Abstract
This paper proposes a novel robust neural-adaptive control method for controlling underdamped non-minimum phase system. Without robust modifications to the training rule, adaptive approximators experience weight weight drift which typically causes control chatter and excitation of the natural frequency. Popular robust modifications, like e-modification and deadzone, significantly reduce performance. In the proposed method, an alternate neural network, providing approximately the same output, guides the training. The proposed algorithm trains the alternate weights in a manner so as to avoid the weight drift caused by underdamped vibrations. Experimental results show dramatic improvement in performance over e-modification when controlling a flexible-joint robot.
Similar content being viewed by others
References
Abdelhameed M, Pinspon U, Cetinkunt S (2002) Adaptive learning algorithm for CMAC. Mechatronics 12: 859–873
Albus JS (1975) A new approach to manipulator control: the cerebellar model articulation controller (CMAC). J Dyn Syst Meas Control 97: 220–227
Albus J (1975) Data storage in the cerebellar model articulation controller (CMAC). J Dyn Syst Meas Control 97: 228–233
Albus J (1981) Brains, behaviour, and robotics. BYTE Publications Inc., Peterborough
Bridges M, Dawson D, Abdallah C (1995) Control of rigid-link, flexible-joint robots—a survey of backstepping methods. J Robot Syst 12: 199–216
Brogliato B, Ortega R, Lozano R (1995) Global tracking controllers for flexible-joint manipulators: a comparative study. Automatica 31: 941–956
Chatlatanagulchai W, Meckl P (2005) Intelligent control of a two-link flexible-joint robot, using backstepping, neural networks, and direct method. In: IEEE/RSJ internetional conference on intelligent robots and systems. Edmonton, Canada, pp 1594–1599
Chen F, Chang C (1996) Practical stability issues in CMAC neural network control systems. IEEE Trans Control Syst Technol 4: 86–91
Chen F, Chang C (2004) An alternative CMAC trained with genetic algorithms to solve and instable control process. Proceedings of IEEE Conference on Robotics and Biometrics, pp 950–954
Dwivedy S, Eberhard P (2006) Dynamic analysis of flexible manipulators, a literature review. Mech Mach Theory 41: 749–777
French M, Szepesvari C, Rogers E (2000) Uncertainty, performance, and model dependency in approximateadaptive nonlinear control. IEEE Trans Autom Control 45(2): 353–358
Gu W, Lei J, Lei Y (2005) Single input rbf neural robust controller design for a class of nonlinear system with linear input unmodeled dynamics and unknown control function matrices. In: Proceedings of IEEE international conference on machine learning and cybernetics. Guangzhou, China, pp 4662–4666
Hwang C (2004) A novel Takagi-Sugeno-based robust adaptive fuzzy sliding-mode controller. IEEE Trans Fuzzy Syst 12: 676–687
Ioannuou P, Kokotovic P (1984) Instability analysis and improvement of robustness of adaptive control. Automatica 20(5): 583–594
Jiang Z, Wang S (2003) A general learning scheme for CMAC-based controller. Neural Process Lett 18: 125–138
Kim E (2004) Output feedback tracking control of robot manipulators with model uncertainty via adaptive fuzzy logic. IEEE Trans Fuzzy Syst 12(3): 368–378
Kim N, Calise A, Hovakimyan N (2004) Several extensions in methods for adaptive output feedback control. In: Proceedings of American control conference, Boston, pp 2421–2426
Kim Y, Lewis F (2000) Optimal design of CMAC neural-network controller for robot manipulators. IEEE Trans Syst Man Cybern C 30(1): 22–30
Kraft L, Pallotta JJ (2000) Real-time vibration control using CMAC neural networks with weight smoothing. In: Proceedings of IEEE American control conference, Chicago, pp 3939–3943
Kuljaca O, Swamy N, Lewis F, Kwan C (2003) Design and implentation of industrial neural network controller using backstepping. IEEE Trans Ind Electron 50: 193–201
Kwan C, Lewis F (2000) Robust backstepping control of nonlinear systems using neural networks. IEEE Trans Syst Man Cybern A 30: 753–766
Lee T, Kumarawadu S, Perng J (2005) Direct-adaptive neurocontrol of robots with unknown nonlieararities and velocity feedback. In: Proceedings of IEEE conference on systems man cybernetics, pp 2073–2077
