4 papers
Actor-Identifier-Critic Reinforcement Learning for Adaptive Model-Free Optimal Control of Nonlinear Systems with Stochastic Packet Dropouts
Kianoush Aqabakee, Kosar Behnia, Amirhossein Heydarian Ardakani +2
Packet dropouts in control systems poses a critical challenge, as it can significantly compromise system performance and stability. In these conditions, classical controllers often…
Online Detection and Mitigation of Robust Zero Dynamics Anomaly Behavior in MIMO Nonlinear Control Systems
Kosar Behnia, H. A. Talebi, Farzaneh Abdollahi
This paper presents a methodology to detect robust zero dynamics anomaly behavior and mitigate the impacts in general multi-input multi-output (MIMO) nonlinear systems. The propose…
Geometric Fault-Tolerant Neural Network Tracking Control of Unknown Systems on Matrix Lie Groups
Robin Chhabra, Farzaneh Abdollahi
We present a geometric neural network-based tracking controller for systems evolving on matrix Lie groups under unknown dynamics, actuator faults, and bounded disturbances. Leverag…
Autonomous Driving using Residual Sensor Fusion and Deep Reinforcement Learning
Amin Jalal Aghdasian, Amirhossein Heydarian Ardakani, Kianoush Aqabakee +1
This paper proposes a novel approach by integrating sensor fusion with deep reinforcement learning, specifically the Soft Actor-Critic (SAC) algorithm, to develop an optimal contro…