Abstract
Underactuated robotic finger could be used as adaptive mechanism with simple control algorithm. In this study the main aim was to estimate the robotic finger contact forces by soft computing methods. Soft computing approach was applied in order to overcome high nonlinearity in the finger behavior. Kinetostatic analysis was performed in order to extract the input/output data samples for the soft computing methods. The main goal was to estimate the contact forces based on contact locations with the objects. Seven soft computing methods were applied: genetic programming, support vector machine, support vector machine with firefly algorithm, artificial neural network, support vector machine with wavelet transfer function), extreme learning machine and extreme learning machine with wavelet transfer function. The reliability of these computational models was analyzed based on simulation results. Extreme learning machine with wavelet transfer function shown the best accuracy for the contact forces estimation.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.