Posts Tagged Mathematical model
[Abstract] Configuration Optimization of a Dual-Arm Rehabilitation Robot – IEEE Conference Publication
[Abstract] Design and development of an upper limb rehabilitation robotic system – IEEE Conference Publication
[Abstract] Kinematic analysis and control for upper limb robotic rehabilitation system – IEEE Conference Publication
Statistics shows that, at European Union level, the upper limb is second common body part injured, as a result of unintentional physical injury . Also, one can note the shortage of therapists and high costs for patient or healthcare insurance systems. Current development in robotics may offer a solution for this problem , allowing the creation of robotic devices to support the rehabilitation process, in a supervised or unsupervised way, in physiotherapy clinics or at home. In this context, we proposed RAPMES, a new intelligent, adaptive robotic system, which can provide the rehabilitation protocols, defined by a therapist, for the wrist and elbow of upper limb, considering the patient reactions and based on real-time feedback. RAPMES robotic system is designed on an ongoing research project, which implies several stages of development. In a first stage, we conducted a study involving therapists, the personnel and devices existent in a physiotherapy clinic. The role of this study was to determine the requirements for the robotic device, and to reveal the specific therapeutic needs of patients with rehabilitation indications at wrist and elbow level. On a second stage, we used a real-time video motion analysis system, to determine and understand specific functional movements frequently made with the dominant upper limb, by healthy persons. One of our research objectives is to include these movements as a part of RAPMES control algorithm, as they may offer a better rehabilitation of the upper limb, for specific moves. Next, we designed the robotic device, based on findings described above, and realized an experimental model of the robotic device.
[ARTICLE] Reinforcement learning neural network (RLNN) based adaptive control of fine hand motion rehabilitation robot.
Recent neural science research suggests that a robotic device can be an effective tool to deliver the repetitive movement training that is needed to trigger neuroplasticity in the brain following neurologic injuries such as stroke and spinal cord injury (SCI).
In such scenario, adaptive control of the robotic device to provide assistance as needed along the intended motion trajectory with exact amount of force intensity, though complex, is a more effective approach. A critic-actor based reinforcement learning neural network (RLNN) control method is explored to provide adaptive control during post-stroke fine hand motion rehabilitation training.
The effectiveness of the method is verified through computer simulation and implementation on a hand rehabilitation robotic device.
Results suggest that the control system can fulfil the assist-as-needed (AAN) control with high performance and reliability. The method demonstrates potential to encourage active participation of the patient in the rehabilitation process and to improve the efficiency of the process.