SCIENCE CHINA Information Sciences, Volume 61, Issue 11: 112201(2018) https://doi.org/10.1007/s11432-017-9363-y

Cooperative deterministic learning control for a group of homogeneous nonlinear uncertain robot manipulators

More info
  • ReceivedOct 28, 2017
  • AcceptedJan 31, 2018
  • PublishedMay 23, 2018


This paper addresses the learning control problem for a group of robotmanipulators with homogeneous nonlinear uncertaindynamics, where all the robots have an identical system structure but the reference signals to be tracked differ. The control objective is twofold: to track on reference trajectories andto learn/identify uncertain dynamics. For this purpose, deterministic learning theoryis combined with consensus theory to find a common neural network(NN) approximation of the nonlinear uncertain dynamics for a multi-robotsystem. Specifically, we first present a control scheme called cooperativedeterministic learning using adaptive NNs to enable the robotic agentsto track their respective reference trajectories on one hand andto exchange their estimated NN weights online through networked communicationon the other. As a result, a consensus about one common NN approximationfor the nonlinear uncertain dynamics is achieved for all the agents.Thus, the trained distributed NNs have a better generalization capabilitythan those obtained by existing techniques. By virtue of the convergenceof partial NN weights to their ideal values under the proposed scheme,the cooperatively learned knowledge can be stored/represented by NNswith constant/converged weights, so that it can be used to improvethe tracking control performance without re-adaptation. Numericalsimulations of a team of two-degree-of-freedom robot manipulatorswere conducted to demonstrate the effectiveness of the proposedapproach.


[1] Yuan C, Licht S, He H. Formation learning control of multiple autonomous underwater vehicles with heterogeneous nonlinear uncertain dynamics. IEEE Trans Cybern, 2017, doi: 10.1109/TCYB.2017.2752458 CrossRef PubMed Google Scholar

[2] Yang C, Ganesh G, Haddadin S. Human-like adaptation of force and impedance in stable and unstable interactions. IEEE Trans Robot, 2011, 27: 918-930 CrossRef Google Scholar

[3] Chung S J, Slotine J J E. Cooperative robot control and concurrent synchronization of lagrangian systems. IEEE Trans Robot, 2009, 25: 686-700 CrossRef Google Scholar

[4] Li Z J, Tao P Y, Ge S S. Robust adaptive control of cooperating mobile manipulators with relative motion.. IEEE Trans Syst Man Cybern B, 2009, 39: 103-116 CrossRef PubMed Google Scholar

[5] Huang J, Wen C, Wang W. Adaptive finite-time consensus control of a group of uncertain nonlinear mechanical systems. Automatica, 2015, 51: 292-301 CrossRef Google Scholar

[6] Liu Y J, Lu S, Li D. Adaptive Controller Design-Based ABLF for a Class of Nonlinear Time-Varying State Constraint Systems. IEEE Trans Syst Man Cybern Syst, 2017, 47: 1546-1553 CrossRef Google Scholar

[7] Liu Y J, Tong S. Barrier Lyapunov functions for Nussbaum gain adaptive control of full state constrained nonlinear systems. Automatica, 2017, 76: 143-152 CrossRef Google Scholar

[8] Li D P, Li D J, Liu Y J. Approximation-Based Adaptive Neural Tracking Control of Nonlinear MIMO Unknown Time-Varying Delay Systems With Full State Constraints.. IEEE Trans Cybern, 2017, 47: 3100-3109 CrossRef PubMed Google Scholar

[9] Liu L, Wang Z, Zhang H. Adaptive fault-tolerant tracking control for MIMO discrete-time systems via reinforcement learning algorithm with less learning parameters. IEEE Trans Automat Sci Eng, 2017, 14: 299-313 CrossRef Google Scholar

[10] Zeinali M, Notash L. Adaptive sliding mode control with uncertainty estimator for robot manipulators. Mech Mach Theor, 2010, 45: 80-90 CrossRef Google Scholar

[11] He W, Chen Y, Zhao Y. Adaptive neural network control of an uncertain robot with full-state constraints. IEEE Trans Cybern, 2015, 46: 620--629. Google Scholar

[12] Li Z, Deng J, Lu R. Trajectory-tracking control of mobile robot systems incorporating neural-dynamic optimized model predictive approach. IEEE Trans Syst Man Cybern Syst, 2016, 46: 740-749 CrossRef Google Scholar

[13] Liang X, Wang H, Liu Y H. Adaptive task-space cooperative tracking control of networked robotic manipulators without task-space velocity measurements. IEEE Trans Cybern, 2016, 46: 2386-2398 CrossRef PubMed Google Scholar

[14] Yuan C, Abdelatti M, Dong X, et al. Cooperative deterministic learning control of multi-robot manipulators. In: Proceedings of Chinese Control Conference, Wuhan, 2018. accepted. Google Scholar

