The rhythm in which robotic prostheses have evolved over the past two decades indicates that they have a promising potential to replace passive prostheses in the foreseeable future. Powered lower limb prostheses, unlike the passive ones, can provide net positive work during the late stance, thus reducing the metabolic cost. Moreover, robotic prostheses can provide different characteristics in compliance with the walking terrains. The conventional three-level controllers of robotic lower limb prostheses are known for their intermittent and nondynamic properties, which limit prosthesis functioning to certain predefined tasks and require intense calibration for the controller’s parameters for each user. In this study, we report the capability of a nonlinear autoregressive recurrent neural network with exogenous inputs of generating the foot patterns for upslope terrain, that is, 10° incline, which is unknown for the neural network (not included in the training dataset). A new set of evaluation data from six able-bodied subjects (average age 31 and average weight 70.2 kg) was used to assess the network performance. The results show that the NARX was able to estimate foot trajectory for the new terrain without any further training, with an average RMSE of 2.953° for all six subjects.
Marzen-GrollerKBartmanK.Building a successful support group for post-amputation patients. J Vasc Nurs2005; 23: 42–45.
2.
BarmparasGInabaKTeixeiraPG, et al. Epidemiology of post-traumatic limb amputation: a National Trauma Databank analysis. Am Surg2010; 76: 1214–1222.
3.
McLaughlinMJ.10 - lower limb amputation and gait. In: CifuDXLewHL (eds) Braddom’s Rehabilitation Care: A Clinical Handbook. Elsevier, 2018, pp. 57–65.e54.
4.
HorganOMacLachlanM.Psychosocial adjustment to lower-limb amputation: a review. Disabil Rehabil2004; 26: 837–850.
5.
JonesLHallMSchuldW.Ability or disability? A study of the functional outcome of 65 consecutive lower limb amputees treated at the Royal South Sydney Hospital in 1988–1989. Disabil Rehabil1993; 15: 184–188.
6.
BehelJMRybarczykBElliottTR, et al. The role of perceived vulnerability in adjustment to lower extremity amputation: a preliminary investigation. Rehabil Psychol2002; 47: 92–105.
7.
GoldfarbMLawsonBEShultzAH.Realizing the promise of robotic leg prostheses. Sci Transl Med2013; 5: 210ps15–210ps215.
8.
WatersRLPerryJAntonelliD, et al. Energy cost of walking of amputees: the influence of level of amputation. J Bone Joint Surg Am1976; 58: 42–46.
9.
EphraimPLWegenerSTMacKenzieEJ, et al. Phantom pain, residual limb pain, and back pain in amputees: results of a national survey. Arch Phys Med Rehabil2005; 86: 1910–1919.
10.
BurkeMJRomanVWrightV.Bone and joint changes in lower limb amputees. Ann Rheum Dis1978; 37: 252–254.
11.
LemaireEDFisherFR.Osteoarthritis and elderly amputee gait. Arch Phys Med Rehabil1994; 75: 1094–1099.
12.
Jiménez-FabiánRVerlindenO.Review of control algorithms for robotic ankle systems in lower-limb orthoses, prostheses, and exoskeletons. Med Eng Phys2012; 34: 397–408.
13.
JayaramanCMummidisettyCKAlbertMV, et al. Using a microprocessor knee (C-leg) with appropriate foot transitioned individuals with dysvascular transfemoral amputations to higher performance levels: a longitudinal randomized clinical trial. J Neuroeng Rehabil2021; 18: 88.
14.
TuckerMROlivierJPagelA, et al. Control strategies for active lower extremity prosthetics and orthotics: a review. J Neuroeng Rehabil2015; 12: 1–30.
15.
WindrichMGrimmerMChristO, et al. Active lower limb prosthetics: a systematic review of design issues and solutions. Biomed Eng Online2016; 15: 140–219.
16.
WoodwardRBSpaniasJAHargroveLJ. User intent prediction with a scaled conjugate gradient trained artificial neural network for lower limb amputees using a powered prosthesis. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2016, pp. 6405–6408.
17.
BhaktaKCamargoJDonovanL, et al. Machine learning model comparisons of user independent & dependent intent recognition systems for powered prostheses. IEEE Robot Autom Lett2020; 5: 5393–5400.
18.
InoueKFukudaTWadaT. A control method for transfemoral prosthetic knees based on thigh angular motion. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2019, pp. 6644–6647.
19.
StolyarovRBurnettGHerrH.Translational motion tracking of leg joints for enhanced prediction of walking tasks. IEEE Trans Biomed Eng2018; 65: 763–769.
