321 papers
The paper introduces the Frequency-Separable Hamiltonian Neural Network (FS-HNN), a novel architecture that decomposes Hamiltonian functions into distinct fast and slow modes trained on different timescales to overcome the spectral bias of existing methods and significantly improve long-horizon extrapolation for multi-timescale dynamical systems and PDEs.
This paper introduces CLAIRE, a hybrid deep learning framework that combines unsupervised latent representation learning with supervised classification and game-theoretic interpretability to achieve robust, explainable fault detection in high-dimensional industrial environments.
This paper introduces "control barrier corridors," a unified framework that converts control barrier functions into local safe goal regions to bridge the gap between functional safety filtering and geometric safe motion planning, enabling verifiably safe and persistent path following in complex, unknown environments.
This paper proposes an adaptive data-driven min-max model predictive control scheme for discrete-time linear time-varying systems that utilizes online input-state data to update state-feedback gains via semidefinite programming, ensuring exponential stabilization and constraint satisfaction for both noise-free and noisy scenarios.
This paper extends a hardware-efficient hybrid digital-analog RIS architecture by proposing a pragmatic phase-only beam design for hierarchical codebooks and a low-complexity multiuser MIMO framework that achieves high spectral efficiency under realistic mmWave multipath channels while maintaining full compliance with 3GPP 5G NR standards.
This paper presents a novel uncertainty-aware adaptive dynamics framework for underwater vehicle-manipulator systems that employs moving horizon estimation with convex physical constraints to achieve rapid, online parameter convergence and high-fidelity modeling, as validated by experiments on a BlueROV2 Heavy platform.
This paper proposes a method for efficiently estimating interference graphs in wireless sensor networks by integrating the process with concurrent flooding through transmit power control, thereby eliminating the need for separate, resource-heavy measurement tasks on commercial off-the-shelf devices.
This paper proposes DDKL-PT, a distributed data-driven framework where multi-agent systems achieve consensus on global dynamics by exchanging local deep Koopman model estimates derived from private partial trajectories, enabling accurate model predictive control without sharing raw training data.
This paper proposes a robust stabilization framework for linear Markov-jumping hyperbolic PDEs by combining backstepping control with neural operator approximations, proving mean-square exponential stability under parameter uncertainty and validating the approach through freeway traffic control simulations.
The paper presents SHIELD, a host-independent framework that leverages deep filesystem features parsed at the storage controller level to achieve tamper-resistant, real-time ransomware detection and mitigation with over 97% accuracy and minimal impact on benign applications.
This paper challenges the prevailing view that selectivity in State Space Models requires time-varying dynamics by introducing the Geometric SSM, which leverages geometric control theory to achieve selective pattern recognition and superior performance on induction tasks while maintaining efficient Linear Time-Invariant (LTI) properties.
This paper proposes a novel multi-agent reinforcement learning algorithm that enhances sample efficiency by combining a decomposed centralized critic with a diversity-regularized ensemble for uncertainty-guided selective exploration, a truncated TD() variant for reduced-variance off-policy learning, and a mixed-sample actor training approach to balance stability and efficiency.
This paper utilizes contraction theory to establish that semicontraction in the observable space is a sufficient condition for different network structures of nonlinear dynamical systems, such as Kuramoto oscillators, to become indistinguishable when only partial nodal measurements are available.
This paper investigates the limitations of uniquely identifying network structures in linear dynamical systems from partial measurements by characterizing the space of consistent networks through observability properties, demonstrating that observing over 6% of nodes in random networks achieves approximately 99% edge classification accuracy while linking structural identifiability to the spectral properties of an augmented observability Gramian.
This paper presents a lightweight, model-free approach for real-time slip detection and tire-road friction coefficient estimation in autonomous racing that relies solely on IMU, LiDAR, and control inputs, demonstrating accurate performance across varying friction levels without requiring complex models or training data.
This paper proposes a framework for managing conflicts between concurrent xApps in Open RAN by combining explainable machine learning and causal inference to identify conflicting control parameters, model their interactions via causal graphs, and quantify their impacts on network performance.
This paper proposes a scalable multi-period sparse optimization method that leverages circuit-theory formulations and persistency constraints to proactively identify persistent vulnerability locations across a sequence of power grid blackouts under increasing stress, thereby enhancing system resilience through early warning diagnosis.
This paper proposes and experimentally validates a conductive amplitude and phase matrix framework that enables the emulation of multiple targets with arbitrary radar profiles for testing integrated sensing and communication (ISAC) base stations equipped with large-scale antenna arrays using radar target simulators with limited interface ports.
This paper proposes a semantics-guided fuzzy control framework that leverages Large Language Models to compress multimodal observations into interpretable tokens for robust, GPS-denied underwater navigation and semantic communication-based coordination among multi-robot swarms.
This paper introduces two novel rate-and-state-dependent friction models within the Friction with Bristle Dynamics (FrBD) framework based on Generalized Maxwell and Generalized Kelvin-Voigt viscoelastic elements, demonstrating that they satisfy boundedness and passivity for any physically meaningful parameters and illustrating their utility for control design in robotics.