arXiv subjects

David Naso

Publications and source records attributed to David Naso.

4 recordsLinked to original sources

arXiv2025

ViTA-Seg: Vision Transformer for Amodal Segmentation in Robotics

Occlusions in robotic bin picking compromise accurate and reliable grasp planning. We present ViTA-Seg, a class-agnostic Vision Transformer framework for real-time amodal segmentation that leverages global attention to recover complete object masks, including hidden regions. We proposte two architectures: a) Single-Head for amodal mask prediction; b) Dual-Head for amodal and occluded mask prediction. We also introduce ViTA-SimData, a photo-realistic synthetic dataset tailored to industrial bin-picking scenario. Extensive experiments on two amodal benchmarks, COOCA and KINS, demonstrate that ViTA-Seg Dual Head achieves strong amodal and occlusion segmentation accuracy with computational efficiency, enabling robust, real-time robotic manipulation.

cs.RO↗

arXiv2025

Comparison of linear observation techniques for robust load torque estimation in actuators

The paper addresses the problem of estimating robustly the external load torque in rotary actuator systems, when only the generated motor drive torque and angular displacement are the available input and output. We compare, theoretically and experimentally, two sufficiently established linear observation techniques (i) reduced-order Luenberger observer and (ii) disturbance observer, both using the same identified model of a permanent magnet synchronous motor (PMSM)-based actuator. Our goal is to highlight several aspects related to the implementation, relative degree of the input-torque to estimated-load-torque transfer characteristics, observer open-loop transfer function, and the associated sensitivity (respectively stability margins) with respect to inherently uncertain system plants. Apart from the developed analysis, a detailed experimental case study is demonstrated where the load torque sensor provides reference measurements and allows for evaluation of both observers.

eess.SY↗

arXiv2025

Robust Synchronous Reference Frame Phase-Looked Loop (PLL) with Feed-Forward Frequency Estimation

Synchronous reference frame phase-locked loop (SRF-PLL) techniques are widely used for interfacing and control applications in the power systems and energy conversion at large. Since a PLL system synchronizes its output with an exogenous harmonic signal, often 3-phases voltage or current, the locking of the frequency and phase angle depends on the performance of the feedback loop with at least two integrator terms, and on the distortions of the measured input quantities. For the conventional SRF-PLL with a proportional-integral (PI) control in feedback, we are providing a robust design which maximizes the phase margin and uses the normalization scheme for yielding the loop insensitive to the input amplitude variations. The main improvement in the transient behavior and also in tracking of frequency ramps is achieved by using the robust feed-forward frequency estimator, which is model-free and suitable for the noisy and time-varying harmonic signals. The proposed feed-forward-feedback SRF-PLL scheme is experimentally evaluated on the 3-phases harmonic currents from a standard PMSM drive with the varying angular speeds and loads. Both, the tracked angular frequency and locked phase angle are assessed as performance indicators of the proposed SRF-PLL with feedforwarding.

eess.SY↗

arXiv2021

Robust interaction control of a dielectric elastomer actuator with variable stiffness

This paper presents an interaction control algorithm for a dielectric elastomer membrane actuator. The proposed method permits efficient exploitation of the controllable stiffness of the material, allowing to use the membrane as a "programmable spring" in applications such as robotic manipulation or haptic devices. To achieve this goal, we propose a design algorithm based on robust control theory and linear matrix inequalities. The resulting controller permits to arbitrarily shape the stiffness of the elastomer, while providing robust stability and performance with respect to model nonlinearities. A self-sensing displacement estimation algorithm allows implementation of the method without the need of a deformation sensor, thus reducing cost and size of the system. The approach is validated on an experimental prototype consisting of an elastomer membrane preloaded with a bistable biasing spring.

eess.SY↗