Similar papers
2026
Physics-Constrained Residual Learning for Refined Dynamic Identification and Robust Torque Estimation
Accurate dynamic modeling of industrial robots is essential for high-performance control and estimating torque. However, traditional physics-based models often fail to capture unmodeled dynamics such as complex friction, payload variations, and gearbox-induced distortions. This article refines a physics-based modeling framework with a data-driven residual learning policy to compensate for unmodeled dynamics. We first employ a nested optimization strategy using multistart sequential quadratic programming (MS-SQP) and QR-based base parameter extraction to identify identifiable inertial and Stribeck friction parameters. To compensate for remaining systematic errors, we integrate the residual error policy model using physics-aware feature engineering. The proposed method is validated on both synthetic datasets and a real-world six-DOF industrial manipulator across various trajectories (including Fourier, chirp, and trapezoidal excitations) and payload conditions. A friction modeling ablation study confirms that richer friction representations progressively reduce the residual space, with the Stribeck backbone achieving 2.32-Nm root-mean-square error (RMSE) compared to 3.89 Nm for the rigid-body-only baseline. Experimental results demonstrate that the proposed physics-imbued residual framework improves torque prediction RMSE 31.5 % in real-world trajectories and 31.7 % in unseen synthetic payload testing. The results confirm that the framework effectively captures complex unmodeled dynamics while maintaining physical interpretability and generalization capabilities essential for industrial instrumentation and measurement applications.
Fauzy Satrio Wibowo, Hsien-I Lin, Wen-Hui Chen
· IEEE Transactions on Instrum... · 0 citations
Preprint
Aug 2026
Control-Oriented Learning for Dynamic Tracking and Stability Analysis of Soft Pneumatic Actuators
Soft pneumatic actuators offer inherent compliance and safe interaction but remain difficult to model and control because of their highly nonlinear, distributed dynamics. We present a control-oriented data-driven modeling and control framework that decomposes actuator behavior into a nonlinear static equilibrium model and a linear residual dynamics model identified using Extended Dynamic Mode Decomposition with control (EDMDc). This representation enables feedforward compensation, task-space feedback control, and local closed-loop stability analysis through an augmented linear model. Experiments achieve approximately 1 mm root mean square error (RMSE) during low-speed (approximately 10 mm/s) trajectory tracking and below 10 mm RMSE at higher speeds (approximately 100 mm/s). The framework further achieves stable tracking of highly dynamic user-generated references with peak accelerations exceeding 25 m/s^2 while simultaneously performing real-time obstacle avoidance. Finally, the proposed stability analysis is experimentally validated by accurately predicting stable, marginal, and unstable operating regimes. These results demonstrate that structured, control-oriented learning provides an accurate and practical framework for soft actuator control.
Nithin S. Kumar, Eric J. Barth
· 0 citations
Open access
Aug 2026
Reinforcement learning-based adaptive gyroscopic control for torsional response mitigation: a proof-of-concept study
Torsional vibrations induced by seismic excitation can significantly increase structural demand, particularly in systems with geometric or stiffness irregularities. This proof-of-concept study proposes a hybrid adaptive control framework that combines passive gyroscopic damping with reinforcement learning (RL)-based adaptive torque control for torsional response mitigation. A simplified three-degree-of-freedom (3DOF) structural model is evaluated under bidirectional earthquake loading, while the control policy is trained using the Proximal Policy Optimization (PPO) algorithm to generate adaptive torque directly from measured system states without explicit system identification. Numerical simulations using recorded earthquake ground motions show that the proposed approach reduces root-mean-square torsional displacement to 0.012 ± 0.001 rad, representing a 65.7% reduction relative to the uncontrolled case and improved performance over passive gyroscopic control alone. Sensitivity analyses involving variations in mass, stiffness, and damping indicate stable controller performance across the structural parameter ranges considered. The trained controller achieved sub-millisecond inference time with minimal computational overhead, supporting its computational feasibility for future real-time implementation. The results demonstrate the potential of integrating physically grounded gyroscopic damping with data-driven adaptive control for intelligent torsional vibration mitigation.
