scholarly journals Research on manipulator grasping method based on vision

2020 ◽  
Vol 309 ◽  
pp. 04004
Author(s):  
Lei Yang ◽  
Shiliang Wu ◽  
Zhenlong Lv ◽  
Feng Lu

Aiming at the problem that the manipulator cannot grasp the object accurately when the robot changes the position and pose of the object in the process of static grasping, a set of manipulator grasping method research based on vision is proposed. Firstly, a set of camera detection and robot grasping system model is built. Secondly, each coordinate system is created for the grasping system, and the transformation relation between each coordinate system, matrix model and the quantity that needs to be calibrated are introduced in detail. Thirdly, the trajectory function from the image coordinate system to the coordinates of the manipulator is obtained through the direct linear method calibration experiment. Finally, the experimental platform for camera detection and manipulator grasping objects based on xavis was built, and the grasping success rate of the experimental platform was tested. The experimental results show that the grasping error rate of the experimental platform is within the control range. Therefore, the manipulator grasping method based on vision is of reference significance for engineering applications.

2019 ◽  
Vol 220 (3) ◽  
pp. 2021-2038
Author(s):  
Jochen Kamm ◽  
Michael Becken ◽  
Rafael Abreu

SUMMARY Maxwell’s equations are valid regardless of the choice of the coordinate system. By this property a change of coordinates can be equivalently expressed as a change of the material parameters. This idea opens a new approach to the problem of accurate electromagnetic modelling in the vicinity of steep topography or bathymetry. Via a change of coordinates, any earth model with complicated layer interfaces can be represented by an equivalent model where those interfaces are flat, but with its materials correspondingly altered. This new model could then be discretized on a regular mesh and fields could be computed by an appropriate finite difference or integral equation code. Unfortunately, this is not straightforward because both the new electric and magnetic materials are fully anisotropic. By instead applying a finite element secondary field approach to the equivalent model, we can completely account for the topography interface in the planar layered background model. The only modification required to existing finite element formulations is a slightly more complicated right-hand side of the linear system of equations, whereas the system matrix is unchanged in any coordinate system. In a numerical modelling experiment we confirm that our technique gives increased accuracy when compared with a recently published technique for dealing with topography in a secondary field formulation for the case of a magnetotelluric source field. In turn, in the vicinity of conductivity anomalies, accuracy can also be negatively affected.


2019 ◽  
Vol 492 (3) ◽  
pp. 4546-4552
Author(s):  
Dmitrii E Vavilov

ABSTRACT This paper presents a robust linear method for impact probability estimation of near-Earth asteroids with the Earth. This method is a significantly modified and improved method, which uses a special curvilinear coordinate system associated with the nominal orbit of an asteroid. One of the coordinates of this system is the mean anomaly in the osculating orbit of an asteroid. A normal distribution of errors of coordinates and velocities of this system is assumed. Because of the usage of the curvilinear coordinate system, the fact that the confidence region is curved and stretched mainly along the nominal asteroid orbit is taken into account. On the main axis of the curvilinear confidence ellipsoid the virtual asteroid, which is the closest to the Earth, is found. The part of the curvilinear confidence ellipsoid, around the found virtual asteroid, is obtained and mapped on to its target plane. The impact probability is calculated as the probability of the asteroid being in the region of the found virtual asteroid multiplied by the probability of a collision of the found virtual asteroid with the Earth. This approach is shown to give more accurate and trustworthy results than the target plane method.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Zhengtuo Wang ◽  
Yuetong Xu ◽  
Guanhua Xu ◽  
Jianzhong Fu ◽  
Jiongyan Yu ◽  
...  

Purpose In this work, the authors aim to provide a set of convenient methods for generating training data, and then develop a deep learning method based on point clouds to estimate the pose of target for robot grasping. Design/methodology/approach This work presents a deep learning method PointSimGrasp on point clouds for robot grasping. In PointSimGrasp, a point cloud emulator is introduced to generate training data and a pose estimation algorithm, which, based on deep learning, is designed. After trained with the emulation data set, the pose estimation algorithm could estimate the pose of target. Findings In experiment part, an experimental platform is built, which contains a six-axis industrial robot, a binocular structured-light sensor and a base platform with adjustable inclination. A data set that contains three subsets is set up on the experimental platform. After trained with the emulation data set, the PointSimGrasp is tested on the experimental data set, and an average translation error of about 2–3 mm and an average rotation error of about 2–5 degrees are obtained. Originality/value The contributions are as follows: first, a deep learning method on point clouds is proposed to estimate 6D pose of target; second, a convenient training method for pose estimation algorithm is presented and a point cloud emulator is introduced to generate training data; finally, an experimental platform is built, and the PointSimGrasp is tested on the platform.


