Filip Bečanović

Filip Bečanović

Auto-generated profile, based on publicly available information

Filip Bečanović

School of Electrical Engineering, University of Belgrade,Belgrade,Serbia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 October 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
FBFilip Becanovic
Filip Becanovic
VBVincent Bonnet
Vincent Bonnet
Raphael DumasRaphael Dumas
Raphael Dumas
KJKosta Jovanovic
Kosta Jovanovic
Samer MohammedSamer Mohammed
Samer Mohammed
Human gait patterns have been intensively studied, both from medical and engineering perspectives, to understand and compensate pathologies. However, the muscle-force sharing problem is still debated as acquiring individual muscle force measurements is challenging, requiring the use of invasive devices. Recent studies, using various objective functions, suggest muscle-force sharing may result from an optimization process. This study proposes using inverse optimal control to identify an objective function. Two popular methods of inverse optimal control, bilevel and inverse Karush-Kuhn-Tucker, were investigated. The identified objective functions were then used to predict muscle forces during gait, and their performances were compared to an exhaustive list of biological cost functions from the literature. The best prediction was achieved by the bilevel inverse optimal control method, with a root-mean-squared error of 176 N (162 N) and a correlation coefficient of 0.76 (0.68) for the stance (swing) phase of the gait cycle. These muscle force predictions were thereafter used to compute joint stiffness, exhibiting an average root-mean-square error of 42 Nm.rad $^{-1}$ and a correlation coefficient of 0.90 when compared to the reference. The bilevel method's prevalence in terms of robustness over inverse Karush-Kuhn-Tucker was demonstrated on human data and explained on a toy example.

3 June 2024
Verified
Conference Paper
Closed access
DKDanilo Klasanović
Danilo Klasanović
LJLazar Jugović
Lazar Jugović
Nikola RuzicNikola Ruzic
Nikola Ruzic
FBFilip Bečanović
Filip Bečanović
NKNikola Knezevic
Nikola Knezevic
Automation of waste sorting operations using robotic systems marks a significant advance in ecological development. The use of robotic arms with elastic grippers offers advantages over conventional grippers, which require a pre-defined regular shape, composition, and mass of the handled objects. To successfully grasp and manipulate irregularly shaped objects, it is necessary to define the optimal design of an elastic robotic gripper tailored to the sorted items. This paper presents a method for evaluating robotic fingers with four different configurations operating with seven types of known and regular-shaped objects. An external pneumatic control system for the robotic arm and a predefined robot trajectory during testing were used, involving various translational and rotational movements, spatial perturbations, and strong centrifugal forces. Additionally, an interactive inspection of the gripping was conducted using a seven-step scoring system, examining the impact of the object's mass, orientation, position, and center of mass change on the gripping outcome. It was concluded that the robotic gripper with three elastic fingers achieved the best overall results in testing the grip quality of objects with and without added mass, scoring 0.86 out of a maximum of 1. Meanwhile, the four-fingered gripper performed best in tests assessing the impact of position changes, orientation, and center of mass, with scores of 0.54, 0.61, and 1, respectively.

3 June 2024
Verified
Conference Paper
Closed access
FRFilip Rodić
Filip Rodić
FBFilip Bečanović
Filip Bečanović
JAJelena Aleksic
Jelena Aleksic
Dragan MirkovDragan Mirkov
Dragan Mirkov
KJKosta Jovanovic
Kosta Jovanovic
This paper presents a procedure and Python im-plementation for the offline synchronization of vertical jumping data from a motion capture system and from force plates when a hardware trigger is unavailable and the sampling rates of the systems are known. Experimental data from a total of 15 subjects was collected. The synchronized data is used to evaluate predictions of ground reaction force with a 6-degree-of-freedom rigid-body model of the human skeletal system. The motion capture kinematic data was used as an input to the inverse kinematics and the force plate data was used to evaluate the output of the inverse dynamics of the rigid-body model. The results of the synchronization procedure, the predictions of the ground reaction forces, and an analysis of the joint trajectories are presented. The typical metrics of vertical jumping performance over our dataset were computed and agreed with typical trends and values noted in the literature.

16 March 2026 in Journal of Biomechanics
Verified
Journal Article
Closed access
FBFilip Bečanović
Filip Bečanović
VBVincent Bonnet
Vincent Bonnet
KJKosta Jovanovic
Kosta Jovanovic
Samer MohammedSamer Mohammed
Samer Mohammed
Raphael DumasRaphael Dumas
Raphael Dumas

3 June 2024
Verified
Conference Paper
Closed access
Branko LukićBranko Lukić
Branko Lukić
MRMarija Radmilovic
Marija Radmilovic
FBFilip Bečanović
Filip Bečanović
Motion capture technology finds wide application in various fields such as entertainment, sports analysis, and biomechanics, enabling accurate digitization of real-world movements for replication in digital environments. There exist diverse motion capture systems utilizing different technologies, supported by software tools for marker movement extraction. Further processing of acquired data requires additional investment in software development. This paper presents the human motion estimator application developed using GUI in MATLAB App Designer. This application aims to generate human movement based on recorded marker data obtained from motion capture systems (MCS), currently supporting two MCSs: Vicon and ART. The developed application aims to become a universal tool for estimating human movements, supporting data from ART or Vicon MCS. The application provides visual instructions for mounting markers on the body and initialization position, while data processing is based on optimization algorithms for defined criteria functions. The application targets research institutions by providing essential software support for ART or Vicon MCSs, thus enhancing data analysis capabilities for estimating upper body movement. The application is a framework, a starting point, to be upgraded and future developed with additional MCS and features.

1 June 2026
Verified
Conference Paper
Closed access
MSMarina Svilar
Marina Svilar
DMDušan Mišković
Dušan Mišković
KNKosta Nedeljković
Kosta Nedeljković
MTMarko Tepavčević
Marko Tepavčević
Branko LukićBranko Lukić
Branko Lukić
FBFilip Bečanović
Filip Bečanović