Full Length Research Paper
Abstract
In order to improve pose accuracy of a parallel robot in the application, a compensator is constructed to predict leg length errors using back propagation neural network. In this method, the back propagation neural network is used with conventional inverse kinematics computation module in parallel. A back propagation neural network is designed and implemented to learn kinematic model errors for parallel robots. The non-linear mapping from the operation variable space for the mobile platform to the joint variable space is accomplished solving the location and posture. The trained neural network can be used to performed on-line pose accuracy compensation in the task. Simulation and experimental results show that this method provides a good pose accuracy improvement and keeps good robustness and adaptability at the same time.
Key words: Parallel robot, pose accuracy, back propagation network, kinematic calibration, error compensation.
Copyright © 2024 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0