Abstract
In recent technological advancements, designing of exoskeleton have gained attraction from various scientists and researchers across the world. Exoskeletons are assistive devices which are used by the subjects with limb impairments. Various trajectory tracking control schemes have been developed in the past, however there are several challenges like human machine interaction, external disturbances and model uncertainties present that should be handled in the efficient designing of a controller. This paper deals with the development of 2-link lower limb extremity manipulator for rehabilitation purposes in bio-medical engineering. A novel control strategy is proposed to track the desired trajectory for assistive devices using the robust adaptive sliding mode controller coupled with Radial Basis Function (RBF) neural network and fuzzy techniques for function approximation. The simulations are carried out on a musculoskeletal model Gait2354 which can be scaled according to the physical dimensions of the experimental subject developed in OpenSim software. The controller designed is robust in terms of uncertainties and disturbances present in the system and reduces chattering problems. In addition, Minimum Learning Parameter is also incorporated in the system which reduces the number of parameters to only one, thereby reducing the computational cost and enhancing the real time performance of the system. For validation of the proposed model, Matlab Simulink environment is used. The different performance index parameters used in comparative analysis are Integral Absolute Error (IAE), Integral Square Error (ISE), Integral Time Absolute Error (ITAE) and Integral Time Square Error (ITSE). The simulation results show that SMC-RBF network has better performance and tracking rate as compared to other controllers implemented. The results obtained were also compared with the existing method to prove their effectiveness. The simulation results obtained ensures to provide effective and comfortable rehabilitation services for lower limb extremity in the future.
Similar content being viewed by others
References
Vélez-Guerrero MA, Callejas-Cuervo M, Mazzoleni S (2021) Artificial intelligence-based wearable robotic exoskeletons for upper limb rehabilitation: a review. Sensors 21(6):2146
Liang X, Wang H, Zhang Y (2022) Adaptive nonsingular terminal sliding mode control for rehabilitation robots. Comput Electr Eng 99:107718
Baud R, Manzoori AR, Ijspeert A, Bouri M (2021) Review of control strategies for lower-limb exoskeletons to assist gait. J NeuroEng Rehabil 18(1):1–34
Wu AR, Dzeladini F, Brug TJ, Tamburella F, Tagliamonte NL, Van Asseldonk EH, Van Der Kooij H, Ijspeert AJ (2017) An adaptive neuromuscular controller for assistive lower-limb exoskeletons: a preliminary study on subjects with spinal cord injury. Front Neurorobot 11:30
Chrif F, Nef T, Lungarella M, Dravid R, Hunt KJ (2017) Control design for a lower-limb paediatric therapy device using linear motor technology. Biomed Signal Process Control 38:119–127
Zhou L, Chen W, Bai S, Wang J, Zhao Z, Zhao X, Yu X (2022) Lower limb exoskeleton parasitic force modeling and minimizing with an adaptive trajectory controller. Mech Mach Theory 170:104731
Wang Y, Liu Z, Feng Z (2022) Design of a control framework for lower limb exoskeleton rehabilitation robot based on predictive assessment. Clin Biomech 95:105660
Chen G, Qi P, Guo Z, Yu H (2016) Gait-event-based synchronization method for gait rehabilitation robots via a bioinspired adaptive oscillator. IEEE Trans Biomed Eng 64(6):1345–1356
Hidayah R, Bishop L, Jin X, Chamarthy S, Stein J, Agrawal SK (2020) Gait adaptation using a cable-driven active leg exoskeleton (C-Alex) with post-stroke participants. IEEE Trans Neural Syst Rehabil Eng 28(9):1984–1993
Yu J, Zhang S, Wang A, Li W, Song L (2021) Musculoskeletal modeling and humanoid control of robots based on human gait data. PeerJ Comput Sci 7:e657
Cardona M, Cena CEG (2019) Biomechanical analysis of the lower limb: a full-body musculoskeletal model for muscle-driven simulation. IEEE Access 7:92709–92723
Sabah N, Hameed E, AL-Huseiny MS (2022) Design of modified adaptive PID controller for lower limb rehabilitation robot based on grey wolf optimization algorithm. Webology 19(1)
