|S. Kružić, J. Musić (Fakultet elektrotehnike, strojarstva i brodogradnje, Split, Croatia), R. Kamnik (Univerza v Ljubljani, Fakulteta za elektrotehniko, Ljubljana, Slovenia), V. Papić (Fakultet elektrotehnike, strojarstva i brodogradnje, Split, Croatia)
Estimating Robot Manipulator End-effector Forces using Deep Learning
The measurement of the robotic manipulator endeffector interaction forces can in certain cases be challenging, especially when using robots that have a small payload (and consequently not capable of using wrist-mounted force sensor), which is often case with educational robots. In the paper, a method for estimation of end-effector forces using measurements from the base-mounted force sensor and deep neural networks is presented. Several deep architectures were trained using data collected on real 6-DOF robot manipulator (Commonplace Robotics Mover6 robot) using custom-made interaction object operated by a human. The obtained results show that when using appropriate deep architecture promising estimates can be achieved (with an RMSE metric on test set which was 16%, 12% and 6% of maximum force in respective directions of x, y and z axes). This makes this approach suitable for use in a variety of applications, including but not limited to usage with haptic feedback interfaces for robot control.
|E. Kamenar, N. Črnjarić-Žic (University of Rijeka, Faculty of Engineering, Rijeka, Croatia), D. Haggerty (UC Santa Barbara, Department of Mechanical Engineering, Santa Barbara, United States), S. Zelenika (University of Rijeka, Faculty of Engineering, Rijeka, Croatia), E. Hawkes, I. Mezić (UC Santa Barbara, Department of Mechanical Engineering, Santa Barbara, United States)
Prediction of the Behavior of a Pneumatic Soft Robot Based on Koopman Operator Theory
Thanks to their flexibility, soft robotic devices offer critical advantages over rigid robots, allowing adaptation to uncertainties in the environment. As such, soft robots enable various intriguing applications, including human-safe interaction devices, soft active rehabilitation devices, and soft grippers for pick-and-place tasks in industrial environments. In most cases, soft robots use pneumatic actuation to inflate the channels in a compliant material to obtain the movement of the structure. However, due to their flexibility and nonlinear behavior, as well as the compressibility of air, controlled movements of the soft robotic structure are difficult to attain. Obtaining physicallybased mathematical models, which would enable the development of suitable control approaches for soft robots, constitutes thus a critical challenge in the field. The aim of this work is, therefore, to predict the movement of a pneumatic soft robot by using a data-driven approach based on the Koopman operator framework. The Koopman operator allows simplifying a nonlinear system by “lifting” its dynamics into a higher dimensional space, where its behavior can be accurately approximated by a linear model, thus allowing a significant reduction of the complexity of the design of the resulting controllers.
|P. Linna (Tampere University, Pori, Finland), T. Aaltonen (Satakunta University of Applied Sciences, Pori, Finland), A. Halla, J. Grönman, N. Narra (Tampere University, Pori, Finland)
Conceptual Design of an Autonomous Rover with Ground Penetrating Radar: Application in Characterizing Soils Using Deep Learning
In the pursuit to make agricultural production efficient, the earliest farmers used data in the form of notes of observations. In the current age of data, it has become easier to collect data over a wide spectrum of parameters. There are numerous sensing technologies for measuring processes and parameters over the field surface, typically mounted on satellites, aerial (drone), ground vehicle and static platforms. In the latest understanding soil is gaining increasing attention and recognition of its significance in not only increasing productivity but also stabilizing the environment. However characterizing soil in a field is not trivial, especially when required to access the deeper layers and quantifying the essential contents – water, nutrients and organic matter.
