Abstract
Acquiring human motor control strategies or intents is helpful for clinical research, wearable robotic device design and human-robot cooperation control. The state-of-art method is to construct an optimal control framework which is capable to predict the target motion and take the cost function as the potential control intents. Aimed to solve this problem, an echo state networks based state space model (SSM) extraction method and input-tracking inverse MPC algorithm are proposed in this paper. By applying Taylor expansion around an operating point, it is convenient to acquire the SSM via the SSM extraction method and more detailed information about human musculoskeletal system is preserved. Setting the target of the upper level optimization as input-tracking is more rational than conventional output-tracking structure, given the consideration that human motion control is a multiple-solution problem. The effectiveness of the proposed method is verified in both simulation and real-world experiments.
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
Todorov, E.: Optimality principles in sensorimotor control. Nat. Neurosci. 7, 907–915 (2004)
Kuo, A.D.: An optimal control model for analyzing human postural balance. IEEE Trans. Biomed. Eng. 42, 87–101 (1995)
Dorn, T.W., Wang, J.M., Hicks, J.L., Delp, S.L.: Predictive simulation generates human adaptations during loaded and inclined walking. PLoS One 10, e0121407 (2015)
Mombaur, K., Truong, A., Laumond, J.-P.: From human to humanoid locomotion—an inverse optimal control approach. Auton. Robot. 28, 369–383 (2010)
Rebula, J.R., Schaal, S., Finley, J., Righetti, L.: A robustness analysis of inverse optimal control of bipedal walking. IEEE Robot. Autom. Lett. 4, 4531–4538 (2019)
Ramadan, A., Choi, J., Radcliffe, C.J., Popovich, J.M., Reeves, N.P.: Inferring control intent during seated balance using inverse model predictive control. IEEE Robot. Autom. Lett. 4, 224–230 (2019)
Pan, Y., Wang, J.: Model predictive control of unknown nonlinear dynamical systems based on recurrent neural networks. IEEE Trans. Industr. Electron. 59, 3089–3101 (2012)
Armenio, L.B., Terzi, E., Farina, M., Scattolini, R.: Model predictive control design for dynamical systems learned by echo state networks. IEEE Control Syst. Lett. 3, 1044–1049 (2019)
Xiang, K., Li, B.N., Zhang, L., Pang, M., Wang, M., Li, X.: Regularized Taylor echo state networks for predictive control of partially observed systems. IEEE Access 4, 3300–3309 (2016)
Acknowledgment
This work was supported by the National Natural Science Foundation of China under Grant 61603284 and 61903286.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Gong, P., Pang, M., Xiang, K., Zhang, L., Tang, B. (2021). Human Control Intent Inference Using ESNs and Input-Tracking Based Inverse Model Predictive Control. In: Liu, XJ., Nie, Z., Yu, J., Xie, F., Song, R. (eds) Intelligent Robotics and Applications. ICIRA 2021. Lecture Notes in Computer Science(), vol 13013. Springer, Cham. https://doi.org/10.1007/978-3-030-89095-7_61
Download citation
DOI: https://doi.org/10.1007/978-3-030-89095-7_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89094-0
Online ISBN: 978-3-030-89095-7
eBook Packages: Computer ScienceComputer Science (R0)