Design and Analysis of six DOF Robotic Manipulator

Pratheep, V. G.; Chinnathambi, M.; Priyanka, E. B.; Ponmurugan, P; Thiagarajan, Pridhar

doi:10.1088/1757-899x/1055/1/012005

Cited by 8 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a commercial Franka Emika Panda 7-DOF manipulator for this work, as the redundant DOF provides a much larger dexterous workspace compared to 6-DOF ones [25][26][27], which we found to be crucial for grasping objects in arbitrary orientation [28,29]. In addition, the manipulator's electrically adjustable compliance greatly helped prevent possible damage to the delicate robotic hand.…”

Section: Manipulator Armmentioning

confidence: 99%

Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

Kim

Kang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

This paper presents an autonomous grasping approach for complex-shaped objects using an anthropomorphic robotic hand. Although human-like robotic hands have a number of distinctive advantages, most of the current autonomous robotic pickup systems still use relatively simple gripper setups such as a two-finger gripper or even a suction gripper. The main difficulty of utilizing human-like robotic hands lies in the sheer complexity of the system; it is inherently tough to plan and control the motions of the high degree of freedom (DOF) system. Although data-driven approaches have been successfully used for motion planning of various robotic systems recently, it is hard to directly apply them to high-DOF systems due to the difficulty of acquiring training data. In this paper, we propose a novel approach for grasping complex-shaped objects using a high-DOF robotic manipulation system consisting of a seven-DOF manipulator and a four-fingered robotic hand with 16 DOFs. Human demonstration data are first acquired using a virtual reality controller with 6D pose tracking and individual capacitive finger sensors. Then, the 3D shape of the manipulation target object is reconstructed from multiple depth images recorded using the wrist-mounted RGBD camera. The grasping pose for the object is estimated using a residual neural network (ResNet), K-means clustering (KNN), and a point-set registration algorithm. Then, the manipulator moves to the grasping pose following the trajectory created by dynamic movement primitives (DMPs). Finally, the robot performs one of the object-specific grasping motions learned from human demonstration. The suggested system is evaluated by an official tester using five objects with promising results.

show abstract

Section: Manipulator Armmentioning

confidence: 99%

Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

Kim

Kang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Today, the development of technology is very fast, and everything seems to run so fast. Particularly related to the development and utilization of robot technology, both on a small and industrial scale [1], [2]. One type of robot that is widely used on an industrial scale is the robotic manipulator.…”

Section: Introductionmentioning

confidence: 99%

“…The arms are connected through joints that can move in rotation and translation related to the ability of the robot to move freely, which is called degree of freedom (DOF) [5]. Many studies have been carried out related to the development of robotic manipulator systems [2]- [4], [6]- [11]. However, most of the studies carried out are related to the system design and sensors used.…”

Section: Introductionmentioning

confidence: 99%

Rotation Component of Robotic Manipulator Motion in 4-Dof by the Quaternion Method

Yasmini,

Isna,

Risha

2024

IPR

View full text Add to dashboard Cite

Most of the study of robots is about the system. Because of that, we analyze the motion of the robot by using rigid body motion concepts. This study aims to analyze the rotation components of a robotic manipulator with four degrees of freedom (4-DoF) by using the quaternion method of manual analysis so that the end effector of the robotic manipulator under study is obtained. The research is theoretical and was conducted through a review and analysis of related literature. Based on the literature review, the robotic manipulator is a robot with a shape resembling an arm. The robotic manipulator consists of bases, links, joins, and an end effector. In terms of physics, the kinematics of robot motion can be studied based on the concept of rigid body motion. The research shows that the quaternion method can be used to determine the end effector of the rotation component of the robotic manipulator, and the steps are shorter than analyses by using screw and twist theory. Based on this case, the end effector of the rotation component depends on the initial state and the total rotation angle of each join.

show abstract

“…An offline programming technique was used to build the method. Pratheep et al [10] used SolidWorks to create a six-DOF manipulator and then analyzed its motion, load capacity, and route traceability. To circumvent the issue of singularity, Zhao et al [11] used the product of the exponentials approach for kinematics modeling.…”

Section: Introductionmentioning

confidence: 99%

Surgical Self- steering Robot using Artificial Neural Network

Mahfouz,

Gamal,

Awad

et al. 2023

Preprint

View full text Add to dashboard Cite

The aim of this work is to design a robot that can be used in surgery and can remove tumors by accurately and safely following contours. This is achieved by the medical imaging set such as DICOM-formatted images from several sources (CT, MRI, and Ultrasound) of these tumors using artificial neural networks. The workspace of a suggested 7 degrees of freedom robot is defined by calculating the position of the end effector for multiple positions of its links using DH tables and feed-forward kinematics. The data obtained are used to train three artificial neural networks to get the inverse kinematics. The suggested neural networks are the Generalized Regression Neural Network, Radial Basis, and Feed Forward. A training course for inverse kinematics of 23328 workspace points of the end effector of the suggested robot is used for training the three neural networks. The most accurately trained one was found to be the Feed-Forward neural network. It shows a root mean square error for those points of 2.08 mm and a training time of 1236 seconds and is to be applied to steer the robot links. The patient medical images are digitized using the image processing toolbox of MATLAB. The data obtained is to be fed to the superior neural network to get the robot links positions needed to move the end effector mounted with a cutter to follow the tumor contour accurately. The absolute error distance between the corresponding points of the contours resulting from testing the trained Feed-Forward NN with 51 points of a contour doesn’t exceed 2.08 mm.

show abstract

Design and Analysis of six DOF Robotic Manipulator

Cited by 8 publications

References 7 publications

Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

Anthropomorphic Grasping of Complex-Shaped Objects Using Imitation Learning

Rotation Component of Robotic Manipulator Motion in 4-Dof by the Quaternion Method

Surgical Self- steering Robot using Artificial Neural Network

Contact Info

Product

Resources

About