An Adaptive Robotic Assistance Platform for Neurorehabilitation Therapy of Upper Limb
Abstract
There are many human-robot physical interaction methods for physical therapy in patients of upper limbs disabilities. The use of haptic devices for this purpose is abundant, as are the different proposals for motion control in haptic guidance, as part of a clinical protocol with the patient in the loop. A conclusive result of these interaction platforms is the need to modify elements of the control strategy and the motion planning, this for each patient. In this paper, we propose a new approach to the control of human-robot physical interaction systems. To guarantee the bilateral energy flow between the robotic system and the patient under stable conditions and, without modifying the interaction platform; we propose an adaptive control structure, free of the dynamic model. The control scheme is called PID Wavenet, and identifies the dynamics using a radial basis neural network with daughter RASP1 wavelets activation function; its output is in cascaded with an infinite impulse response (IIR) filter toprune irrelevant signals and nodes as well as to recover a canonical form. Then, online adaptive of a discrete PID regulator is proposed, whose closed-loop guarantees global regulation for nonlinear dynamical plants, in our case a haptic device with the human in the loop. Effectiveness of the proposed method is verified by the real-time experiments on a Geomagic Touch haptic interface.
Keywords
Human robot interaction Haptic interface Wavelet neural network control Rehabilitation roboticsReferences
- 1.Daubechies, I.: Ten Lectures on Wavelets. SIAM, Philadelphia (1992)CrossRefGoogle Scholar
- 2.Fu, M.J., Cavusoglu, M.C.: Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface. IEEE Trans. Syst., Man, Cybern., Part B (Cybern.) 42, 1633–1644 (2012)CrossRefGoogle Scholar
- 3.Haykin, S.: Kalman Filtering and Neural Networks. Wiley, Hoboken (2001)CrossRefGoogle Scholar
- 4.Jarillo-Silva, A., Domínguez-Ramírez, O.A., Parra-Vega, V., Ordaz-Oliver, J.P.: PHANToM OMNI haptic device: kinematic and manipulability. In: IEEE, Electronics, Robotics and Automotive Mechanics Conference 2009, CERMA 2009, pp. 193–198 (2016). https://doi.org/10.1109/CERMA.2009.55
- 5.Krebs, H.I., Hogan, N., Aisen, M.L., Volpe, B.T.: Robot-aided neurorehabilitation. IEEE Trans. Rehabil. Eng. 6, 75–87 (1998)CrossRefGoogle Scholar
- 6.Levin, A., Narendra, K.: Control of nonlinear dynamical systems using neural networks: controllability and stabilization. IEEE Trans. Newral Netw. 4, 192–206 (1993)CrossRefGoogle Scholar
- 7.Ramos-Velasco, L.E., Domínguez-Ramírez, O.A., Parra-Vega, V.: Wavenet fuzzy PID controller for nonlinear MIMO systems: experimental validation on a high-end haptic robotic interface. Appl. Soft Comput. 40, 199–205 (2016)CrossRefGoogle Scholar
- 8.Suleman, K., Andersson, K., Wikander, J.: Dynamic based control strategy for haptic devices. In: IEEE, World Haptics Conference, pp. 131–136 (2011)Google Scholar
- 9.Spong, M.W., Vidyasagar, M.: Robot Dynamics and Control. Wiley, Hoboken (1989)Google Scholar
- 10.Turijan-Rivera, J.A., Ruiz-Sanchez, F.J., Domínguez-Ramírez, O.A., Parra-Vega, V.: Modular platform for haptic guidance in paediatric rehabilitation of upper limb neuromuscular disabilities. In: Pons, J., Torricelli, D., Pajaro, M. (eds.) Converging Clinical and Engineering Research on Neurorehabilitation. BIOSYSROB, vol. 1, pp. 923–928. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-34546-3_150CrossRefGoogle Scholar