Dynamic sensor-based control of robots with visual feedback

Weiss, Lee E.; Sanderson, Arthur C.; Neuman, C. P.

doi:10.1109/jra.1987.1087115

Cited by 732 publications

(279 citation statements)

References 12 publications

Supporting

Mentioning

269

Contrasting

Unclassified

Order By: Relevance

“…Visual features can be drawn from a large class of visual measurements [23,15], but we have found that the ones which can be represented as point positions or point vectors in camera space are suitable [16]. We track features such as boundary discontinuities (lines,corners) and surface markings.…”

Section: Viewing Modelmentioning

confidence: 99%

“…Visual servoing, when supplemented with online visual model estimation, fits into the active vision paradigm. Results with visual servoing and varying degrees of model adaption have been presented for robot arms [23,4,21,15,16,13,2,11] 2 . Visual models suitable for specifying visual alignments have also been studied [9,1,10], but it remains to be proven that the approach works on more complex manipulators than the serial link robot arm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Acquiring visual-motor models for precision manipulation with robot hands

Jägersand

Fuentes

Nelson

1996

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Dextrous high degree of freedom (DOF) robotic hands provide versatile motions for fine manipulation of potentially very different objects. However, fine manipulation of an object grasped by a multifinger hand is much more complex than if the object is rigidly attached to a robot arm. Creating an accurate model is difficult if not impossible. We instead propose a combination of two techniques: the use of an approximate estimated motor model, based on the grasp tetrahedron acquired when grasping an object, and the use of visual feedback to achieve accurate fine manipulation. We present a novel active vision based algorithm for visual servoing, capable of learning the manipulator kinematics and camera calibration online while executing a manipulation task. The approach differs from previous work in that a full, coupled image Jacobian is estimated online without prior models, and that a trust region control method is used, improving stability and convergence. We present an extensive experimental evaluation of visual model acquisition and visual servoing in 3, 4 and 6 DOF.

show abstract

Section: Viewing Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Acquiring visual-motor models for precision manipulation with robot hands

Jägersand

Fuentes

Nelson

1996

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Recently, there have been many studies on visual servoing control schemes utilizing the visual sensors to increase the capability of the robot systems in the dynamic environments(you can find a summary in [1]). In these days, many studies focus on control schemes which make features on the image planes converge to the desired values [2][3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Visual Servoing Utilizing Zoom Mechanism.

Hosoda

Moriyama

Asada

1998

Journal of the Robotics Society of Japan

View full text Add to dashboard Cite

“…For vision-based robots, image features on the image planes are primitive descriptions of the environments. In this sense, featurebased visual servoing control is the most fundamental one for the vision-based robots in which image features are controlled to converge to the desired ones, and therefore has been focused by a number of researchers [2][3][4][5][6][7][8][9][10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

“…Such a controller, however, is not robust for disturbances and changes of the parameters. To overcome this problem, some on-line parameter identification schemes have been proposed [8][9][10][11][12][13]. Weiss et al [8] assumed that the system could be modeled by linear SISO (Single Input Single Output) equations, and applied an MRAC (Model Reference Adaptive Control) controller.…”

Section: Introductionmentioning

confidence: 99%

Adaptive visual servoing for various kinds of robot systems

Hosoda

Asada

1998

Experimental Robotics V

View full text Add to dashboard Cite

This paper propose an adaptive visual servoing method consisting of an on-line estimator of the robot/image Jacobian matrix and a feedback/feedforward controller for uncalibrated camera-manipulator systems. The estimator does not need a priori knowledge on the kinematic structure nor on parameters of the camera-manipulator system. The controller consists of feedforward and feedback terms to make the image features converge to the desired trajectories using the estimated results. Some experimental results are given to show the validity of the proposed method.

show abstract

Dynamic sensor-based control of robots with visual feedback

Cited by 732 publications

References 12 publications

Acquiring visual-motor models for precision manipulation with robot hands

Acquiring visual-motor models for precision manipulation with robot hands

Visual Servoing Utilizing Zoom Mechanism.

Adaptive visual servoing for various kinds of robot systems

Contact Info

Product

Resources

About