Abstract
In this paper, a hybrid position/force tracking control scheme based on neural network observer is proposed for robotic systems with uncertain parameters and external disturbances. First, an observer based on neural network is designed to estimate joint velocities. Then, a neural network-based adaptive hybrid position/force controller is proposed based on the observed joint velocities. By using strict positive real method and Lyapunov stability theory, it is proved that all the signals of the closed-loop system are ultimately uniformly bounded. Finally, the simulation tests on a two-link manipulator are conducted. The simulation results show the feasibility and effectiveness of the control scheme.
Similar content being viewed by others
References
Raibert MH, Craig JJ (1981) Hybrid position/force control of manipulators. ASME J Dyn Syst Meas Control 103(2):126–133
Lozano R, Brogliato B (1992) Adaptive hybrid force-position control for redundant manipulators. IEEE Trans Autom Control 37(10):1501–1505
Kwan CM (1995) Hybrid force/position control for manipulators with motor dynamics using a sliding-adaptive approach. IEEE Trans Autom Control 40:963–968
Bassi E, Benzi F, Capisani LM, Cuppone D (2009) Hybrid position/force sliding mode control of a class of robotic manipulators. In: IEEE Conference on Decision & Control, pp 2966–2971
Chen ZH, Chen L (2011) Dynamics for dual-arm space robot with closed-chain and hybrid force and position control for grasped object based on sliding-mode compensation. Eng Mech 28(5):226–232
Peng J, Yang Z, Wang Y, Zhang F, Liu Y (2019) Robust adaptive motion/force control scheme for crawler-type mobile manipulator with nonholonomic constraint based on sliding mode control approach. ISA Trans 92:166–179
Peng J, Wang J, Wang Y (2011) Neural network based robust hybrid control for robotic system: an \(H_{\infty }\) approach. Nonlinear Dyn 65(4):421–431
Mohajerpoor R, Rezaei M, Talebi A et al (2012) A robust adaptive hybrid force/position control scheme of two planar manipulators handling an unknown object interacting with an environment. Proc Inst Mech Eng Part I J Syst Control Eng 226(4):509–522
Singh HP (2013) Stability analysis of robust adaptive hybrid position/force controller for robot manipulators using neural network with uncertainties. Neural Comput Appl 22(7–8):1745–1755
Zhou F, Li Y, Liu G (2017) Robust decentralized force/position fault-tolerant control for constrained reconfigurable manipulators without torque sensing. Nonlinear Dyn 89(3):955–969
Touati Y, Djouani K, Amirat Y (2004) Neuro-fuzzy based approach for hybrid force/position robot control. Integr Comput-Aided Eng 11(1):85–98
Canul RC, Garcia-Hernandez R, Rullan-Lara JL et al (2014) Decentralized adaptive fuzzy control applied to a robot manipulator. Adv Trends Soft Comput 314:123–135
Wen S, Yu H, Zhang B et al (2017) Fuzzy identification and delay compensation based on the force/position control scheme of the 5-DOF redundantly actuated parallel robot. Int J Fuzzy Syst 19(1):124–140
Peng J, Rickey D (2019) Adaptive fuzzy backstepping control for a class of uncertain nonlinear strict-feedback systems based on dynamic surface control approach. Expert Syst Appl 120:239–252
Karayiannidis Y, Rovithakis G, Doulgeri Z (2007) Force/position tracking for a robotic manipulator in compliant contact with a surface using neuro-adaptive control. Automatica 43(7):1281–1288
Peng J, Yang Z, Ma T (2019) Position/force tracking impedance control for robotic systems with uncertainties based on adaptive Jacobian and neural network. Complexity 2019:1–16
Kumar N, Panwar V, Sukavanam N, Sharma SP, Borm JH (2011) Neural network based hybrid force/position control for robot manipulators. Int J Precis Eng Manuf 12(3):419–426
Ghajar M-H, Keshmiri M, Bahrami J (2018) Neural-network-based robust hybrid force/position controller for a constrained robot manipulator with uncertainties. Trans Inst Meas Control 40(5):1625–1636
Rani K, Kumar N (2018) Design of intelligent hybrid force and position control of robot manipulator. Procedia Comput Sci 125:42–49
Mills JK, Goldenberg AA (1989) Force and position control of manipulators during constrained motion tasks. IEEE Trans Robot Autom 5(1):30–46