Kong D, Wang W, Guo D, Shi Y (2022) RBF sliding mode control method for an upper limb rehabilitation exoskeleton based on intent recognition. Appl Sci 12(10):4993
Raheema MN, Kadhim DA, Hussein JS (2021) Design an intelligent hybrid position/force control for above knee prosthesis based on adaptive neuro-fuzzy inference system. Indones J Electr Eng Comput Sci 23:675–685
Amer AF, Sallam EA, Elawady WM (2011) Adaptive fuzzy sliding mode control using supervisory fuzzy control for 3 dof planar robot manipulators. Appl Soft Comput 11(8):4943–4953
Zhang Y, Liu Y, Liu L (2020) Minimal learning parameters-based adaptive neural control for vehicle active suspensions with input saturation. Neurocomputing 396:153–161
Guan W, Zhou L, Cao Y (2021) Joint motion control for lower limb rehabilitation based on iterative learning control (ILC) algorithm. Complexity 2021
Zhang X, Ma H, Luo M, Liu X (2020) Adaptive sliding mode control with information concentration estimator for a robot arm. Int J Syst Sci 51(2):217–228
Khamar M, Edrisi M, Forghany S (2022) Designing a robust controller for a lower limb exoskeleton to treat an individual with crouch gait pattern in the presence of actuator saturation. ISA Trans 126:513–532
Gordon DF, McGreavy C, Christou A, Vijayakumar S (2022) Human-in-the-loop optimization of exoskeleton assistance via online simulation of metabolic cost. IEEE Trans Robot 38(3):1410–1429
Hu N, Wang A, Wu Y (2021) Robust adaptive pd-like control of lower limb rehabilitation robot based on human movement data. PeerJ Comput Sci 7:e394
Du Y, Wang H, Qiu S, Yao W, Xie P, Chen X (2018) An advanced adaptive control of lower limb rehabilitation robot. Front Robot AI 5:116
Al-Quraishi MS, Elamvazuthi I, Daud SA, Parasuraman S, Borboni A (2018) EEG-based control for upper and lower limb exoskeletons and prostheses: a systematic review. Sensors 18(10):3342
Niu J, Yang Q, Wang X, Song R (2017) Sliding mode tracking control of a wire-driven upper-limb rehabilitation robot with nonlinear disturbance observer. Front Neurol 8:646
Rezaee K, Haddadnia J, Delbari A (2015) Modeling abnormal walking of the elderly to predict risk of the falls using Kalman filter and motion estimation approach. Comput Electr Eng 46:471–486
Ali A, Ahmed SF, Kadir KA, Joyo MK, Yarooq RS (2018) Fuzzy pid controller for upper limb rehabilitation robotic system. In: 2018 IEEE international conference on innovative research and development (ICIRD), pp 1–5
Miao Q, Zhang M, Wang Y Xie SQ (2017) Design and interaction control of a new bilateral upper-limb rehabilitation device. J Healthc Eng 2017
He W, Ge SS, Li Y, Chew E, Ng YS (2015) Neural network control of a rehabilitation robot by state and output feedback. J Intell Robot Syst 80(1):15–31
Rose L, Bazzocchi MC, Nejat G (2022) A model-free deep reinforcement learning approach for control of exoskeleton gait patterns. Robotica 40(7):2189–2214
Joyo MK, Raza Y, Ahmed SF, Billah M, Kadir K, Naidu K, Ali A, Mohd Yusof Z (2019) Optimized proportional-integral-derivative controller for upper limb rehabilitation robot. Electronics 8(8):826
Al-Waeli KH, Ramli R, Haris SM, Zulkoffli ZB, Amiri MS (2021) Offline ANN-PID controller tuning on a multi-joints lower limb exoskeleton for gait rehabilitation. IEEE Access 9:107360–107374
Liu C, Su J (2011) Bipedwalking control using offline and online optimization. In: Proceedings of the 30th Chinese control conference, pp 3472–3477
Jezernik S, Pfister A, Frueh H, Colombo G, Morari M (1999) Robotic orthosis lokomat: its use in the rehabilitation of locomotion and in the development of the biology-based neural controller. In: Annual IFESS conference, Ljubljana, pp 301–303
Jezernik S, Colombo G, Keller T, Frueh H, Morari M (2003) Robotic orthosis lokomat: A rehabilitation and research tool. Neuromodul: Technol Neural Interf 6(2):108–115
Baronchelli F, Zucchella C, Serrao M, Intiso D, Bartolo M (2021) The effect of robotic assisted gait training with lokomat® on balance control after stroke: systematic review and meta-analysis. Front Neurol 12:1073
Westlake KP, Patten C (2009) Pilot study of lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke. J Neuroeng Rehabil 6(1):1–11
