reuse for longer-horizon planning. The planner solves cluttered planar scenes in tens of milliseconds (14-78x faster than a kinodynamic RRT baseline) and reduces terminal error on a nonlinear underactuated benchmark by 26-86% over sampling and NLP baselines.

Safety-aware motion planning remains a challenge in robotics, especially when missions are time-critical and are under complex specifications. In this paper, we propose safety-aware-stl-mppi, a computationally efficient sampling-based receding-horizon planning framework designed to promote satisfaction of constraints expressed in Signal Temporal Logic (STL). Our approach encodes discrete-time STL formulas into candidate time-varying control barrier functions (CBF), which are integrated into a model predictive path integral (MPPI) controller. Our method inherits the benefits of low computational cost from an efficiently parallelizable sampling based planner and utilizes CBF for constraints expressed in STL. We compare against several MPPI baselines using four artificial Mars Rover planning case studies with a diverse environment and cost setups, where we show our method consistently achieving high safety and efficiency. We show a quadcopter planning experiment with NVIDIA Isaac Lab.

Repetitive maritime operations can be effectively learned using the Imitation Learning (IL) paradigm, which transfers human expertise directly to Unmanned Surface Vehicle (USV) control systems. Dynamical Systems (DS) are widely used to model non-linear human demonstrations while offering inherent stability guarantees. However, real-world execution under persistent marine perturbations reveals a critical trade-off: standard DS-based IL approaches prioritize global target convergence at the expense of localized trajectory reproduction fidelity. To address this limitation, we present a hybrid learning-control architecture that integrates a DS-based IL reference generator with a neuroadaptive controller. Our approach introduces a control action that drives the USV back to the demonstrated path following exogenous disturbances, enabling dynamic human-like reactive alignment-termed behavioral tracking. The proposed methodology is validated using the Marine Systems Simulator (MSS) toolbox. Simulation results confirm that the framework generalizes complex maneuvering tasks while substantially improving trajectory tracking fidelity under disturbances compared to alternative control strategies.

We consider a federated reinforcement learning setting involving $M$ agents, all of whom interact with a common Markov Decision Process (MDP). The agents exchange information via a central server to learn the optimal value function. Our goal is to understand to what extent one can hope for collaborative sample-complexity speedups in such a setting, when a small fraction of the agents are adversarial and can act arbitrarily. To that end, we propose Robust Fed-Q}, a federated Q-learning algorithm that blends ideas from both model-based and model-free RL, along with the median-of-means device from robust statistics. We prove that despite corruption, with high-probability, Robust Fed-Q (i) guarantees exact convergence to the optimal value function in the limit of infinite samples, and (ii) enjoys near-optimal finite-time rates that benefit from collaboration. In addition, our approach requires just $\tilde{O}(1)$ rounds of communication to achieve each of the above guarantees, a feature of independent interest in FL where communication is the major bottleneck.

Real-time optimization (RTO) relies on process models to locate economically optimal operating conditions. Because developing first-principles models requires significant process knowledge, data-driven alternatives are increasingly attractive. Modern machine-learning models can fit historical plant data accurately and often pass standard validation tests. Whether such models can be trusted for economic optimization, however, remains unclear. We investigate this question using a vinyl acetate monomer benchmark process with a unique, well-conditioned economic optimum. We train a structured hybrid model that combines known mass balances and thermodynamics with a neural-network closure for unknown kinetics, and a fully data-driven neural ordinary differential equation (ODE) model. Both models reproduce plant measurements accurately and exhibit little variation in predictions across random initializations. Yet their economic optima differ substantially from that of the plant. Where the plant returns a single optimum on multistart search, the trained models return many phantom optima. We further show that the training optimizer alone can be yet another source of error. Even with noise-free data and initialization at weights that recover the plant optimum, stochastic gradient training can drift to weights that yield substantially worse RTO solutions. The identified model is thus an artifact of the training optimizer as well as the data. These results demonstrate that a good predictive fit of all available measurements does not guarantee reliable economic performance. A data-driven model for RTO should at least be required to recover the optimum on a decision-oriented benchmark like the one developed here before being considered for plant testing and application.

This paper proposes a critical weather scenario screening framework for identifying weather conditions that can trigger high-voltage (HV) events in the power grid. Unlike conventional weather-aware contingency analysis limited to component-level outage risk, our framework screens weather scenarios as potential drivers of grid-level voltage violations. Given a non-critical weather scenario, we seek the perturbation over the high-dimensional weather space to maximize a pre-defined voltage criticality score, by using a differentiable weather-to-voltage (W2V) predictive model to facilitate the gradient update over a compact latent space. Specifically, a non-negativity constraint is used for achieving physically-consistent perturbations, with another L1-norm based constraint for bounded perturbation. The latter could promote sparse and interpretable perturbations, and this uniform budget also yields a sensitivity-aware vulnerability ranking across different weather scenarios. Numerical experiments on a 6717-bus synthetic Texas system have effectively demonstrated the potential of weather uncertainty in triggering HV events, and this potential cannot be represented by the voltage analysis of individual weather scenarios. Interestingly, the most vulnerable scenarios are characterized by wind-dominated perturbation patterns concentrated in high wind-capacity regions, coinciding with observations from actual power flow data and experiences in real system operations.