Ovaj odjel zanima se za teme iz područja teorije i primjene robotike i automatizacije. Pod robotikom se ovdje prvenstveno podrazumijeva zanimanje za inteligentne strojeve i sustave korištene, na primjer, u istraživanju okoliša (podmorja, svemira), pružanju usluga ljudima, ili u naprednoj proizvodnji. Pod automatizacijom se prvenstveno podrazumijeva zanimanje za primjenu automatizacijskih metoda i postupaka u tvornicama, uredima, kućanstvima ili, na primjer, u transportnim sustavima s ciljem povećanja njihove djelotvornosti i produktivnosti.
Odjel za robotiku i automatizaciju
IEEE Hrvatska sekcija, Odjel za robotiku i automatizaciju i ZCI-ACROSS vas pozivaju na predavanje
"Design of wearable IMU Sensors-data fusion for a user friendly mobility assistive device"
koje će održati Dr. Omar Nour, poslijedoktorand u Laboratoriju za robotiku i inteligentne upravljačke sustave (LARICS), Fakultet elektrotehnike i računarstva Sveučilišta u Zagrebu, Hrvatska.
Predavanje će se održati u ponedjeljak, 8. svibnja 2017. s početkom u 11:00 sati u Seminaru Zavoda za automatiku i računalno inženjerstvo (ZARI) na IX katu C zgrade Fakulteta elektrotehnike i računarstva. Više o predavaču i predavanju možete naći u nastavku obavijesti.
Abstract:
The ability of sit to stand has been considered an important activity in person’s functional independence. Therefore, recently, many studies have analyzed the sit to stand motion. These studies were very important to estimate the risk of fall for elderly people. In addition, they were also used in the field of rehabilitation and assistive devices. The most challenging task in the development of a rehabilitation device is to measure the posture of human to synchronize the motion of the device with human.
This Research describes two methods for measuring the posture of a human body during different phases of sit to stand motion using inertial sensors. The first Method fuses data from inertial sensors placed in trunk and thigh using Adaptive Neuro-Fuzzy Inference System (ANFIS) followed by a Kalman Filter (KF). The ANFIS attempts to estimate the position of shoulder of the human, at each sampling instant when measurement update step is carried out. The Kalman filter supervises the performance of the ANFIS with the aim of reducing the mismatch between the estimated and actual. The performance of this method is verified by measurements from VICON, motion analysis system. In the Second method, the angles of ankle, knee and hip are calculated from the quaternions data obtained from three inertial sensors placed in trunk, thigh and shank. Then the obtained angles are applied to the human model to find the human posture. The performance of this method is verified by measurements from Optatrack, motion analysis system. The output results show that the estimated position is close enough to the value obtained by the human motion capture system. Therefore, it is believed that the developed sensor system can be used for mobility assistive technology. So the methods are tested with EJAD (Egypt Japan Assistive Device) and support robot developed at Waseda University. The results indicate that the generated path for EJAD is close to the real path of healthy subjects.
CV:
Omar Nour is a Postdoctoral Research Fellow at LARICS. He received his B. Sc. Degree in mechatronics section from Mechanical Engineering Department, Assiut University with grade distinction with honors degree in 2007. He received his M. Sc. and Ph. D. in mechatronics and robotics engineering from Innovation Design Engineering School, Egypt-Japan University of Science and Technology (E-JUST) in 2012, 2015 respectively. He worked as exchange researcher at Waseda University in Japan. He also worked as a Lecturer (assistant professor) at Mechanical Engineering Department, Faculty of Engineering, Assiut University.
His current research interests include industrial robotics, Mechatronics, Assistive devices, human motion analysis and humanoid robotics.