Yoshikawa T, Sudou A (1990) Dynamic hybrid position/force control of robot manipulators: on-line estimation of unknown constraint. IEEE Trans Robot Autom 2:1231–1236
Ravandi AK, Khanmirza E, Daneshjou K (2018) Hybrid force/position control of robotic arms manipulating in uncertain environment based on adaptive fuzzy sliding mode control. Appl Soft Comput 70:864–874
Yu W, Li XO (2006) PD control of robot with velocity estimation and uncertainties compensation. Int J Robot Autom 21(1):1–9
Su Y, Muller PC, Zheng C (2007) A simple nonlinear observer for a class of uncertain mechanical systems. IEEE Trans Autom Control 52(7):1340–1345
Goléa N, Goléa A, Barra K et al (2008) Observer-based adaptive control of robot manipulators: fuzzy systems approach. Appl Soft Comput 8(1):778–787
Peng J, Liu Y, Wang J (2014) Fuzzy adaptive output feedback control for robotic systems based on fuzzy adaptive observer. Nonlinear Dyn 78(2):789–801
Chaudhary H, Parashar A, Prasad R et al (2014) Velocity observer based fuzzy PD+I based hybrid force/position control of an industrial robot. In Engineering and computational sciences, pp 1–6
Bouakrif F (2017) Trajectory tracking control using velocity observer and disturbances observer for uncertain robot manipulators without tachometers. Meccanica 52(4–5):1–15
Yang Z, Peng J, Liu Y (2019) Adaptive neural network force tracking impedance control for uncertain robotic manipulator based on nonlinear velocity observer. Neurocomputing 331:263–280
Kim YH, Lewis FL, Abdallah CT (1997) A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems. Automatica 33(8):1539–1543
Sun F, Sun Z, Woo PY (2001) Neural network-based adaptive controller design of robotic manipulators with an observer. IEEE Trans Neural Networks 12(1):54–67
Abdollahi F, Talebi HA, Patel RV (2006) A stable neural network-based observer with application to flexible-joint manipulators. IEEE Trans Neural Networks 17(1):118–129
Tao G, Ioannou PA (1988) Strictly positive real matrices and the Lefschetz–Kalman–Yakubovich lemma. IEEE Trans Autom Control 33(12):1183–1185
Acknowledgements
The authors would like to acknowledge the funding received from the National Natural Science Foundation of China (61773351, 61603345), the Program for Science & Technology Innovation Talents in Universities of Henan Province (20HASTIT031), the Training Plan for University’s Young Backbone Teachers of Henan Province (2017GGJS004), the Natural Science Foundation of Henan Province (162300410260) and the China Scholarship Council (201907045008) to conduct this research investigation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there are no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A: Proof of Theorem 1
Considering the following Lyapunov function,
Taking the differentiation of Eq. (63) and substituting Eqs. (21) and (26), yields
According to Eq. (20), we can obtain,
Now, using the updating laws Eq. (27), the facts \(\dot{{\tilde{W}}}=-\dot{{\hat{W}}}\) and \(B_oP^{{\mathrm {T}}}{\tilde{x}}=C_o{\tilde{x}}={\tilde{x}}_1\), we can obtain,
According to inequality (25) and Eq. (28), we can obtain,
Therefore,
Substituting Eq. (68) into Eq. (64) yields,
This implies \(V_o>0\) and \({\dot{V}}_o \le 0\), the stability of the observer can be then ensured so that \({\tilde{x}}\) and \({\tilde{W}}_o\) are bounded.
Appendix B: Proof of Theorem 2
Considering the following Lyapunov function,
Taking the differentiation of Eq.(70) yields
Substituting Eqs. (54) and (56) into Eq. (71), and considering the fact \(\dot{{\tilde{W}}}_c=-\dot{{\hat{W}}}_c\), we can obtain,
According to property 2, we have,
Substituting Eqs. (55) and (57) into Eq. (73), we can obtain,
It can be concluded that the closed-loop system is asymptotically stable. Integrating Eq. (74) from time \(t=0\) to \(t=T\) yields,
Using Eq. (70), we can obtain,
According to inequality (75), we have,
This implies that \({\hat{s}}\) and \({\tilde{W}}_c\) are bounded. Since \(W_c\) is bounded, \({\hat{W}}_c\) is hence bounded.
Rights and permissions
About this article
Cite this article
Peng, J., Ding, S., Yang, Z. et al. Neural Network-Based Hybrid Position/Force Tracking Control for Robotic Systems Without Velocity Measurement. Neural Process Lett 51, 1125–1144 (2020). https://doi.org/10.1007/s11063-019-10138-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-019-10138-1