An Enhanced GRU Model With Application to Manipulator Trajectory Tracking

Zuyan Chen; Jared Walters; Gang Xiao; Shuai Li

doi:10.4108/airo.v1i.7

Authors

Zuyan Chen Swansea University
Jared Walters Swansea University
Gang Xiao Shenzhen In-cube Automation Co. Ltd., China
Shuai Li Swansea University

DOI:

https://doi.org/10.4108/airo.v1i.7

Keywords:

Trajectory tracking, gated recurrent unit (GRU), neural hidden state, gate unit, robot manipulators

Abstract

Service robots, e.g. massage robots, have attracted more and more attention in recent years and the most popular study within this field is trajectory tracking. Due to the actual demand for service robots, the solution of trajectory tracking requires fast convergence and high accuracy. In order to solve the above issues, this paper proposed an enhanced Gated recurrent unit (GRU) to deal with trajectory tracking tasks of robot manipulators. The main feature of enhanced GRU is utilizing cell states as well as various gate units to build a novel neural cell. Besides, the presented enhanced GRU resolves the problem of the general neural network model and large memory occupancy. Then the derivations about the computational process of cell state and mixed hidden state of the proposed model have been illustrated. Finally, three trajectory tracking applications, comparison, and visual simulation have verified feasibility as well as the superiority of the enhanced GRU model.

Downloads

References

[1] W. Si, G. Srivastava, Y. Zhang, L. Jiang, ”Green Internet of Things Application of a Medical Massage Robot With System Interruption,” IEEE Access, vol. 7, pp. 127066-127077, 2019.

[2] H. Wang, Y. Huang, S. Xiao, Y. Lin, Z. Jiang, ”Design of A New Parallel Metamorphic Robot for Chinese Medicine Massage,” Basic and Clinical Pharmacology and Toxicology, vol. 124, no. 3, pp. 39-40, Apr. 2019.

[3] Z. Pang, B. Zhang, J. Yu, Z. Sun, L. Gong, ”Design and Analysis of a Chinese Medicine Based Humanoid Robotic Arm Massage System,” Applied Science-Basel, vol. 9, no. 20, Oct. 2019.

[4] S. Kumar, K. Madhava, S. Srikanth, ”Planning nonholonomic stable trajectories on uneven terrain through non-linear time scaling,” Mechanism and Machine Theory, vol. 40, no. 8, pp. 1419-1440, Dec. 2016.

[5] O. Kayumov, ”Planning the Subminimum-Time Motion of a Robotic Manipulator Which Avoids Obstacles,” Journal of Computer and System International, vol. 55, no. 6, pp. 865-877, Nov. 2016.

[6] K. Dumlu, ”Trajectory Tracking Control for a 3-DOF Parallel Manipulator Using Fractional-Order Control,” IEEE Trans. Ind. Electron., vol. 61, no. 7, pp. 3417–3426, Aug. 2013.

[7] M. Galicki, ”Finite-time trajectory tracking control in a task space of robotic manipulators,” Automatica, vol. 67, pp. 165–170, May. 2016.

[8] A. Duka, ”Neural network based inverse kinematics solution for trajectory tracking of a robotic arm,” Procedia Technology, vol. 12, pp. 20–27, Dec. 2013.

[9] H. Peng, F. Li, J. Liu, Z. Ju, ”A Symplectic Instantaneous Optimal Control for Robot Trajectory Tracking With Differential-Algebraic Equation Models ,” IEEE Trans. Ind. Electron, vol. 67, no. 5, pp. 3819-3829, May. 2020.

[10] L. Truong, S. Huang, V. Yen, P. Cuong, ”Adaptive Trajectory Neural Network Tracking Control for Industrial Robot Manipulators with Deadzone Robust Compensator,” International Journal of Control Automation and System, [online], Doi: 10.1007/s12555-019-0513-7.