Actuators ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 85
Author(s):  
Jiang Hua ◽  
Liangcai Zeng

A robot can identify the position of a target and complete a grasping based on the hand–eye calibration algorithm, through which the relationship between the robot coordinate system and the camera coordinate system can be established. The accuracy of the hand–eye calibration algorithm affects the real-time performance of the visual servo system and the robot manipulation. The traditional calibration technique is based on a perfect mathematical model AX = XB, in which the X represents the relationship of (A) the camera coordinate system and (B) the robot coordinate system. The traditional solution to the transformation matrix has a certain extent of limitation and instability. To solve this problem, an optimized neural-network-based hand–eye calibration method was developed to establish a non-linear relationship between robotic coordinates and pixel coordinates that can compensate for the nonlinear distortion of the camera lens. The learning process of the hand–eye calibration model can be interpreted as B=fA, which is the coordinate transformation relationship trained by the neural network. An accurate hand–eye calibration model can finally be obtained by continuously optimizing the network structure and parameters via training. Finally, the accuracy and stability of the method were verified by experiments on a robot grasping system.


Author(s):  
Na Xiang ◽  
Fa-fa Wang ◽  
Bin-bin Wang ◽  
Sheng-lun Yi ◽  
Xue-bo Jin ◽  
...  

Wearable technology has been proposed as a potential tool to change the way of human life, such as the smart bracelet and the Google Glass. In the wearable technology, the inertial sensor has great significance in tracking the object movements. The paper focused on detecting the movements of user’s finger based on the inertial sensor to give the control signals. Firstly, the attitude matrix, which represented the transformation relation of carrier coordinate system and the navigation coordinate system, was obtained. Secondly, the attitude matrix was expressed based on the quaternions. Thirdly, the finger gesture was processed by the attitude matrix to get the attitude angle. Finally, the robot was controlled by attitude angle to make the moving action. The experimental results showed the detection of the finger movement is effective.


1975 ◽  
Vol 26 ◽  
pp. 87-92
Author(s):  
P. L. Bender

AbstractFive important geodynamical quantities which are closely linked are: 1) motions of points on the Earth’s surface; 2)polar motion; 3) changes in UT1-UTC; 4) nutation; and 5) motion of the geocenter. For each of these we expect to achieve measurements in the near future which have an accuracy of 1 to 3 cm or 0.3 to 1 milliarcsec.From a metrological point of view, one can say simply: “Measure each quantity against whichever coordinate system you can make the most accurate measurements with respect to”. I believe that this statement should serve as a guiding principle for the recommendations of the colloquium. However, it also is important that the coordinate systems help to provide a clear separation between the different phenomena of interest, and correspond closely to the conceptual definitions in terms of which geophysicists think about the phenomena.In any discussion of angular motion in space, both a “body-fixed” system and a “space-fixed” system are used. Some relevant types of coordinate systems, reference directions, or reference points which have been considered are: 1) celestial systems based on optical star catalogs, distant galaxies, radio source catalogs, or the Moon and inner planets; 2) the Earth’s axis of rotation, which defines a line through the Earth as well as a celestial reference direction; 3) the geocenter; and 4) “quasi-Earth-fixed” coordinate systems.When a geophysicists discusses UT1 and polar motion, he usually is thinking of the angular motion of the main part of the mantle with respect to an inertial frame and to the direction of the spin axis. Since the velocities of relative motion in most of the mantle are expectd to be extremely small, even if “substantial” deep convection is occurring, the conceptual “quasi-Earth-fixed” reference frame seems well defined. Methods for realizing a close approximation to this frame fortunately exist. Hopefully, this colloquium will recommend procedures for establishing and maintaining such a system for use in geodynamics. Motion of points on the Earth’s surface and of the geocenter can be measured against such a system with the full accuracy of the new techniques.The situation with respect to celestial reference frames is different. The various measurement techniques give changes in the orientation of the Earth, relative to different systems, so that we would like to know the relative motions of the systems in order to compare the results. However, there does not appear to be a need for defining any new system. Subjective figures of merit for the various system dependon both the accuracy with which measurements can be made against them and the degree to which they can be related to inertial systems.The main coordinate system requirement related to the 5 geodynamic quantities discussed in this talk is thus for the establishment and maintenance of a “quasi-Earth-fixed” coordinate system which closely approximates the motion of the main part of the mantle. Changes in the orientation of this system with respect to the various celestial systems can be determined by both the new and the conventional techniques, provided that some knowledge of changes in the local vertical is available. Changes in the axis of rotation and in the geocenter with respect to this system also can be obtained, as well as measurements of nutation.


1975 ◽  
Vol 26 ◽  
pp. 21-26

An ideal definition of a reference coordinate system should meet the following general requirements:1. It should be as conceptually simple as possible, so its philosophy is well understood by the users.2. It should imply as few physical assumptions as possible. Wherever they are necessary, such assumptions should be of a very general character and, in particular, they should not be dependent upon astronomical and geophysical detailed theories.3. It should suggest a materialization that is dynamically stable and is accessible to observations with the required accuracy.


Sign in / Sign up

Export Citation Format

Share Document