20.
StolyarovRCarneyMHerrH.Accurate heuristic terrain prediction in powered lower-limb prostheses using onboard sensors. IEEE Trans Biomed Eng2021; 68: 384–392.
21.
LeiLYinmaoSPengY, et al. Gait recognition based on the mean impact value and probability neural network. In: 2021 33rd Chinese Control and Decision Conference (CCDC). IEEE, 2021, pp. 1704–1707.
22.
MyersDRMoskowitzGD.Myoelectric pattern recognition for use in the volitional control of above-knee prostheses. IEEE Trans Syst Man Cybern1981; 11: 296–302.
23.
HillstromHJMoskowitzGD. Robust intent recognition for prosthesis control. In: 1992 14th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 1992, pp. 1448–1449.
24.
JinDZhangRZhangJ, et al. An intelligent above-knee prosthesis with EMG-based terrain identification. In: SMC 2000 Conference Proceedings. 2000 IEEE international conference on systems, man and cybernetics. ‘Cybernetics evolving to systems, humans, organizations, and their complex interactions’ (cat no 0). IEEE, 2000, pp. 1859–1864.
25.
AuSKBonatoPHerrH. An EMG-position controlled system for an active ankle-foot prosthesis: an initial experimental study. In: 9th International Conference on Rehabilitation Robotics, 2005 ICORR 2005. IEEE, 2005, pp. 375–379.
26.
AuSBernikerMHerrH.Powered ankle-foot prosthesis to assist level-ground and stair-descent gaits. Neural Netw2008; 21: 654–666.
27.
HuangHKuikenTALipschutzRD.A strategy for identifying locomotion modes using surface electromyography. IEEE Trans Biomed Eng2009; 56: 65–73.
28.
ChenLYangZZhangC, et al. Periodic locomotion-model recognition based on electromyography of thigh stump. In: 2018 24th International Conference on Automation and Computing (ICAC). IEEE, 2018, pp. 1–6.
29.
FanZHeH.Source selection for real-time user intent recognition toward volitional control of artificial legs. IEEE J Biomed Health Inform2013; 17: 907–914.
30.
ZhangFDiSantoWRenJ, et al. A novel CPS system for evaluating a neural-machine interface for artificial legs. In: 2011 IEEE/ACM Second International Conference on Cyber-Physical Systems. IEEE, 2011, pp. 67–76.
31.
SpaniasJASimonAMIngrahamKA, et al. Effect of additional mechanical sensor data on an EMG-based pattern recognition system for a powered leg prosthesis. In: 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER). IEEE, 2015, pp. 639–642.
32.
SpaniasJASimonAMFinucaneSB, et al. Online adaptive neural control of a robotic lower limb prosthesis. J Neural Eng2018; 15: 016015.
33.
ChenBZhengEFanX, et al. Locomotion mode classification using a wearable capacitive sensing system. IEEE Trans Neural Syst Rehabil Eng2013; 21: 744–755.
34.
ZhengEWangLWeiK, et al. A noncontact capacitive sensing system for recognizing locomotion modes of transtibial amputees. IEEE Trans Biomed Eng2014; 61: 2911–2920.
35.
DuLZhangFLiuM, et al. Toward design of an environment-aware adaptive locomotion-mode-recognition system. IEEE Trans Biomed Eng2012; 59: 2716–2725.
36.
ZhongBSilvaRLDLiM, et al. Environmental context prediction for lower limb prostheses with uncertainty quantification. IEEE Trans Autom Sci Eng2021; 18: 458–470.
37.
KrauszNEHargroveLJ.Sensor fusion of vision, kinetics, and kinematics for forward prediction during walking with a transfemoral prosthesis. IEEE Trans Med Robot Bionics2021; 3: 813–824.
38.
ZhangKXiongCZhangW, et al. Environmental features recognition for lower limb prostheses toward predictive walking. IEEE Trans Neural Syst Rehabil Eng2019; 27: 465–476.
39.
ZhangKLuoJXiaoW, et al. A subvision system for enhancing the environmental adaptability of the powered transfemoral prosthesis. IEEE Trans Cybern2021; 51: 3285–3297.
40.
LaschowskiBMcNallyWWongA, et al. Environment classification for robotic leg prostheses and exoskeletons using deep convolutional neural networks. Front Neurorobot2021; 15: 730965.
41.
GreggRDLenziTHargroveLJ, et al. Virtual constraint control of a powered prosthetic leg: from simulation to experiments with transfemoral amputees. IEEE Trans Robot2014; 30: 1455–1471.
42.