This paper presents a short review of applications of ground penetrating radars (GPR) in measuring soil content and structure. The focus is on deep learning constructs that have been used for interpreting and establishing correlations. The review serves to inform design considerations for a planned autonomous rover that will be used for surveying field soils in the Satakunta region of Finland.
|L. Drobilo, M. Švaco, B. Jerbić (Fakultet strojarstva i brodogradnje, Zagreb, Croatia)
Increasing the Accuracy of Robotic Neurosurgical Procedures through Robot Calibration
One of the main concerns in neurosurgical procedures, besides safety and achieving sterile environments, is procedure accuracy. Although robots are well known for their reliability, absolute accuracy has always been an issue, especially for configurations with serially linked revolute joints. This issue can be addressed through various localisation and positioning strategies which significantly increase procedure accuracy but also increase overall procedure duration and can never achieve the full potential of the system. To address this issue robot calibration is performed to better fit the model used for positional calculations to the robot. In this article an experimental setup based on the neurosurgical robotic system RONNA is presented. A robot tool with highly precise sensors combined with a precisely measured reference phantom is used to perform measurements as well as for validation, and robot parameters are calibrated using a Sequential Quadratic Programming-based algorithm. A method for implementing the calibrated model into the RONNA workflow is presented and positioning accuracy achieved using the calibrated model is compared with a model obtained through the commercial calibration software RoboDK. Validation results show positioning accuracies comparable to the commercially calibrated model, with additional improvements yet to be implemented into the model and calibration setup. Experimental testing shows a potential for decrease in localisation time and increase in overall procedure accuracy of neurosurgical procedures, which can be very beneficial, especially for more complex procedures.
|T. Aaltonen (SatakuntaUniversityof Applied Sciences, Pori, Finland), M. Saarivirta (Tampere University/ Faculty of Information Technology and Communication Sciences, Pori, Finland), T. Kerminen (SatakuntaUniversityof Applied Sciences, Pori, Finland), J. Grönman (Tampere University/ Faculty of Information Technology and Communication Sciences, Pori, Finland)
Implementation of a Low-cost Autonomous Underwater Vehicle Using Open Source ROS Components with Consumer Class Sonar Technologies
The increase in the availability of low-costcomponents has madeit possible to design and implement new and innovative devicesfor theunderwaterrobotics. Today, cost-effective and open solutions can be created to replace previous expensive and proprietary robotsystems. This study presents the prototype of an autonomous underwater vehicle. The system was built using commonly available sensor components in combination with anopen source code and in house designed parts.The configuration of the autonomous underwater vehicle is introduced in this study. The results obtained from thecomponenttests performed in the actual operating environment are presented. Based on these tests, the subsystemswere found to be well suited for underwater environment.
|A. Žgaljić (Faculty of Mechanical Engineering and Naval Architecture, Zagreb, Croatia), M. Švaco, B. Jerbić (Fakultet strojarstva i brodogradnje, Zagreb, Croatia)
Improving Markerless Registration Accuracy by Mapping Facial Deformation
Robotics is gaining an increasing role in stereotactic neurosurgery. Novel methods for intraoperative localization of the patient should be developed for tackling the challenges of the localization and registration processes simplification. Most state of the art robotic systems use marker-based localization and registration while markerless localization is at its infancy.
One of the challenges of markerless localization and registration is face deformation. The human skin and parts of the human face can deform from the preoperative scanning phase to the operative position in the actual surgery due to swelling, different orientations of scanning and operation, etc. The human face is not uniformly deformable, with some parts of the face deforming less than others for example due to the differences in skin thickness, and the depth of the bone with respect to the outer surface of the skin. This presents an opportunity for improving the markerless registration by identifying and using less deformable parts of the face while not registering parts of the face that are more deformable. In this paper, an algorithm for dividing the face surface into multiple regions and determining each region's deformability is proposed and validated on preliminary data from actual neurosurgical operations. Two approaches for determining the facial regions are proposed. The first approach creates a uniform n×n 3D grid and superimposes it over the point cloud of the patient’s face. The second approach utilizes the detection of facial landmarks in a 2D image and maps these landmarks to the point cloud, where each of the landmarks corresponds to one distinct facial region. To calculate the deformability of any facial region, multiple point clouds can be registered using ground truth measurements, followed by their respective deformability calculation as a standard deviation of all point clouds. Ground truth registration is calculated using bone attached fiducial markers.
