Title: End trajectory tracking control of flexible space manipulator based on improved RBF neural network

Authors: Bing Chen; Lei Wang; Junfeng Wu

Addresses: Faculty of Engineering, Huanghe Science and Technology University, Zhengzhou, 450063, China; Henan Engineering Research Center of Acoustic Meta-Structure, Huanghe Science and Technology University, Zhengzhou, 450063, China ' Faculty of Engineering, Huanghe Science and Technology University, Zhengzhou, 450063, China; Henan Engineering Research Center of Acoustic Meta-Structure, Huanghe Science and Technology University, Zhengzhou, 450063, China ' Faculty of Engineering, Huanghe Science and Technology University, Zhengzhou, 450063, China; Henan Engineering Research Center of Acoustic Meta-Structure, Huanghe Science and Technology University, Zhengzhou, 450063, China

Abstract: The end trajectory of a flexible space manipulator is susceptible to various interference factors during operation, resulting in significant deviations between the actual trajectory and the expected trajectory, which affects the accuracy of the model. A flexible space manipulator end trajectory tracking control method based on an improved RBF neural network is proposed. Analyse the problems with the end effector trajectory of flexible articulated robotic arms, improve the RBF neural network through weights and learning factors, construct a trajectory tracking control method, clarify the control step flow, adjust the joint information of the robotic arm in real-time, and ensure accurate tracking of the end effector trajectory. The experimental results show that the improved method has an average relative position error of 3.01 mm and a maximum error of 10.94 mm in the motion space. The experimental results show that the average relative position error of the improved method in motion space is 3.01 mm, and the maximum error is 10.94 mm. The proposed method maintains a response speed of ten seconds, which is significantly improved compared to traditional methods, and can achieve high-precision control of the end trajectory tracking effect. The main improvement is the weight and learning factor improvement of the RBF neural network, which enhances the tracking accuracy.

Keywords: flexible space; mechanical arm; end; trajectory; tracking control; improve RBF neural network.

DOI: 10.1504/IJIMS.2025.150845

International Journal of Internet Manufacturing and Services, 2025 Vol.11 No.4, pp.341 - 356

Received: 31 Dec 2024
Accepted: 28 Mar 2025
Published online: 24 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article