[11] I. Komnik, M. Peters, J. Funken, S. David, S. Weiss, W. Potthast, ”Non-Sagittal Knee Joint Kinematics and Kinetics during Gait on Level and Sloped Grounds with Unicompartmental and Total Knee Arthroplasty Patients,” PLos One, vol. 11, no. 12, Dec. 2016.

[12] Y. Zhao, S. Hu, Y. Yang, ”Inverse kinematics of asymmetric octahedral variable geometry truss manipulator with obstacle avoidance through inexact interior point optimization,” International Journal of Advanced Robotic System, vol. 15, no. 6, Dec. 2018.

[13] J. Kim, J. Lee, Y. Choi, ”PiROB: Vision-based pipeclimbing robot for spray-pipe inspection in nuclear plants,” International Journal of Advanced Robotic System, vol. 15, no. 6, Dec. 2018.

[14] Z. Zake, F. Chaumette, N. Pedemonte, S. Caro, ”Robust 21/2D Visual Servoing of A Cable-Driven Parallel Robot Thanks to Trajectory Tracking,” IEEE Robotics and Automation Letter, vol. 5, no. 2, pp. 660-667, Apr. 2020.

[15] M. wang, Z. Lu, H. Li, W. Jiang, Q. Liu, ”genCNN: A Convolutional Architecture for Word Sequence Prediction,” ACL 2015, arXiv: 1503.05034.

[16] S. Hochreiter and J. Shmidhuber, ”Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735-1780, Nov. 1997.

[17] M. Gao, G. Shi, S. Li, ”Online Prediction of Ship Behavior with Automatic Identification System Sensor Data Using Bidirectional Long Short-Term Memory Recurrent Neural Network,” Sensors, vol. 18, no. 12, Dec. 2018.

[18] P. Shrey, K. Thenkurussi, ”IART: Learning From Demonstration for Assisted Robotic Therapy Using LSTM,” IEEE Robotics and Automation Letter, vol. 5, no. 2, pp. 477-484, Apr. 2020.

[19] D. Robert, A. Narges, M. Anand, W. Madeleine, L. GI, L. MR, V. SS, H. GD, ”Segmenting and classifying activities in robot-assisted surgery with recurrent neural networks,” International Journal of Computer assisted Radiology and Surgery, vol. 14, no. 11, pp. 2005-2020, Nov. 2019.

[20] T. Shibahara, K. Yamanishi, et al. ”Event De-NoisingConvolutional Neural Network for Detecting Malicious URL Sequences from Proxy Logs,” IEICE Trans. Fundenmentals of Electronic Communication and Computer Science, vol. E101A, no. 12, pp. 2149-2161, Dec. 2018.

[21] Y. Li, S. Li, D. Caballero, M. Miyasaka, A. Lewis and B. Hannaford, "Improving control precision and motion adaptiveness for surgical robot with recurrent neural network," 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, 2017, pp. 3538-3543.

[22] S. Li, H. Wang, M. Rafique, ”A Novel Recurrent Neural Network for Manipulator Control Improved Noise Tolerance,” IEEE Trans. Neural Netw. Syst., vol.29, no. 5, pp.1908-1918, Apr. 2017.

[23] J. Wu, J. She, Y. Wang, C. Su, ”Position and Posture Control of Planar Four-Link Underactuated Manipulator Based on Neural Network Model,” IEEE Trans. Ind. Electron., vol.67, no. 6, pp. 4721-4728, Jun. 2020.

[24] S. Li, Y. Zhang, L. Jin, ”Kinematic Control of Redundant Manipulators Using Neural Networks,” IEEE Trans.Neural Network and Learning Systems, vol. 28, no. 10, pp. 2243-2254, Oct. 2017.

[25] Z. Zhang, L. Zheng, Z. Chen, L. Kong, H. Reza, ”Mutual-Collision-Avoidance Scheme Synthesized by Neural Networks for Dual Redundant Robot Manipulators Executing Cooperative Tasks,” IEEE Trans. Neural Network and Learning Systems, Apr. 2020, Doi: 10.1109/TNNLS.2020.2980038.

