Syed Pouladi

Syed Pouladi

Learning-based dynamical models face a persistent tension between expressiveness and formal guarantees: richer model classes improve predictive accuracy, but their stability properties are typically verified only empirically, if at all. This paper proposes \emph{Stable Fiber-Koopman Residual Dynamics} (SFKD), a unified framework that simultaneously addresses environment-aware geometric consistency, latent-space stability certification, and bounded residual perturbation propagation. Concretely, SFKD constructs a fiber bundle latent manifold whose fibers encode environment-specific dynamics; an environment-conditioned Koopman operator governs the dominant linear evolution on each fiber; and a contraction-constrained residual neural network captures unmodeled nonlinear effects while admitting an explicit input-to-state stability (ISS) certificate. The resulting model is embedded in a sampling-based MPPI controller for autonomous vehicle path tracking under variable surface conditions and wind disturbances. Theoretical analysis establishes ISS of the latent dynamics and a finite ultimate bound on tracking error. Numerical experiments against five baselines -- Koopman MPC, Neural ODE, ICODE, ControlSynth, and ICODE-MPPI -- demonstrate a 31\% reduction in tracking RMSE, a 44\% improvement in control smoothness, and near-zero latent stability violation rate across environment-switching scenarios.

Syed Pouladi

This paper addresses the problem of nonlinear state estimation for dynamical systems whose governing equations are approximated through Koopman operator liftings. While Koopman-based predictors have demonstrated broad approximation capability for nonlinear dynamics, certifying observer convergence under model mismatch and measurement noise has remained a largely open problem. To resolve this, we establish a structural correspondence between the error dynamics of a Koopman latent-space observer and the class of generalized Persidskii systems, which admits diagonal Lyapunov functions and incremental sector characterizations. Exploiting this connection, we design a nonlinear correction term whose gain is computed via a linear matrix inequality (LMI) that simultaneously certifies input-to-state stability (ISS) of the estimation error with respect to both lifting residuals and external disturbances. Exponential convergence in the nominal case and ultimate boundedness under bounded perturbations are established analytically. Numerical validation on the Van~der~Pol oscillator and a nonlinear robotic arm with friction uncertainty demonstrates that the proposed observer substantially outperforms both the Extended Kalman Filter and a linear Koopman observer in terms of estimation accuracy and robustness, achieving up to a 42\% reduction in steady-state RMSE under lifting mismatch.

Syed Pouladi

This paper addresses the stability analysis and state estimation of generalized Persidskii systems subject to time-varying delays and external disturbances. The generalized Persidskii class, which couples linear dynamics with sector-bounded nonlinear feedback loops, offers a tractable yet expressive framework for modeling electromechanical and neural network systems. We develop delay-dependent conditions for input-to-state stability (ISS) via Lyapunov--Krasovskii functionals incorporating Persidskii-type integral terms, and cast these conditions as linear matrix inequalities (LMIs). A structured robust observer is proposed for systems with partial state measurement, and its convergence is guaranteed through an $H_\infty$ synchronization criterion. To handle plant uncertainty, the system matrices are identified from trajectory data using a stability-preserving Koopman lifting procedure, in which the ISS-LMI constraint is embedded as a convex side condition during parameter regression. The identified model populates the prediction horizon of an ICODE-MPPI (Input-dependent Control-oriented Dynamical Estimation -- Model Predictive Path Integral) controller. The complete framework is validated on a 1.5 kW Permanent Magnet Synchronous Motor (PMSM) drive equipped with a programmable load brake. Experimental results confirm a 35\% reduction in velocity estimation RMSE relative to an Extended Kalman Filter and a 67\% improvement in speed-tracking accuracy relative to standard Field-Oriented Control, corroborating the theoretical ISS bounds established herein.