S. Stephen, Ali Hadi, O. Akinradewo et al.
· Asian Journal of Civil Engin... · 0 citations
Open access
Aug 2026
Feedback-Linearization-Assisted Observer-Based Interconnection and Damping Assignment Passivity Control for Electromechanical Actuators
Electromechanical actuators (EMAs) are increasingly used in aerospace servo actuation because of their compact structure, high power density, and convenient integration with electric flight-control systems. However, load-side aerodynamic torque, friction, parameter perturbations, and unmodeled transmission effects enter the EMA dynamics through a channel different from the motor-current input, which leads to a mismatched disturbance rejection problem. This paper develops a feedback-linearization-assisted observer-based interconnection and damping assignment passivity-based control (IDA-PBC) method for EMA trajectory tracking. A fourth-order input–output feedback-linearized normal-coordinate model is first derived, through which the original load-side mismatched disturbance is transformed into a matched term acting on the highest-order channel. An extended state observer is then constructed to estimate the transformed disturbance. Based on the observer output, a desired Hamiltonian function is generated from a Lyapunov equation, and the interconnection and damping matrices are explicitly assigned so that the closed-loop tracking-error dynamics admit a dissipative port-Hamiltonian representation. A composite Lyapunov analysis proves closed-loop exponential stability under the assumption of slowly varying disturbance. The resulting framework combines the disturbance-channel-reshaping capability of feedback linearization with the energy-shaping interpretation of IDA-PBC, providing a systematic controller design for high-precision EMA servo systems subject to load-side disturbances.
Xi Xiao, Xuming Cheng, Bo-Hao Li et al.
· Actuators · 0 citations
Open access
2026
Operational temperature effect on MR dampers in stay cable vibration control : an adaptive RL-based control strategy
This paper proposes a reinforcement-learning (RL)-based semi-active control strategy to mitigate stay-cable vibrations using magnetorheological (MR) dampers while explicitly addressing MR fluid temperature variations during damper operation. The controller is model-free and based on the Q-learning method. The controller updates its policy online using local measurements, including the displacement and velocity at the damper location. The control law avoids a fixed inverse-damper model by using a quadratic action–value approximation, which yields a closed-form current command, while a target matrix is used to stabilize the online learning. The controller performance is numerically evaluated on the A10 cable of the Dongting Lake Bridge using a temperature-dependent hyperbolic-tangent MR damper model implemented in MATLAB. A comparison with a classical LQR-based semi-active controller that relies on an inverse MR damper model is presented. The results indicate that the proposed RL controller remains effective under temperature-induced uncertainty, while still requiring lower control effort in terms of improved energy efficiency.
Y. M. Delijani, Shaohong Cheng, F. Ghrib
· International Symposium on D... · 0 citations
Conference
Jul 2026
Hybrid Computed Torque Control and Soft Actor-Critic Framework for Sample-Efficient Robotic Manipulator Control
Reinforcement Learning (RL) has emerged as a promising approach for robotic control, enabling agents to learn control policies through interaction with complex and dynamic environments. However, standalone RL methods often suffer from poor sample efficiency, limiting their practicality for real-world robotic systems. To address this limitation, recent studies have combined RL with classical controllers such as proportional–integral–derivative (PID) control, where the classical controller provides a baseline policy and RL learns residual corrective actions. Nevertheless, conventional PID controllers do not explicitly incorporate the full nonlinear manipulator dynamics.This paper proposes a physics-informed residual reinforcement learning framework that combines Computed Torque Control (CTC) with Soft Actor-Critic (SAC) for trajectory tracking of a 2-DOF robotic manipulator. The CTC component utilises analytical Lagrangian dynamics to provide a nominal control torque, while SAC learns bounded residual corrections to compensate for model uncertainties and unmodelled effects. The proposed framework is evaluated in CoppeliaSim and compared against CTC-only, RL-only, and PID+SAC baselines under identical experimental conditions.Experimental results demonstrate that the proposed CTC+SAC framework achieves the lowest mean and steady-state tracking errors among all evaluated methods, with a 4.9% reduction in mean error over RL-only and a 3.3% reduction over PID+SAC within the considered simulation setup. The results suggest that incorporating analytical robot dynamics into the residual learning framework improves tracking performance and sample efficiency compared to both pure RL and classical controller baselines.
Mona Alsbakhi, Mohammed M. Lubbad, M. Tabash et al.
· International Conference on... · 0 citations