Soft Robotics and Control Lab

Melih Turkseven is currently an Assistant Professor in the Faculty of Engineering and Sciences at Sabancı University, Istanbul, Turkey. He received his B.S. degree in Mechanical Engineering at Boğaziçi University in 2010, and his Ph.D. degree in Mechanical Engineering at the Georgia Institute of Technology in 2016.

Following his graduate study, he joined the Center for Modeling, Simulation, and Imaging (CeMSIM) at Rensselaer Polytechnic Institute as a post-doctoral research associate, where he developed haptic interfaces for surgical virtual reality simulators.

His research interests include control of dynamic systems, design and characterization of haptic systems, control of human machine interfaces and soft robotics.

Email: melih.turkseven@sabanciuniv.edu
Location: FENS L018

I’m Ali Ebrazeh, a master’s student in Mechatronics Engineering at Sabancı University. I earned my bachelor’s degree in mechanical engineering from the University of Tehran. I’m currently working at the Soft Robotics and Control Laboratory (SRCL). My main research interest is data-driven modeling and control of robotic systems, from classical approaches to reinforcement learning. At the moment, I’m focused on developing a physically realistic and computationally efficient simulation environment for soft robots using MuJoCo, to support future work in learning-based control and design.

I am Araz Haghnazari Esfahlan, a Master of Science student at Sabanci University. I obtained my bachelor’s degree in mechanical engineering from the University of Tabriz, specializing in modeling and controlling dynamical systems. I am researching at the Soft Robotics and Control Laboratory (SRCL). My research focuses on the design, prototyping, and control of soft actuators. I leverage my background in mechanical engineering to contribute to advancements in the field, with a particular emphasis on the intersection of modeling and control for soft robotic systems.

I'm Elham Banaepour Ghaffari, an engineer with a background in Electronic and Control Engineering. Currently, I am working towards my master’s degree in mechatronics engineering at the Soft Robotics and Control Laboratory (SRCL). My research is centered around soft robotics, with a particular focus on the development of a novel pneumatically driven soft elbow exoskeleton.

I am Zaid Mustafa, a graduate student pursuing a master’s degree in Mechatronics Engineering at Sabancı University. From my Mechatronics Engineering Bachelor's degree, I have an academic journey based on mechanical, control, and electrical engineering foundations, upon which I constantly build. My current research lies within the field of soft robotics. My research project focuses on the design and control of a hyper-redundant under-actuated soft robot with programmable stiffness.

Soft actuators are well-suited for upper-extremity physical assistance devices due to their typically lower weight compared to rigid actuators, as the effectiveness of an upper-extremity assistance system decreases with added weight. This is especially important for elbow exoskeletons, where providing flexion and extension assistance requires a mechanism positioned between the upper and lower arm, often placing additional weight on the user’s shoulder. This study aims to evaluate the effectiveness of multi-actuator pneumatically driven soft exoskeletons in delivering optimal physical assistance, despite the kinematic complexity of the target limb and variations in operational configurations. Ideally, the force exerted by the exoskeleton should malign tangentially with the natural movement path of the limb, avoiding axial loads that could cause discomfort.

Soft pneumatic actuators have been very popular for their high power-to-weight ratio and ability to yield significantly large motions. However, these actuators are usually limited in delivering reconfigurable deformation, limiting their versatility. A recent direction to rectify this limitation is to couple pneumatic actuation with active materials. Our aim is to explore the potential of this idea in accomplishing complex robotic tasks such as grasping, locomotion and human-machine interaction. This project proposes a novel pneumatically driven soft actuation unit that employs the reprogrammable stiffness concept to deliver reconfigurable deformation characteristics. Stiffness modulation is enabled via 3D-printed elements made of PLA.

Cement clinker production is an energy-intensive process that accounts for a substantial share of global industrial energy consumption. Model predictive control (MPC) is commonly used to regulate this process, requiring a compact control-oriented model that describes the input-output relationships of the production system. This project introduced a methodology for mapping these dynamically coupled internal variables by modeling the production process as a network of interconnected chambers. The developed model consistently outperformed alternative commonly used linear models in predicting their variations, particularly when the prediction horizon extends.