[26] H. Jiang, G. Xu, W. Zeng, F. Gao, ”Design and kinematic modeling of a passively-actively transformable mobile robot,” Mechanism and Machine Theory, vol. 142, Dec. 2019.

[27] Y. Chen, X. Luo, B. Han, Y. Jia, G. Liang, X. Wang, ”A General Approach Based on Newton’s Method and Cyclic Coordinate Descent Method for Solving the Inverse Kinematics,” Applied Science-Basel, vol. 9, no. 24, Dec. 2019.

[28] Y. Wan, Z. Han, J. Zhong, G. Chen, ”Pattern recognition and bionic manipulator driving by surface electromyography signals using convolutional neural network,” International Journal of Advanced Robotic Systems, vol. 15, no. 5, Oct. 2018.

[29] C. Yang, F. Yao, M. Zhang, ”Adaptive Backstepping Terminal Sliding Mode Control Method Based on Recurrent Neural Networks for Autonomous Underwater Vehicle,” Chinese Journal of Mechanical Engineering, vol. 31, no. 1, Dec. 2018.

[30] M. Er, Y. Zhang, N. Wang, M. Pratama, ”Attention pooling-based convolutional neural network for sentence modelling,” Information Science, vol. 373, pp. 388-403, Dec. 2016.

[31] X. Liu, Z. Pan, H. Yang, X. Zhou, W. Bai, X. Niu, ”An Adaptive Moment estimation method for online AUC maximization,” PLos One, vol. 14, no. 4, Apr. 2019.

[32] E. Tsironi, P. Barros, C. Weber, S. Wermter, ”An analysis of Convolutional Long Short-Term Memory Recurrent Neural Networks for gesture recognition,” Neurocomputing, vol. 268, pp. 76-86, Dec. 2017.

[33] R. Zhao, D. Wang, R. Yan, K. Mao, F. Shen, J. Wang, ”Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks,” IEEE Trans. Ind. Electron., vol. 65, no. 2, pp. 1539-1548, Feb. 2018.

[34] S. Li, J. He, U. Rafique, and Y. Li, ”Distributed Recurrent Neural Networks for Cooperative Control of Manipulators: A Game-Theoretic Perspective”, IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(2): 415 - 426.

[35] S. Li, Y. Zhang and L. Jin, ”Kinematic Control of Redundant Manipulators Using Neural Networks”, IEEE Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2243-2254.

[36] S. Li, H. Wang and U. Rafique, ”A Novel Recurrent Neural Network for Manipulator Control with Improved Noise Tolerance”, IEEE Transactions on Neural Networks and Learning Systems, 2018, 29.5: 1908-1918.

[37] S. Li, Y. Guo, ”Distributed source seeking by cooperative robots: All-to-all and limited communications”, ICRA, 2012, DOI: 10.1109/ICRA.2012.6224713

[38] X. Jiang, S. Li, ”BAS: Beetle Antennae Search Algorithm for Optimization Problems”, International Journal of Robotics and Control, vol.1, no.1, 2018

[39] AH. Khan, S. Li, D. Chen, ”Tracking control of redundant mobile manipulator: An RNN based metaheuristic approach”, Neurocomputing, 2020, 400(4), 272-284.

[40] Z. Li, S. Li, ”Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective”, IEEE Transactions on Neural Networks and Learning Systems, 2021, 14.9: 1-15.

[41] D. Wu, Y. He, MC. Zhou, ”A latent factor analysis-based approach to online sparse streaming feature selection”, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 4.8: 1-15.

[42] M. Shang, Y. Yuan, X. Luo, ”An α-β -Divergence-Generalized Recommender for Highly Accurate Predictions of Missing User Preferences”, IEEE Transactions on Cybernetics, 2021, 18.1: 1-13.

[43] Z. Li, S. Li, X. Luo, ”An Overview of Calibration Technology of Industrial Robots”, IEEE/CAA Journal of Automatica Sinica, 2021, Volume: 8, Issue: 1, Pages: 23 -36.