arXiv subjects

Kosar Behnia

Publications and source records attributed to Kosar Behnia.

3 recordsLinked to original sources

arXiv2026

Deformable Object Manipulation under Partial Observability via Real-Time Full-Shape Estimation

Manipulating deformable objects (DOs) is challenging due to their high-dimensional state space, underactuated dynamics, and partial observability. In this paper, we propose cRVAE, a lightweight conditional recurrent variational autoencoder that estimates the full DO state from only partial corner-node observations during inference. The resulting model is used as the forward model in a receding-horizon optimal control framework for obstacle-aware collaborative DO manipulation. In simulation on rope and fabric, cRVAE estimates the full DO state from the available corner-node measurements alone, matching the accuracy of a parameter-identified XPBD model. At inference it uses no physical parameters as model inputs and performs no online parameter identification. It also runs approximately 350 times faster on the rope and over 1500 times faster on the fabric per forward pass, keeping horizon-based planning within the 100 ms control budget where XPBD exceeds it already at short horizons. Full-shape estimation from corner sensing at in-loop speed is what makes the model deployable on hardware, which we demonstrate on a Unitree Go2 robot.

cs.RO↗

arXiv2026

Actor-Identifier-Critic Reinforcement Learning for Adaptive Model-Free Optimal Control of Nonlinear Systems with Stochastic Packet Dropouts

Packet dropouts in control systems poses a critical challenge, as it can significantly compromise system performance and stability. In these conditions, classical controllers often struggle to deliver effective control, as they rely on accurate system models, which may not always be available. This paper proposes a novel Actor-Identifier-Critic~(AIC) controller to address model-free tracking control of nonlinear systems in the presence of packet dropouts in both the controller-to-actuator and sensor-to-controller channels. Using an identifier to learn the system dynamics, the proposed controller is able to handle packet dropouts in the communication link and facilitate gradient propagation from the critic to the actor within a model-free control framework. The performance of the proposed method is demonstrated on two nonlinear SIMO and MIMO systems and a case study on power system stability subject to stochastic packet dropouts.

eess.SY↗

arXiv2025

Online Detection and Mitigation of Robust Zero Dynamics Anomaly Behavior in MIMO Nonlinear Control Systems

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 proposed method guarantees the resiliency and stability of the closed-loop system without relying on an accurate dynamical model. The presented method operates in two stages. First, it measures the difference between the system input and that of the model as a residual signal to detect the anomaly behavior. After detecting the attack, a recovery signal is generated to restore the system to its nominal condition. In this stage, a neural network model is used to estimate the anomaly signal and recover the closed-loop system. The weights of the neural network model are updated online using adaptation rules without needing prior data for training. The accuracy and performance of the proposed methods are verified by simulating various scenarios on a fourtank system.

eess.SY↗