A statistical measure of the registration of different regions is used to validate the best regions to be used in each approach and to validate each approach. Preliminary results are given for one intraoperative point cloud. Error is measured as the average Euclidean distance from registered cloud markers to ground truth markers. When the whole face was used for registration, the error was 4.19mm, while when using only selected parts of the face, the error was reduced to 1.78mm.
|D. Vrbanec (IV. osnovna škola Varaždin, Varaždin, Croatia)
Programiranje robota u učionici budućnosti
Učenje programiranja trebalo bi rezultirati stvaranjem rješenja kao najvažnijim ishodom. Ono se mora temeljiti na postupku koji će učenike što više osloboditi od pisanja kôda, a što bolje naučiti stvarati apstraktne modele rješenja. Svakako je tu od jednake važnosti da se stvoreno rješenje može učenicima prikazati brzo i jednostavno. U ovom radu prikazani su primjeri takvog učenja programiranja uz pomoć edukacijskih robota.
Bojan Jerbić (Croatia), Karolj Skala (Croatia)
Tadej Bajd (Slovenia), Ante Bakić (Croatia), Ricardo Branco (Portugal), Bojan Jerbić (Croatia), Zlatko Katalenić (Slovenia), Igor Kotenko (Russia), Zdenko Kovačić (Croatia), Danica Kragić Jensfelt (Sweden), Jadran Lenarčič (Slovenia), Duc Truong Pham (UK), Vincenzo Piuri (Italy), Ioan Sacala (Romania), Bruno Siciliano (Italy), Karolj Skala (Croatia), Uroš Janez Stanič (Slovenia), Zorislav Šojat (Croatia)
Registration / Fees:
The discount doesn't apply to PhD students.
REGISTRATION / FEES
|Price in EUR
Up to 14 September 2020
From 15 September 2020
|Members of MIPRO and IEEE
|Students (undergraduate and graduate), primary and secondary school teachers
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Ivana Lucica 5
HR-10000 Zagreb, Croatia
Phone: +385 1 6168 356
Rudjer Boskovic Institute
Center for Informatics and Computing
HR-10000 Zagreb, Croatia
Accepted papers will be published in the ISSN registered conference proceedings. Presented papers in English will be submitted for inclusion in the IEEE Xplore Digital Library (and exclusively not presented papers with the justified reason for not being able to be presented).
There is a possibility that the selected scientific papers with some further modification and refinement are being published in the Journal of Computing and Information Technology (CIT).
Opatija, with its 170-year-old tourism tradition, is the leading seaside resort of the Eastern Adriatic and one of the most famous tourist destinations on the Mediterranean. With its aristocratic architecture and style, Opatija has been attracting artists, kings, politicians, scientists, sportsmen, as well as business people, bankers and managers for more than 170 years.
The tourist offer in Opatija includes a vast number of hotels, excellent restaurants, entertainment venues, art festivals, superb modern and classical music concerts, beaches and swimming pools – this city satisfies all wishes and demands.
Opatija, the Queen of the Adriatic, is also one of the most prominent congress cities in the Mediterranean, particularly important for its ICT conventions, one of which is MIPRO, which has been held in Opatija since 1979, and has attracted more than a thousand participants from over forty countries. These conventions promote Opatija as one of the most desirable technological, business, educational and scientific centers in South-eastern Europe and the European Union in general.
For more details, please visit www.opatija.hr and visitopatija.com.
Robotics Conference and Sailing Hub - ROBOCO 2020
Robotics – Future of Technology World
Agile Event Contribution during the Croatian Presidency of the Council of Europe
In two and a half days until MIPRO 2020 we will explore, in an extraordinary environment, challenges facing societies today, but also in the near future in terms of the relationship between humans and robots in any field of life and business surroundings.
Impactful (Innovative) companies, scientists, engineers, entrepreneurs, ... will share their knowledge, experience and visions about robotics, artificial intelligence, machine vision and learning, IoTs, all kinds of robotics; drones, ground and underwater robots, and all related fields with stress to the new scientific and technological paradigms based on idea of breaking boundaries among digital, physical and biological domains for the benefit of modern technology based society.