Paper Contents
Abstract
One of the trickiest uses of soft computing approaches is robotics. Its sensory feedback, intricate control mechanism, and direct interface with the outside environment are its defining features. This study examines the use of soft computing techniques, specifically neural networks, in the area of robotic manipulator visual servoing. Neural network-based networks perform similarly to many other absolute apple dynamic systems in nonlinear tracking controllers. Aptitude systems are non-linear and suitably seek an acceptable adjustment of authoritative the system's actions. In order to address this issue, the layout must be linearized and various beeline system controls must be applied once more to manage the system. The ability of a lyapunoy stability adjustment to be accepted by the subtask tracking system would depend on how proficient the redundant manipulators were in the linearization process. Numerous robotic jobs falling within the purview of visual servoing are identified, and the challenges associated with using soft computing techniques to address these concerns are talked about. The study offers some useful recommendations for using neural networks on these kinds of tasks.
Copyright
Copyright © 2023 RAHUL SHARMA. This is an open access article distributed under the Creative Commons Attribution License.