Lee Y, Zak SH (2004) Uniformly ultimately bounded fuzzy adaptive tracking controllers for uncertain systems. IEEE Trans Fuzzy Syst 12: 797–811
Li Y, Qiang S, Kaynak O (2004) Robust and adaptive backstepping control for nonlinear systems using RBF neural networks. IEEE Trans Neural Netw 15(3): 693–701
Macnab C (2006) Robust associative-memory adaptive control in the presence of persistent oscillations. Neural Inf Process Lett Rev 10: 277–287
Macnab C (2009) Stable neural control of a flexible-joint manipulator subjected to sinusoidal disturbance. In: International conference on autonomous robots and agents. Wellington, New Zealand, pp 698–703
Macnab C, D’Eleuterio G (1998) Stable, on-line learning using CMACs for neuroadaptive tracking control of flexible-joint manipulators. In: Proceedings of IEEE international conference on robotics and automation. Leuven, Belgium, pp 511–517
Nakanishi J, Schaal, S (2004) Feedback error learning and nonlinear adaptive control. Neural Netw 17: 1453–1465
Nicol C, Macnab C, Ramirez-Serrano A (2008) Robust neural network control of a quadrotor helicopter. In: IEEE Proceedings of Canadian conference on electrical and computer engineering. Niagara Falls, Canada, pp 1233–1238
Ozgoli S, Taghirad HD (2006) A survey on the control of flexible joint robots. Asian J Control 8(4): 1–15
Sanner R, Slotine J (1995) Stable adaptive control of robot manipulators using neural networks. Neural Comput 7(4): 753–790
Slotine J, Li W (1987) On the adaptive control of robot manipulators. Int J Robot Res 6(3): 49–59
Spong M, Vidyasagar M (1989) Robot dynamics and control. Wiley, New York
Spooner J, Passino K (1996) Stable adaptive control using fuzzy systems and neural networks. IEEE Trans Fuzzy Syst 4: 339–359
Tomei P, Nicosia S, Ficola A (1986) An approach to the adaptive control of elastic joints robots. Proceedings of IEEE international conference of robotics and Automation, pp 552–558
Wang C, Hill D (2004) Learning from direct adaptive neural control. In: Proceedings of Asian control conference, pp 674–681
Wang D, Huang J (2002) Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form. Automatica 38: 1365–1372
Yang Y, Feng G, Ren J (2004) A combined backstepping and small-gain approach to robust adaptive fuzzy control for strict-feedback nonlinear systems. IEEE Trans Syst Man Cybern A 34: 406–419
Yeh M (2007) Single-input CMAC control system. Neurocomputing 70: 2638–2644
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
An n-link flexible joint robot with large gear ratios has model
where
- \({\bf x}_1\) :
-
are link angles
- \({\bf x}_2\) :
-
are link angular velocities
- \({\bf x}_3\) :
-
are rotor angles
- \({\bf x}_4\) :
-
are rotor angular velocities
- \({\bf M}({\bf x}_1) \in {\mathcal{R}}^{n \times n}\) :
-
is the link inertia matrix
- \({\bf K} \in {\mathcal{R}}^{n \times n}\) :
-
is a diagonal matrix of (positive) spring constants
- \({\bf J} \in {\mathcal{R}}^{n \times n}\) :
-
is the rotor inertia matrix (after gear reduction)
- \({\bf u} \in {\mathcal{R}}^{n}\) :
-
is control torque
- \( {\bf F}_1, {\bf F}_2 \in {\mathcal{R}}^n\) :
-
contain linear and non-linear terms.
Given a desired trajectory \(\varvec{\theta}_d,\dot{\varvec{\theta}}_d,\ddot{\varvec{\theta}}_d\) for the link coordinates, then the filtered error tracking error is defined
To use backstepping, the desired rotor states are considered to be virtual controls. The first virtual control \({\bf v}_1\) contains the desired rotor positions, and the second, \({\bf v}_2\), contains the desired rotor velocities. The virtual control errors are then defined as
The (virtual) controls using CMACs are chosen
where each \({\bf G}_i\) is a positive-definite matrix of control gains. The closed-loop error dynamics can be written
where
Since (46) has the same basic form as (5) the stability proof of the new weight update method is still valid.
Rights and permissions
About this article
Cite this article
Macnab, C.J.B. Neural-adaptive control using alternate weights. Neural Comput & Applic 20, 211–221 (2011). https://doi.org/10.1007/s00521-010-0366-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-010-0366-8