2020/03/02 by Michał Bednarek, Piotr Kicki, Bednarek, Michał +5
Computer Science · Engineering · Neuroscience · #Artificial intelligence #Artificial neural network #Computer science #Computer vision #Control engineering #Engineering #FOS: Computer and information sciences #Grippers #Inertial frame of reference #Inertial measurement unit #Machine Learning (cs.LG) #Mechanical engineering #Object (grammar) #Physical system #Physics #Robot #Robot Manipulation and Learning #Robotics (cs.RO) #Simulation #Soft Robotics and Applications #Soft computing #Soft robotics #Soft sensor #Stiffness #Structural engineering #Tactile and Sensory Interactions #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2003.00784
published in arXiv (Cornell University) (Cornell University) · Submitted to IEEE IROS 2020
openalex publication_date 2020/03/02 · arxiv created 2020/03/03 · arxiv updated 2020/03/04 · openalex created_date 2020/03/06 · openalex updated_date 2026/07/28
Soft grippers are gaining significant attention in the manipulation of elastic objects, where it is required to handle soft and unstructured objects which are vulnerable to deformations. A crucial problem is to estimate the physical parameters of a squeezed object to adjust the manipulation procedure, which is considered as a significant challenge. To the best of the authors' knowledge, there is not enough research on physical parameters estimation using deep learning algorithms on measurements from direct interaction with objects using robotic grippers. In our work, we proposed a trainable system for the regression of a stiffness coefficient and provided extensive experiments using the physics simulator environment. Moreover, we prepared the application that works in the real-world scenario. Our system can reliably estimate the stiffness of an object using the Yale OpenHand soft gripper based on readings from Inertial Measurement Units (IMUs) attached to its fingers. Additionally, during the experiments, we prepared three datasets of signals gathered while squeezing objects -- two created in the simulation environment and one composed of real data.