[15] Xiao H, Li Z, Philip Chen C L. Formation control of leader-follower mobile robots' systems using model predictive control based on neural-dynamic optimization. IEEE Trans Ind Electron, 2016, 63: 5752-5762 CrossRef Google Scholar

[16] Li Z, Xia Y, Wang D. Neural network-based control of networked trilateral teleoperation with geometrically unknown constraints. IEEE Trans Cybern, 2016, 46: 1051-1064 CrossRef PubMed Google Scholar

[17] Li Z, Yang C, Su C Y. Decentralized fuzzy control of multiple cooperating robotic manipulators with impedance interaction. IEEE Trans Fuzzy Syst, 2015, 23: 1044-1056 CrossRef Google Scholar

[18] Wang C, Hill D J. Deterministic Learning Theory for Identification, Recognition and Control. Boca Raton: CRC Press, 2009. Google Scholar

[19] Yuan C, Wang C. Persistency of excitation and performance of deterministic learning. Syst Control Lett, 2011, 60: 952-959 CrossRef Google Scholar

[20] Yuan C, Wang C. Performance of deterministic learning in noisy environments. Neurocomputing, 2012, 78: 72-82 CrossRef Google Scholar

[21] Yuan C Z, Wang C. Design and performance analysis of deterministic learning of sampled-data nonlinear systems. Sci China Inf Sci, 2014, 57: 032201. Google Scholar

[22] Xu B, Yang C G, Shi Z K. Reinforcement learning output feedback NN control using deterministic learning technique.. IEEE Trans Neural Netw Learning Syst, 2014, 25: 635-641 CrossRef PubMed Google Scholar

[23] Cong Wang , Hill D J. Deterministic learning and rapid dynamical pattern recognition.. IEEE Trans Neural Netw, 2007, 18: 617-630 CrossRef PubMed Google Scholar

[24] Chen W, Hua S, Zhang H. Consensus-based distributed cooperative learning from closed-loop neural control systems. IEEE Trans Neural Netw Learn Syst, 2015, 2: 331--345. Google Scholar

[25] Ren W, Beard R W, Atkins E M. Information consensus in multivehicle cooperative control. IEEE Control Syst Mag, 2007, 27: 71-82 CrossRef Google Scholar

[26] Ni W, Cheng D. Leader-following consensus of multi-agent systems under fixed and switching topologies. Syst Control Lett, 2010, 59: 209-217 CrossRef Google Scholar

[27] Wang C, Hill D J. Learning from neural control. IEEE Trans Neural Netw, 2006, 17: 130-146 CrossRef PubMed Google Scholar

[28] Shilnikov L P, Shilnikov A L, Turaev D V, et al. Methods of Qualitative Theory in Nonlinear Dynamics. Singapore: World Scientific, 2001. Google Scholar

[29] Olfati-Saber R, Fax J A, Murray R M. Consensus and cooperation in networked multi-agent systems. Proc IEEE, 2007, 95: 215-233 CrossRef Google Scholar

[30] Dai S L, Wang C, Luo F. Identification and learning control of ocean surface ship using neural networks. IEEE Trans Ind Inf, 2012, 8: 801-810 CrossRef Google Scholar

[31] Yuan C, He H, Wang C. Cooperative deterministic learning-based formation control for a group of nonlinear uncertain mechanical systems. IEEE Trans Ind Inf, 2018, doi: 10.1109/TII.2018.2792455 CrossRef Google Scholar

[32] Jadbabaie A, Jie A L, Morse A S. Coordination of groups of mobile autonomous agents using nearest neighbor rules. IEEE Trans Automat Contr, 2003, 48: 988-1001 CrossRef Google Scholar

[33] Vicsek T, Czirók A, Ben-Jacob E. Novel type of phase transition in a system of self-driven particles. Phys Rev Lett, 1995, 75: 1226-1229 CrossRef PubMed ADS Google Scholar

[34] Khalil H. Nonlinear Systems. Upper Saddle River: Prentice-Hall, 2002. Google Scholar

[35] Swaroop D, Hedrick J K, Yip P P. Dynamic surface control for a class of nonlinear systems. IEEE Trans Automat Contr, 2000, 45: 1893-1899 CrossRef Google Scholar

[36] Xu B, Shi Z, Yang C. Composite neural dynamic surface control of a class of uncertain nonlinear systems in strict-feedback form. IEEE Trans Cybern, 2014, 44: 2626-2634 CrossRef PubMed Google Scholar

  • Table 1   Parameters of the robot
    Parameter Value
    $m_{1}$ $({\rm~kg})$ $0.8$
    $m_{2}$ $({\rm~kg})$ $2.3$
    $l_{1}$ $({\rm~m})$ $1$
    $l_{2}$ $({\rm~m})$ $1$
    $I_{1}\times10^{-3}$ $({\rm~kg\cdot~m}^{2})$ $61.25$
    $I_{2}\times10^{-3}$ $({\rm~kg\cdot~m}^{2})$ $20.42$

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1       京公网安备11010102003388号