Paper Info
Title
Composite Learning Robot Control with Friction Compensation: A Neural Network-Based Approach
Abstract
Friction is one of the significant obstacles that hinders high-performance robot tracking control because accurate friction modeling and effective compensation are challenging issues. To address this problem, in this paper, we propose a modified neural network (NN) structure with additional jump approximation activation functions to model the inherent discontinuous friction in robotic systems, this structure allows us to improve the NN approximation accuracy without using too many NN nodes. The modeling accuracy is theoretically guaranteed by a composite learning technique, it explores both online historical data and instantaneous data to achieve NN weight convergence under a much weaker interval-excitation condition than the stringent persistent-excitation condition. Furthermore, a partitioned NN technique is used to handle a problem caused by variable substitution when formulating the prediction error for composite learning. This technique also helps us to alleviate the requirements regarding the inertial matrix inversion and joint acceleration signals. The practical exponential stability of the closed-loop system is proved under the more realizable interval-excitation condition. Experimental results demonstrate the effectiveness and superiority of the proposed approach.
Year
DOI
Venue
2019
10.1109/tie.2018.2886763
IEEE Transactions on Industrial Electronics
Keywords
Field
DocType
Artificial neural networks,Friction,Service robots,Convergence,Standards
Convergence (routing),Robot control,Matrix (mathematics),Control theory,Exponential stability,Acceleration,Engineering,Artificial neural network,Robot,Jump
Journal
Volume
Issue
ISSN
66
10
0278-0046
Citations 
PageRank 
References 
6
0.41
0
Authors
3
Name
Order
Citations
PageRank
Kai Guo161.43
Yongping Pan2504.64
Haoyong Yu362174.47