A computer program product comprising a non-transitory computer readable medium having a computer readable program embodied therein, wherein the computer readable program, when executed on a computing device, causes the computing device to:
- personalize a neuromusculoskeletal arm model having three joints and a set of muscle actuators, wherein the neuromusculoskeletal arm model is adapted to conform with anthropometric measurements of a subject and is configured to perform one or more motion tasks by the subject using the three joints being a ball and socket shoulder joint along with clavicle and scapula having three degrees of freedom (DoF), an elbow joint with one DoF and a wrist joint having three DoF, wherein the anthropometric measurements of the subject include height, weight, triceps and mid-upper-arm circumference that provides a proxy measure of body composition including muscularity, fat free mass and fat mass, wherein the neuromusculoskeletal arm model captures dynamics of glenohumeral joint for specific point to point hand reaching task involving active elbow flexion, and wherein the one or more motion tasks resemble point to point hand reaching tasks in a three-dimensional plane, keeping trajectory of the elbow joint fixed in all three motions, M1, M2 and M3 and the motions resemble routine exercise motion to regain joint operative range of motion after stroke or any rehabilitation specific to neuro-motor disorder;
- optimize the set of muscle actuators by performing the following iterative steps starting with the set of muscle actuators in the personalized neuromusculoskeletal arm model in a first iteration and every subsequent iteration having a reduced number of muscle actuators in the set of muscle actuators compared to a previous iteration by:
- calculating a muscle torque indicative of a muscle force based on a moment arm, an activation value a obtained from a muscle Electromyography (EMG) data, a normalized length l and a normalized velocity {dot over (l)} of each muscle actuator in the set of muscle actuators, wherein when a muscle is neurally excited, the activation value increases and when the muscle's excitation decreases, the activation value decreases;
- calculating a joint torque indicative of loading on each of the three joints, wherein the joint torque is based on an acceleration {umlaut over (q)} due to the joint torque t, the joint angle q, an inertia tensor function Q, a mass matrix M, a Coriolis component C, a gravity component G and an external force F applied to the neuromusculoskeletal arm model;
- generating a trajectory associated with a corresponding motion profile for each of the one or more motion tasks based on forward dynamics using the calculated muscle torque and the calculated joint torque;
- and
- evaluating a mean square error between the generated trajectory and a target trajectory associated with a corresponding motion profile for each of the one or more motion tasks;
- until the evaluated mean square error is less than a pre-defined threshold;
- identify the set of the muscle actuators with the reduced number of muscle actuators at the end of the iterative steps as the optimized set of muscle actuators to perform the one or more motion tasks;
- and
- estimating optimal muscle synergy, via the one or more hardware processors, corresponding to the one or more motion tasks using Non-Negative Matrix Factorization (NNMF), wherein the NNMF reduces a number of commands needed for controlling the optimized set of muscle actuators into a low dimensional subspace, wherein the muscle synergy is used to derive redundant muscle information from the optimized set of muscle actuators, which aids to recreate desired motion if any of the major muscles get damaged due to motor injury,
- wherein the personalized neuromusculoskeletal arm model with the optimized set of muscle actuators allows different motions to be simulated using various possible joint configuration and both an orientation and an elevation of the shoulder joint dictates muscle recruitment pattern for fixed elbow motion, and a minimum energy trajectory corresponds to a minimum synergy configuration,
- wherein a similarity index value of 75% for reconstruction of activation, M1 has minimum synergy value of 4, M2 has minimum synergy value of 5 and M3 has minimum synergy value of 3, and M3 corresponding to a configuration due to alteration of both shoulder rotation and elevation shows minimum synergy requirement for reconstruction,
- wherein a synergy space configuration and an energy optimized trajectory enables planning a personalized rehabilitation therapy for post stroke patients with neuromotor disabilities and aid in control of neuro-prosthetic arms.