Jakob Šafarič

Jakob Šafarič

Auto-generated profile, based on publicly available information

Jakob Šafarič

EMSISO d.o.o, Pesnica pri Mariboru 20A, 2211 Pesnica pri Mariboru, Slovenia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2020 in Applied Soft Computing
Verified
Journal Article
Closed access
JŠJakob Šafarič
Jakob Šafarič
PBPrimož Bencak
Primož Bencak
DFDušan Fister
Dušan Fister
RŠRiko Šafarič
Riko Šafarič
IFIztok Fister
Iztok Fister

27 October 2018 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DFDušan Fister
Dušan Fister
JŠJakob Šafarič
Jakob Šafarič
IFIztok Fister
Iztok Fister
RŠRiko Šafarič
Riko Šafarič
IFIztok Fister
Iztok Fister
The majority of non-linear systems nowadays are controlled online using rapid PI-controllers with linear characteristics. Evolutionary algorithms are rarely used, especially for online adaptive control, due to their time complexity. This paper proposes an online adaptive controller based on a dynamic evolution strategy and attempts to overcome this performance problem. The main advantage of the evolution strategies over other gradient machine learning algorithms is that they are insensitive to becoming stuck into local optima. As a result, the proposed controller is capable of responding in real-time (sampling time between 1–5 ms) and was tested on a non-linear, single-degree-of-freedom robotic mechanism. To the extent of our knowledge, this is the first application of evolutionary algorithms in such an online control. In general, the results obtained were better than the results achieved using a traditional PI-controller.

27 September 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Open access
JSJakob Safaric
Jakob Safaric
RKRok Klobucar
Rok Klobucar
BABojan Acko
Bojan Acko
The rapid increase in precision of tactile coordinate measurement machines (CMMs) in recent years has caused an increased demand for high precision calibration artifacts, by which the traceability of coordinate measurements can be assured. This article presents research done in the development and verification of a high precision calibration system for step gauges, which are among the most frequently used CMM calibration artifacts. The main goals for the calibration system are measurement uncertainty of ${U}= ({{{(0.1}\,\,{{\mu m)}}}^{{2}}+{{(0.5\cdot }{{10}}^{{-6}} {\cdot L)}}^{{2}}})^{1/2} $ and full automatization of the measurement process, with human intervention only needed during the initial setup of the step gauge onto the system. Final verification has confirmed that both goals were achieved. The automation allows for autonomous measurement of the step gauge after the operator has performed the step gauge setup and entered nominal values of the measurement points, as well as the number of repetitions.

5 May 2026 in Micromachines
Verified
Journal Article
Open access
PDF file
BBBožidar Bratina
Božidar Bratina
DFDušan Fister
Dušan Fister
JNJernej Nezman
Jernej Nezman
JŠJakob Šafarič
Jakob Šafarič
RŠRiko Šafarič
Riko Šafarič
The new method proposed in this study, featuring a one-finger gripper, uses three types of forces—van der Waals force, capillary force, and coupling force due to ice—to grip and release microobjects to submillimeter-sized objects (5 to 300 µm). The gravitational force of an object can be neglected in the case of microobjects, but this is not the case for submillimeter-sized objects. This is the first reason that we use the coupling force due to ice; the second reason is that the shape of a micro- or submillimeter-sized object does not matter in this case. The usage of all three forces yields greater versatility regarding objects of different sizes and shapes and, consequently, greater overall reliability in gripping or releasing compared with methods that use only one or two of the mentioned forces. In this study, the laboratory set-up involved the active control of the temperature for both the one-finger gripper and the releasing surface for objects from −25 °C to 40 °C in a closed dust-free chamber in atmospheric air at relative humidity (RH) = 30%. A relatively low RH was achieved with the RH controller, enabling the release or grip procedures to last approx. 2–3 s for microobjects and 6 s for submillimeter-sized objects with the same equipment.