23.7ROMar 13
Reinforcement Learning for Elliptical Cylinder Motion Control TasksPawel Marczewski, Paulina Superczynska, Jakub Bernat et al.
The control of devices with limited input always bring attention to solve by research due to its difficulty and non-trival solution. For instance, the inverted pendulum is benchmarking problem in control theory and machine learning. In this work, we are focused on the elliptical cylinder and its motion under limited torque. The inspiration of the problem is from untethered magnetic devices, which due to distance have to operate with limited input torque. In this work, the main goal is to define the control problem of elliptic cylinder with limited input torque and solve it by Reinforcement Learning. As a classical baseline, we evaluate a two-stage controller composed of an energy-shaping swing-up law and a local Linear Quadratic Regulator (LQR) stabilizer around the target equilibrium. The swing-up controller increases the system's mechanical energy to drive the state toward a neighborhood of the desired equilibrium, a linearization of the nonlinear model yields an LQR that regulates the angle and angular-rate states to the target orientation with bounded input. This swing-up + LQR policy is a strong, interpretable reference for underactuated system and serves a point of comparison to the learned policy under identical limits and parameters. The solution shows that the learning is possible however, the different cases like stabilization in upward position or rotating of half turn are very difficult for increasing mass or ellipses with a strongly unequal perimeter ratio.
SYJul 18, 2024
The Construction of a Soft Gripper Based on Magnetorheological Elastomer with Permanent MagnetJakub Bernat, Pawel Czopek, Paulina Superczynska et al.
Recently, magnetorheological elastomers have become an interesting smart material with many new designs for robotics. A variety of applications have been built with magnetorheological elastomers, such as vibration absorbers, actuators, or grippers, showing that this material is promising for soft robotics. In this work, the novel concept of a gripper is proposed, exploring the features of a magnetorheological elastomer and permanent magnet. The gripper uses the energy of a permanent magnet to provide a self-closing gripping mechanism. The usage of flexible material enables one to hold delicate objects of various shapes. This paper presents the rolling effect of magnetorheological elastomer and permanent magnet, the design process, and the features of the soft gripper. The effectiveness of the soft gripper was validated in a series of experiments that involved lifting different objects.
SYOct 28, 2022
Magnetorheological Axisymmetric Actuator with Permanent MagnetJakub Bernat, Paulina Superczynska, Piotr Gajewski et al.
This study examines the concept of axisymmetric actuator based on the magnetorheological membrane, electromagnet and permanent magnet. The construction of the actuator enables its application in wide range of practical devices like pumping, loudspeaker or varying-stiffness button. This work will highlight its working principle especially the influence of permanent magnet. Furthermore, the model of devices will be defined relaying on the Hammerstein model. To show the properties of the actuator and to perform the model identification, the set of experiments was run taking into account static and dynamic working conditions.