Kinematic identification using measurements in 2-D image space was not affected by issues associated with observability which is commonly encountered when measurements of 3-D pose are used. The advantages are well defined experimental strategy and identification of externally defined coordinate frames. The use of camera enabled the combination of geometric and parametric techniques of identification. This is in contrast with multiple stages used earlier. Measurement of end-effector 3- D poses required as input for this process is bypassed by measurements solely in 2-D image space, thus permitting estimation of corrections in parameters in a single stage. This article proposes a new method for kinematic identification of an industrial robot using a monocular camera mounted on its end-effector. The end-effector errors could be reduced by 45% after compensating errors due to kinematic and elasto-static parameters while using the proposed method wherein measurements from a monocular camera were used. Measured values for position repeatability of the robot were close to the robot specifications as well. Deflection due to loading on the end-effector, calculated using pose measurements from an industrial camera was found comparable to that from a laser tracker. Later the end-effector of the robot was subjected to an external load. During experimental validation on the Fanuc 165F robot, the kinematic parameters were initially estimated and the results were found to be superior compared to a recently proposed approach while considering the errors in positioning. It was found that most of the workspace regions of the robot where the experiments were feasible, had high values of observability which simplified the experiments. Coupled with the proposed strategy of experiments, it was possible to check the observability of parameters throughout the whole workspace. The joint compliance values were obtained using a two-stage approach which made it easy to analyze the observability of parameters to be identified. The measurements were made using a monocular camera utilizing fiducial markers. The method of identification involved a parametric method for estimation and the experimental strategy involved joint wise actuation about a particular pose, inspired by the geometric method of parameter identification. This article discusses the identification of elasto-static parameters of an industrial robot using measurements from a monocular camera. The experimental results for tracking control tasks performed on an industrial robot are given to illustrate the effectiveness of the proposed method. An analytic layer-wise deep learning framework is proposed where the deep network is progressively built and trained, and the convergence of the tracking error is guaranteed during the online learning process. In this article, we use a deep network to approximate the Jacobian matrix of a robot with unknown kinematics. Since stability and convergence are critical in robot control, our main aim is to develop a theoretical framework for using deep networks in robotics in a safe and predictable manner. This is due to the fact that convergence analysis is difficult for deep networks. However, existing literature on feedback control of robots mainly focuses on shallow networks where the analysis is developed for the output weights only and the linearity in parameters is often a requirement. Neural networks have been extensively used in robot control for various applications because of their powerful capability in approximation of nonlinear functions.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |