RNN based kinematic control scheme with a novel performance index

Ying Ye; Xuchong Zhang; Kezheng Sun; Yangmin Ou

doi:10.1117/12.2652490

6 September 2022 RNN based kinematic control scheme with a novel performance index

Ying Ye, Xuchong Zhang, Kezheng Sun, Yangmin Ou

Proceedings Volume 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022); 123321E (2022) https://doi.org/10.1117/12.2652490
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 2022, Chengdu, China

Abstract

As a core problem in the field of robotics, kinematic control plays an important role in the control of redundant manipulators. In this paper, a joint control strategy is proposed for kinematic control of redundant manipulators. This strategy transforms the traditional solution of objective function extremum into recurrent neural network (RNN) solution, which not only reduces the amount of computation, but also restricts the joint states of the manipulator to a certain extent and ensures the safety. Finally, a new kinematic control optimization index is proposed, which combines the kinetic energy of the manipulator with the minimum norm of joint velocity. The effectiveness and rationality of the proposed method and optimization index are verified on FRANKA platform which is a 7-DoF redundant manipulator. It aims to effectively reduce energy consumption in the process of manipulator movement.

Citation Download Citation

Ying Ye, Xuchong Zhang, Kezheng Sun, and Yangmin Ou "RNN based kinematic control scheme with a novel performance index", Proc. SPIE 12332, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2022), 123321E (6 September 2022); https://doi.org/10.1117/12.2652490

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available