Abstract
Robotic assistive devices have emerged as a potential complement for repetitive and user-centered gait rehabilitation. In this field, the development of electromyography (EMG)-based torque controls has played a crucial role in improving the user experience with robotic assistive devices. However, most existing approaches for EMG-based joint torque estimation (i) are designed for upper limbs; (ii) often do not consider the complexity of the walking motion, focusing only on the stance phase; and (iii) rely on complex mathematical models that result in time-consuming estimations. This study aims to address these shortcomings by evaluating the generalization ability of a Deep Learning regressor (Convolutional Neural Network (CNN)) for estimating ankle torque trajectories, in real-time. Several inputs were incorporated, namely, EMG signals from Tibialis Anterior and Gastrocnemius Lateralis, hip kinematic data in the sagittal plane (angle, angular velocity, angular acceleration), walking speed (from 1.5 to 2.0 km/h), user’s demographic (gender and age) and anthropometric information (height and mass, ranging from 1.50 to 1.90 m and 50.0 to 90.0 kg, respectively, and shank and foot lengths). Results showed that a CNN model with two convolutional layers showed the highest generalization ability (Root Mean Square Error: 23.4 ± 8.36, Normalized Mean Square Error: 0.494 ± 0.299, and Spearman Correlation 0.754 ± 0.105). CNN model’s time-effectiveness was tested in an active ankle orthosis, being able to estimate ankle joint torques in less than 2 ms. This study contributes to a more time-effective model for real-time EMG-based torque estimation, enabling a promising advancement in EMG-based torque control for lower limb robotic assistive devices.
This work was funded by the Fundação para a Ciência e Tecnologia under the scholarship reference 2020.05711.BD, under the Stimulus of Scientific Employment with the grant 2020.03393.CEECIND, with the FAIR project under grant 2022.05844.PTDC, under the national support to R&D units grant through the reference project UIDB/04436/2020 and UIDP/04436/2020, and under the scholarship reference POCI-01-0247-FEDER-039868_BI_04_2022_CMEMS.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Meng, W., Liu, Q., Zhou, Z., et al.: Recent development of mechanisms and control strategies for robot-assisted lower limb rehabilitation. Mechatronics 31, 132–145 (2015). https://doi.org/10.1016/j.mechatronics.2015.04.005
Zhang, J., Cheah, C.C., Collins, S.H.: Torque control in legged locomotion. In: Bioinspired Legged Locomotion, 1st edn., pp. 347–400. Elsevier (2017)
Baud, R., Manzoori, A.R., Ijspeert, A., Bouri, M.: Review of control strategies for lower-limb exoskeletons to assist gait. J. Neuroeng. Rehabil. 18, 119 (2021). https://doi.org/10.1186/s12984-021-00906-3
Ao, D., Song, R., Gao, J.: Movement performance of human-robot cooperation control based on EMG-driven hill-type and proportional models for an ankle power-assist exoskeleton robot. IEEE Trans. Neural Syst. Rehabil. Eng. 25, 1125–1134 (2017). https://doi.org/10.1109/TNSRE.2016.2583464
Sartori, M., Lloyd, D.G., Reggiani, M., Pagello, E.: A stiff tendon neuromusculoskeletal model of the knee. In: 2009 IEEE Workshop on Advanced Robotics and its Social Impacts, pp. 132–138. IEEE (2009)
Gui, K., Liu, H., Zhang, D.: A practical and adaptive method to achieve EMG-based torque estimation for a robotic exoskeleton. IEEE/ASME Trans. Mechatron. 24, 483–494 (2019). https://doi.org/10.1109/TMECH.2019.2893055
Chandrapal, M., Chen, X., Wang, W., et al.: Investigating improvements to neural network based EMG to joint torque estimation. Paladyn. J. Behav. Robot. 2, 185–192 (2011). https://doi.org/10.2478/s13230-012-0007-2
Lelas, J.L., Merriman, G.J., Riley, P.O., Kerrigan, D.C.: Predicting peak kinematic and kinetic parameters from gait speed. Gait Posture 17, 106–112 (2003). https://doi.org/10.1016/S0966-6362(02)00060-7
Fleischer, C., Reinicke, C., Hommel, G.: Predicting the intended motion with EMG signals for an exoskeleton orthosis controller. In: 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2029–2034. IEEE (2005)
Liu, L., Luken, M., Leonhardt, S., Misgeld, B.J.E.: EMG-driven model-based knee torque estimation on a variable impedance actuator orthosis. In: IEEE International Conference on Cyborg and Bionic Systems (CBS), pp. 262–267. IEEE (2017)