QuinteroDMartinAEGreggRD.Toward unified control of a powered prosthetic leg: a simulation study. IEEE Trans Control Syst Technol2018; 26: 305–312.
43.
BestTKEmbryKRRouseEJ, et al. Phase-variable control of a powered knee-ankle prosthesis over continuously varying speeds and inclines. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2021, pp. 6182–6189.
44.
HornJCGreggRD.Nonholonomic virtual constraints for control of powered prostheses across walking speeds. IEEE Trans Control Syst Technol2022; 30: 2062–2071.
45.
ZhaoHHornJReherJ, et al. Multicontact locomotion on transfemoral prostheses via hybrid system models and optimization-based control. IEEE Trans Autom Sci Eng2016; 13: 502–513.
46.
ZhaoHHornJReherJ, et al. A hybrid systems and optimization-based control approach to realizing multi-contact locomotion on transfemoral prostheses. In: 2015 54th IEEE Conference on Decision and Control (CDC). IEEE, 2015, pp. 1607–1612.
47.
GehlharRAmesAD.Model-dependent prosthesis control with interaction force estimation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2021, pp. 3226–3232.
48.
GehlharRYangJHAmesAD.Powered prosthesis locomotion on varying terrains: model-dependent control with real-time force sensing. IEEE Robot Autom Lett2022; 7: 5151–5158.
49.
HaKHVarolHAGoldfarbM.Volitional control of a prosthetic knee using surface electromyography. IEEE Trans Biomed Eng2011; 58: 144–151.
50.
HaKHVarolHAGoldfarbM. Myoelectric control of a powered knee prosthesis for volitional movement during non-weight-bearing activities. In: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. IEEE, 2010, pp. 3515–3518.
51.
Alcaide-AguirreREMorgenrothDCFerrisDP.Motor control and learning with lower-limb myoelectric control in amputees. J Rehabil Res Dev2013; 50: 687–698.
52.
Hasanzadeh FereydooniRSiahkaliHShayanfarHA, et al. SEMG-based variable impedance control of lower-limb rehabilitation robot using wavelet neural network and model reference adaptive control. Ind Robot Int J Robot Res Appl2020; 47: 349–358.
53.
RaiVRombokasE. A framework for mode-free prosthetic control for unstructured terrains. In: 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR). IEEE, 2019, pp. 796–802.
54.
RaiVSharmaARombokasE. Mode-free control of prosthetic lower limbs. In: 2019 International Symposium on Medical Robotics (ISMR). IEEE, 2019, pp. 1–7.
55.
KouzbaryHAKouzbaryMAThamLK, et al. Generating an adaptive and robust walking pattern for a prosthetic ankle-foot by utilizing a nonlinear autoregressive network with exogenous inputs. IEEE Trans Neural Netw Learn Syst2022; 33: 6297–6305.
56.
Al KouzbaryMAl KouzbaryHThamLK, et al. A combinational approach to generate nonlinear foot trajectories for robotic prothesis with elementary clinical results. In: Kuala Lumpur International Conference on Biomedical Engineering. Springer, 2021, pp. 27–35.
57.
WuRYaoZSiJ, et al. Robotic knee tracking control to mimic the intact human knee profile based on actor-critic reinforcement Learning. IEEE/CAA J Automat Sinica2022; 9: 19–30.
58.
WangYChengXJabbanL, et al. Motion intention prediction and joint trajectories generation toward lower limb prostheses using EMG and IMU signals. IEEE Sens J2022; 22: 10719–10729.
59.
KimMHargroveLJ.A gait phase prediction model trained on benchmark datasets for evaluating a controller for prosthetic legs. Front Neurorobot2022; 16: 1064313.
60.
ClarkRN.Integral of the error squared as a performance index for automatic control systems. Trans Am Inst Electr Eng Part I:I Appl Ind1961; 79: 467–471.
61.
McGinleyJLBakerRWolfeR, et al. The reliability of three-dimensional kinematic gait measurements: a systematic review. Gait Posture2009; 29: 360–369.
62.
Al KouzbaryHAl KouzbaryMLiuJ, et al. ANOVA and linear regression feature selection for GRU-based foot position prediction in powered prostheses. Comput Methods Biomech Biomed Eng2025; 1–18.
63.
FarinaDVujaklijaIBrånemarkR, et al. Toward higher-performance bionic limbs for wider clinical use. Nat Biomed Eng2023; 7: 473–485.
64.
CimolatoADriessenJJMMattosLS, et al. EMG-driven control in lower limb prostheses: a topic-based systematic review. J Neuroeng Rehabil2022; 19: 43.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
