Texture Identification and Object Recognition Using a Soft Robotic Hand Innervated Bio-Inspired Proprioception

نویسندگان

چکیده

In this study, we innervated bio-inspired proprioception into a soft hand, facilitating robust perception of textures and object shapes. The tendon-driven finger with three joints, inspired by the human finger, was detailed. With tension sensors embedded in tendon that simulate Golgi organ body, 17 types can be identified under uncertain rotation angles actuator displacements. Four classifiers were used highest identification accuracy 98.3%. A three-fingered hand based on bionic developed. Its basic grasp capability tested experimentally. distinguish 10 objects vary shape top side grasp, accuracies 96.33% 96.00%, respectively. Additionally, for six close shapes, obtained an 97.69% scan-grasp method. This study offers novel solution texture recognition manipulators.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

DrawBot: a bio-inspired robotic portraitist

We are developing the control architecture of a portraitist artificial agent called DrawBot that reproduces the visuomotor behaviour of a human carrying out a realistic portrait. The visuomotor strategy adopted by DrawBot is based on computational models of eye movements in human beings, and on experimental findings on eye-hand coordination in expert draughtsmen. In this paper we present a beha...

متن کامل

Design and control of a bio-inspired soft wearable robotic device for ankle-foot rehabilitation.

We describe the design and control of a wearable robotic device powered by pneumatic artificial muscle actuators for use in ankle-foot rehabilitation. The design is inspired by the biological musculoskeletal system of the human foot and lower leg, mimicking the morphology and the functionality of the biological muscle-tendon-ligament structure. A key feature of the device is its soft structure ...

متن کامل

Bio-Inspired NMF Object Perception

The paper describes Neural Modeling Fields (NMF) for object perception, a bio-inspired paradigm. I discuss previous difficulties in object detection and recognition, and describe how NMF overcomes this difficulties. Neural and mathematical mechanisms are described and future research directions outlined. I. PAST DIFFICULTIES, COMPLEXITY AND LOGIC Biological object perception involves signals fr...

متن کامل

A Bio-inspired Strategy for Optimal Grasp of an Anthropomorphic Robotic Hand

Safety and dependability are basic requirements for human-robot interaction. Bio-medical robotics is one area of robotics where the need to comply with these requirements is obvious. In all the applications requiring tight human-robot interaction, such as assistive robotics or else prosthetics, grasp stability is a fundamental requirement to address, in order to ensure a safe and reliable inter...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Machines

سال: 2022

ISSN: ['2075-1702']

DOI: https://doi.org/10.3390/machines10030173