van Kammen K, Boonstra AM, van der Woude LH, Visscher C, Reinders-Messelink HA, den Otter R (2020) Lokomat guided gait in hemiparetic stroke patients: the effects of training parameters on muscle activity and temporal symmetry. Disabil Rehabil 42(21):2977–2985
Weng J, Hashemi E, Arami A (2021) Natural walking with musculoskeletal models using deep reinforcement learning. IEEE Robot Autom Lett 6(2):4156–4162
Cespedes N, Munera M, Gomez C, Cifuentes CA (2020) Social human-robot interaction for gait rehabilitation. IEEE Trans Neural Syst Rehabil Eng 28(6):1299–1307
Zhou J, Li Z, Li X, Wang X, Song R (2021) Human-robot cooperation control based on trajectory deformation algorithm for a lower limb rehabilitation robot. IEEE/ASME Trans Mechatron 26(6):3128–3138
Li X, Zhong J (2020) Upper limb rehabilitation robot system based on Internet of Things remote control. IEEE Access 8:154461–154470
Rezage G Al, Tokhi M (2016) Fuzzy pid control of lower limb exoskeleton for elderly mobility. In: 2016 IEEE international conference on automation, quality and testing, robotics (AQTR), pp 1–6
Semwal VB, Gupta A, Lalwani P (2021) An optimized hybrid deep learning model using ensemble learning approach for human walking activities recognition. J Supercomput 77(11):12256–12279
Gupta A, Semwal VB (2022) Occluded gait reconstruction in multi person gait environment using different numerical methods. Multimed Tools Appl 1–28
Rajagopal A, Dembia CL, DeMers MS, Delp DD, Hicks JL, Delp SL (2016) Full-body musculoskeletal model for muscle-driven simulation of human gait. IEEE Trans Biomed Eng 63(10):2068–2079
Seth A, Anderson FC (2017) Gait 2392 and 2354 models
Scherzinger S, Roennau A, Dillmann R (2019) Inverse kinematics with forward dynamics solvers for sampled motion tracking. In: 2019 19th international conference on advanced robotics (ICAR), pp 681–687
Mistry M, Nakanishi J, Cheng G, Schaal S (2008) Inverse kinematics with floating base and constraints for full body humanoid robot control. In: Humanoids 2008–8th IEEE-RAS international conference on humanoid robots, pp 22–27
Li J, Wang J, Chou W, Zhang Y, Wang T, Zhang Q (2001) Inverse kinematics and dynamics of the 3-rrs parallel platform. In: Proceedings 2001 ICRA. IEEE international conference on robotics and automation (Cat. No. 01CH37164), vol 3, pp 2506–2511
Mohammed RH, Bendary F, Elserafi K (2016) Trajectory tracking control for robot manipulator using fractional order-fuzzy-pid controller. Int J Comput Appl 134(15):22–29
Tao Y, Zheng J, Lin Y (2016) A sliding mode control-based on a rbf neural network for deburring industry robotic systems. Int J Adv Robot Syst 13(1):8
Gao W, Shi J, Wang W, Sun Y (2017) Research on sliding mode control for robotic manipulator based on rbf neural network. In: 2017 29th Chinese control and decision conference (CCDC), pp 4934–4938
Bao L, Kim D, Yi S-J, Lee J (2021) Design of a sliding mode controller with fuzzy rules for a 4-dof service robot. Int J Control Autom Syst 19(8):2869–2881
Ak A (2022) Sliding mode controller design using fuzzy sliding surface for flexible joint manipulator. IETE J Res 68(1):760–767
Mishra C, Jebakumar J, Mishra B (2014) Controller selection and sensitivity check on the basis of performance index calculation. Int J Electr Electron Data Commun 2(1):91–93
Acknowledgements
The authors appreciate the HPC unit of MANIT Bhopal for providing high speed computing facility.
Author information
Authors and Affiliations
Contributions
Conceptualisation, A.G and V.B; Methodology, A.G and V.B; Software, A.G; Validation A.G and V.B; Supervision, V.B; writing–original draft preparation, A.G and V.B; proof-reading, A.G and V.B; The final manuscript have been approved by all authors.
Corresponding author
Ethics declarations
Conflict of interest
The authors proclaim no conflict of interest and the manuscript is an original outcome by the authors themselves.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gupta, A., Semwal, V.B. Adaptive neural & fuzzy controller for exoskeleton gait pattern control based on musculoskeletal modeling. Multimed Tools Appl 83, 49419–49439 (2024). https://doi.org/10.1007/s11042-023-17306-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-17306-5