Ivan Petrović

Bio: 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.

Ensemble of LSTMs and feature selection for human action prediction

Abstract: As robots are becoming more and more ubiquitous in human environments, it will be necessary for robotic systems to better understand and predict human actions. However, this is not an easy task, at times not even for us humans, but based on a relatively structured set of possible actions, appropriate cues, and the right model, this problem can be computationally tackled. In this paper, we propose to use an ensemble of long-short term memory (LSTM) networks for human action prediction. To train and evaluate models, we used the MoGaze dataset - currently the most comprehensive dataset capturing poses of human joints and the human gaze. We have thoroughly analyzed the MoGaze dataset and selected a reduced set of cues for this task. Our model can predict (i) which of the labeled objects the human is going to grasp, and (ii) which of the macro locations the human is going to visit (such as table or shelf). We have exhaustively evaluated the proposed method and compared it to individual cue baselines. The results suggest that our LSTM model slightly outperforms the gaze baseline in single object picking accuracy, but achieves better accuracy in macro object prediction. Furthermore, we have also analyzed the prediction accuracy when the gaze is not used, and in this case, the LSTM model considerably outperformed the best single cue baseline

Depth from Mono Accuracy Analysis by Changing Camera Parameters in the CARLA Simulator

Abstract: Depth estimation is an important task in robotics and autonomous driving. By estimating depth and relying only on a single camera, it is no longer necessary to add and calibrate additional sensors - usually a second camera. However, such an approach requires training on extensive datasets and obtaining real-world datasets is time consuming and costly. Given that, using photorealistic simulators can be beneficial, since a multitude of varoius scenes can be created. In this paper we present an approach to training a deep neural network based on the ResNet architecture for estimating depth from a single camera. We target road vehicle scenes and use the CARLA simulator. We evaluate the trained network on the real-world KITTI dataset images and in the CARLA simulator. In the simulated experiments, we compare the performance with respect to the changes in camera intrinsic and extrinsic calibration parameters with respect to the ego vehicle frame.

Proposal of Hypotheses Association for Mobile Robot Localization

Abstract: Global localization is the problem of determining the position of a mobile robot under global uncertainty. The algorithm introduced here is based on the multiple model (MM) and exploits a soft gating of the problem (SG) to reduce the computational requirements of the approach. This localization algorithm is based on combining histograms and Hough transform. Presented algorithm is tested using a Pioneer 2 DX mobile robot simulator

KAŽNjIVO PONAŠANjE I PRAVNI OKVIR ZAŠTITE PRAVA DETETA SA OSVRTOM NA USAGLAŠENOST SA EVROPSKIM STANDARDIMA

Abstract: In the paper, the authors deal with the international and domestic legal framework for the protection of children's rights, with a special focus on the legal consequences of punishable behavior. In this regard, the authors first point to the historical development of the child's rights in international documents, especially addressing the child's right to undertake legal affairs and the child's right to free expression of opinion. In addition to this, the paper also deals with the issue of the position of minors in criminal proceedings, as well as the issue of the imposition and execution of criminal sanctions against minors according to the current criminal legislation of the Republic of Serbia. Special emphasis was given to considering the application of the provisions of the Law on Juvenile Offenders, as well as the position of minors in misdemeanor proceedings. In the final part of the paper, an overview of the legal frameworks of individual European Union countries regarding the position of minors in criminal legislation is presented.

Autotuning Power System Stabilizer based on Fuzzy Plant Model

Abstract: The paper presents a newly proposed autotuning power system stabilizer (PSS) based on a Takagi- Sugeno (TS) fuzzy model The main advantage of the proposed PSS is in a stable regulation structure without the critical parts such as on-line identification and feedback gain calculations in real-time Additionally, the proposed algorithm can be implemented both in floating-point and in fixed-point microprocessor platforms The simulation results presented in the paper show that the proposed PSS effectively damps active power oscillations and that the commissioning process can be performed with no need for expert knowledge from the commissioning staff

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Coverage control for mobile sensing networks

Abstract: This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Adaptive Control

Abstract: This book, written by two major figures in adaptive control, provides a wealth of material for researchers, practitioners, and students. While some researchers in adaptive control may note the absence of a particular topic, the book‘s scope represents a high-gain instrument. It can be used by designers of control systems to enhance their work through the information on many new theoretical developments, and can be used by mathematical control theory specialists to adapt their research to practical needs. The book is strongly recommended to anyone interested in adaptive control.

A Review of Motion Planning Techniques for Automated Vehicles

Abstract: Intelligent vehicles have increased their capabilities for highly and, even fully, automated driving under controlled environments. Scene information is received using onboard sensors and communication network systems, i.e., infrastructure and other vehicles. Considering the available information, different motion planning and control techniques have been implemented to autonomously driving on complex environments. The main goal is focused on executing strategies to improve safety, comfort, and energy optimization. However, research challenges such as navigation in urban dynamic environments with obstacle avoidance capabilities, i.e., vulnerable road users (VRU) and vehicles, and cooperative maneuvers among automated and semi-automated vehicles still need further efforts for a real environment implementation. This paper presents a review of motion planning techniques implemented in the intelligent vehicles literature. A description of the technique used by research teams, their contributions in motion planning, and a comparison among these techniques is also presented. Relevant works in the overtaking and obstacle avoidance maneuvers are presented, allowing the understanding of the gaps and challenges to be addressed in the next years. Finally, an overview of future research direction and applications is given.

SeqSLAM : visual route-based navigation for sunny summer days and stormy winter nights

Abstract: Learning and then recognizing a route, whether travelled during the day or at night, in clear or inclement weather, and in summer or winter is a challenging task for state of the art algorithms in computer vision and robotics. In this paper, we present a new approach to visual navigation under changing conditions dubbed SeqSLAM. Instead of calculating the single location most likely given a current image, our approach calculates the best candidate matching location within every local navigation sequence. Localization is then achieved by recognizing coherent sequences of these “local best matches”. This approach removes the need for global matching performance by the vision front-end - instead it must only pick the best match within any short sequence of images. The approach is applicable over environment changes that render traditional feature-based techniques ineffective. Using two car-mounted camera datasets we demonstrate the effectiveness of the algorithm and compare it to one of the most successful feature-based SLAM algorithms, FAB-MAP. The perceptual change in the datasets is extreme; repeated traverses through environments during the day and then in the middle of the night, at times separated by months or years and in opposite seasons, and in clear weather and extremely heavy rain. While the feature-based method fails, the sequence-based algorithm is able to match trajectory segments at 100% precision with recall rates of up to 60%.