A sensorless interaction forces estimator for bilateral teleoperation system based on online sparse Gaussian process regression. (January 2020)

• Record Type: Journal Article
• Authors: Dong, Ai; Du, Zhijiang; Yan, Zhiyuan
• Is Part Of: Mechanism and machine theory. Volume 143(2020)
• Publication Date: 2020-01
• Subjects: Gaussian process regression -- Interaction forces estimator -- Bilateral teleoperation -- Haptics -- Master-slave manipulator; Machine theory -- Periodicals; Machinery -- Periodicals; Machines -- Périodiques; Génie mécanique -- Périodiques; Machine theory; Machinery; Periodicals; 621.81
• DOI: 10.1016/j.mechmachtheory.2019.103620
• Languages: English
• ISSNs: 0094-114X

Abstract

Highlights: A novel sensorless interaction forces estimator is proposed. The proposed estimator does not require the use of force sensors. The proposed estimator is independent of the dynamic model of slave manipulator. The proposed estimator can estimate the interaction forces in real-time. the proposed estimator can obtain state-of-the-art estimation outcome. Abstract: This paper focuses on sensorless estimation of the interaction forces between the slave manipulator and its surrounding environment in bilateral teleoperation system. The proposed estimator is based on online sparse Gaussian process regression (OSGPR) and it does not need the use of commercially available force sensors. Therefore, the proposed estimator can overcome the shortcomings associated with the employment of force sensors. Through the adoption of machine learning technique, the proposed estimator can accurately estimate the interaction forces even when there are parametric uncertainties and unmodeled disturbances in the dynamic model of the slave manipulator. Meanwhile, online estimation of the interaction forces is realized through the utilization of sparse technique. Two case studies of the estimation of interaction forces are performed to validate the effectiveness and feasibility of the proposed estimator. Experimental results demonstrate that the proposed estimator outperforms several existing alternatives in terms of estimation accuracy.