Abstract
In this paper, a global-state-space visual servoing scheme is proposed for uncalibrated model-independent robotic manipulation. The scheme is based on robust Kalman filtering (KF), in conjunction with Elman neural network (ENN) learning techniques. The global map relationship between the vision space and the robotic workspace is learned using an ENN. This learned mapping is shown to be an approximate estimate of the Jacobian in global space. In the testing phase, the desired Jacobian is arrived at using a robust KF to improve the ENN learning result so as to achieve robotic precise convergence of the desired pose. Meanwhile, the ENN weights are updated (re-trained) using a new input-output data pair vector (obtained from the KF cycle) to ensure robot global stability manipulation. Thus, our method, without requiring either camera or model parameters, avoids the corrupted performances caused by camera calibration and modeling errors. To demonstrate the proposed scheme's performance, various simulation and experimental results have been presented using a six-degree-of-freedom robotic manipulator with eye-in-hand configurations.
Highlights
Visual sensors integrated with robotic manipulators can be increasingly beneficial for robotic perception and behavioral flexibility in unstructured environments [1]; such sensors have caught much attention, and have applications in all walks of life [2,3,4,5].Vision-based robotic manipulation depends mainly on visual information feedback to control the positioning or motioning of a manipulator [6]
(2) The Kalman filtering (KF) is sensitive with respect to the initial robotic state and the initial noises’ statistical characteristics
The Elman neural network (ENN) was adopted as a global estimator for Jacobian learning, and the global map relationship between vision space and the robot workspace is represented by the ENN
Summary
Visual sensors integrated with robotic manipulators can be increasingly beneficial for robotic perception and behavioral flexibility in unstructured environments [1]; such sensors have caught much attention, and have applications in all walks of life [2,3,4,5]. The Jacobian estimation task may involve singularity instability in global space; failure to have end-effector positioning in cases of large displacement between the initial and desired poses is a risk Another solution to this estimation problem involves machine learning techniques [25,26], which are based on biologically inspired approaches, such as neural networking. (2) The KF is sensitive with respect to the initial robotic state and the initial noises’ statistical characteristics (i.e., a small perturbation of noise characteristics to dynamic modeling will lead to serious positioning error) For this problem, the ENN was adopted as a global estimator for Jacobian learning, and the global map relationship between vision space and the robot workspace is represented by the ENN.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