Durandau, G., Farina, D., Sartori, M.: Robust real-time musculoskeletal modeling driven by electromyograms. IEEE Trans. Biomed. Eng. 65, 556–564 (2018). https://doi.org/10.1109/TBME.2017.2704085
Li, Y., Chen, W., Yang, H., et al.: Joint torque closed-loop estimation using NARX neural network based on sEMG signals. IEEE Access 8 (2020). https://doi.org/10.1109/ACCESS.2020.3039983
Lu, L., Wu, Q., Chen, X., et al.: Development of a sEMG-based torque estimation control strategy for a soft elbow exoskeleton. Rob. Auton. Syst. 111, 88–98 (2019). https://doi.org/10.1016/j.robot.2018.10.017
Ullauri, J.B., Peternel, L., Ugurlu, B., et al.: On the EMG-based torque estimation for humans coupled with a force-controlled elbow exoskeleton. In: 2015 International Conference on Advanced Robotics (ICAR), pp. 302–307. IEEE (2015)
Wang, C., Peng, L., Hou, Z.-G., et al.: sEMG-based torque estimation using time-delay ANN for control of an upper-limb rehabilitation robot. In: 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), pp. 585–591. IEEE (2018)
Yang, N., Li, J., Xu, P., et al.: Design of elbow rehabilitation exoskeleton robot with sEMG-based torque estimation control strategy. In: 2022 6th International Conference on Robotics and Automation Sciences (ICRAS), pp. 105–113. IEEE (2022)
Moreira, L., Figueiredo, J., Vilas-Boas, J.P., Santos, C.P.: Kinematics, speed, and anthropometry-based ankle joint torque estimation: a deep learning regression approach. Machines 9, 154 (2021). https://doi.org/10.3390/machines9080154
Figueiredo, J., Santos, C.P., Moreno, J.C.: Smart wearable orthosis to assist impaired human walking (2019)
Bortole, M., Venkatakrishnan, A., Zhu, F., et al.: The H2 robotic exoskeleton for gait rehabilitation after stroke: early findings from a clinical study. J. Neuroeng. Rehabil. 12, 54 (2015). https://doi.org/10.1186/s12984-015-0048-y
Figueiredo, J., Carvalho, S., Vilas-Boas, J.P., et al.: Wearable inertial sensor system towards daily human kinematic gait analysis : benchmarking analysis to MVN BIOMECH. Sensors (2020). https://doi.org/10.3390/s20082185
Figueiredo, J., Ferreira, C., Costa, L., et al.: Instrumented insole system for ambulatory and robotic walking assistance: first advances. In: IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC 2017) (2017)
Pinheiro, C., Figueiredo, J., Magalhães, N., Santos, C.P.: Wearable biofeedback improves human-robot compliance during ankle-foot exoskeleton-assisted gait training: a pre-post controlled study in healthy participants. Sensors 20, 5876 (2020). https://doi.org/10.3390/s20205876
Delsys Incorporated: TRIGNO ® Wireless System SDK User’s Guide, pp. 1–29 (2019)
Lévesque, L.: Nyquist sampling theorem: understanding the illusion of a spinning wheel captured with a video camera. Phys. Educ. 49, 697–705 (2014). https://doi.org/10.1088/0031-9120/49/6/697
Kerrigan, D.C., Todd, M.K., Croce, U.D.: Gender differences in joint biomechanics during walking. Am. J. Phys. Med. Rehabil. 77, 2–7 (1998). https://doi.org/10.1097/00002060-199801000-00002
Karatayev, A.Y., Burlakova, L.E., Miller, T.D., Perrelli, M.F.: Reconstructing historical range and population size of an endangered mollusc: long-term decline of Popenaias popeii in the Rio Grande, Texas. Hydrobiologia 810(1), 333–349 (2015). https://doi.org/10.1007/s10750-015-2551-3
Moreira, L., Figueiredo, J., Fonseca, P., et al.: Lower limb kinematic, kinetic, and EMG data from young healthy humans during walking at controlled speeds. Sci. Data 8, 103 (2021). https://doi.org/10.1038/s41597-021-00881-3
Moreira, L.: Assist-as-needed EMG-based control strategy for powered wearable assistive devices. Universidade do Minho (2019)
ONNX Runtime. https://onnxruntime.ai/
Shah, B., Bhavsar, H.: Time complexity in deep learning models. Procedia Comput. Sci. 215, 202–210 (2022). https://doi.org/10.1016/j.procs.2022.12.023
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Moreira, L., Barbosa, R.M., Figueiredo, J., Fonseca, P., Vilas-Boas, J.P., Santos, C.P. (2024). Real-Time Torque Estimation Using Human and Sensor Data Fusion for Exoskeleton Assistance. In: Marques, L., Santos, C., Lima, J.L., Tardioli, D., Ferre, M. (eds) Robot 2023: Sixth Iberian Robotics Conference. ROBOT 2023. Lecture Notes in Networks and Systems, vol 978. Springer, Cham. https://doi.org/10.1007/978-3-031-59167-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-59167-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-59166-2
Online ISBN: 978-3-031-59167-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)