I
Ivan Petrović
Researcher at University of Zagreb
Publications - 258
Citations - 3638
Ivan Petrović is an academic researcher from University of Zagreb. The author has contributed to research in topics: Mobile robot & Motion planning. The author has an hindex of 28, co-authored 248 publications receiving 3002 citations. Previous affiliations of Ivan Petrović include Czech Technical University in Prague & University of Toronto.
Papers
More filters
Proceedings ArticleDOI
Neural network based sliding mode controller for a class of linear systems with unmatched uncertainties
TL;DR: A neural network is employed for the online estimation of the uncertainties using the simple gradient descent learning algorithm for the performance improvement of the sliding mode controller for a class of linear systems with unmatched uncertainties/disturbances.
Journal ArticleDOI
Applying optimal sliding mode based load-frequency control in power systems with controllable hydro power plants
TL;DR: In this article, an optimal load-frequency controller for nonlinear power system is proposed, which is based on discrete-time sliding mode control, and an estimation method based on fast output sampling is proposed for estimating unmeasured system state and disturbance.
Proceedings ArticleDOI
Efficient navigation for anyshape holonomic mobile robots in dynamic environments
TL;DR: This work presents a navigation strategy for a holonomic mobile robot with anyshape footprint based on a strategy that makes use of discrete and continuous techniques and provides a continuous motion generation approach to generate smooth motions that are fast to compute.
Proceedings Article
An improved CamShift algorithm using stereo vision for object tracking
TL;DR: A tracking algorithm which is based on the CAMSHIFT (Continuously Adaptive Mean Shift) algorithm, which operates on the stereo images, and the disparity image to increase the tracking quality with acceptable losses in the execution time.
Journal ArticleDOI
Partial Mutual Information Based Input Variable Selection for Supervised Learning Approaches to Voice Activity Detection
TL;DR: The results showed that the classifier with the reduced input vector significantly outperformed the standalone detector based on the likelihood ratio, and that among the three classifiers, Boost showed the most consistent performance.