TY - GEN
T1 - Adaptive teleoperation control method based on RBF-Neural Networks and performance analysis
AU - Cheng, Ruizhou
AU - Huang, Panfeng
AU - Lu, Zhenyu
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - This work presents an adaptive teleoperation control method based on RBF-Neural Networks. First, the model of the teleoperation system with two slave robots is built. Then the controllers of the slaves and masters are designed separately. For the slave side, the dynamic uncertainties are considered as the main factor to influence the system stability, which is estimated by the RBF-Neural Networks (RBF-NNs). The structure parameters of the masters are known before the operation. Furthermore, we discuss the system stable conditions and position tracking effect of the slaves to the maters' motions. The proofs reveal that the system will converge to the stable states based on the assumptions that the estimating errors are smaller than a threshold value. The final tracking errors are corresponding with bounding values of the estimating errors of RBF-NNs method. Finally, a simulation is taken to certify the effectiveness of proposed method and the main conclusions.
AB - This work presents an adaptive teleoperation control method based on RBF-Neural Networks. First, the model of the teleoperation system with two slave robots is built. Then the controllers of the slaves and masters are designed separately. For the slave side, the dynamic uncertainties are considered as the main factor to influence the system stability, which is estimated by the RBF-Neural Networks (RBF-NNs). The structure parameters of the masters are known before the operation. Furthermore, we discuss the system stable conditions and position tracking effect of the slaves to the maters' motions. The proofs reveal that the system will converge to the stable states based on the assumptions that the estimating errors are smaller than a threshold value. The final tracking errors are corresponding with bounding values of the estimating errors of RBF-NNs method. Finally, a simulation is taken to certify the effectiveness of proposed method and the main conclusions.
UR - http://www.scopus.com/inward/record.url?scp=85050614653&partnerID=8YFLogxK
U2 - 10.1109/RCAR.2017.8311911
DO - 10.1109/RCAR.2017.8311911
M3 - 会议稿件
AN - SCOPUS:85050614653
T3 - 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
SP - 493
EP - 498
BT - 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
Y2 - 14 July 2017 through 18 July 2017
ER -