TL;DR
Simulation results show that the IRL actor–critic controller matches or improves upon the fixed-gain baseline after a plant change while, unlike the certainty-equivalence scheme, requiring no continuous probing/dither signal for identifiability—avoiding the associated persistent tracking-error penalty.
Simulation results demonstrate that the proposed method outperforms robust control and adaptive model predictive control in tracking accuracy under varying attack intensities, validating the effectiveness of the unified RL-based framework for AVs under coupled physical-cyber threats.
A certified imitation-learning framework for approximating model predictive control (MPC) policies with feedforward neural controllers with feedforward neural controllers is developed and validates it on autonomous-vehicle lateral control.
This research introduces an innovative control technique for Series Elastic Actuators (SEAs) that utilizes Reinforcement Learning (RL) to address the shortcomings of previously fixed-gain adaptive controllers, which are a hybrid of State Feedback Control and Model Reference Adaptive Control by using Lyapunov Stability...
Traditional fixed-gain proportional–integral–derivative (PID) controllers often exhibit limited adaptability when regulating the longitudinal motion of passenger aircraft under varying flight conditions and external disturbances. This study proposes an adaptive control framework that integrates reinforcement learning (...
Comparative simulations on a 2-DOF planar manipulator demonstrate that the proposed method provides faster convergence and improved steady-state tracking accuracy than both a PID baseline and a classical Slotine–Li adaptive baseline, while respecting the predefined-time bound.
This paper addresses a robust tracking problem for linear discrete-time systems by proposing a reinforcement learning (RL) control method based on a diagonal-scaling strategy, offering a solution tailored to the demands of enhanced reliability. To overcome a common limitation in policy-iteration-based RL design, namely...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
