BIOMIMETIC DECODING OF SENSORIMOTOR INTENSION WITH ARTIFICIAL NEURAL NETWORKS

    公开(公告)号:US20240350285A1

    公开(公告)日:2024-10-24

    申请号:US18686027

    申请日:2022-08-24

    摘要: Various examples are provided related to biomimetics and use of ANNs for decoding and control. In one example. a method includes generating muscle model parameters by a musculoskeletal kinematic transformation implemented by a first artificial neural network. generating one or more physics engine parameters from a muscle model, and generating a physics engine transformation implemented by a second artificial neural network based at least in part upon the one or more physics engine parameters. The muscle model parameters can be based at least in part upon sensor inputs and the one or more physics engine parameters can be based at least in part the muscle model parameters. A sensorimotor mechanism can be controlled based on the physics engine transformation. In another example. a system for prosthetic control includes a plurality of sensors and processing circuitry configured to control a sensorimotor mechanism based upon the physics engine transformation.

    SYSTEMS AND METHODS FOR APPROXIMATING MUSCULOSKELETAL DYNAMICS

    公开(公告)号:US20200265943A1

    公开(公告)日:2020-08-20

    申请号:US16643163

    申请日:2018-09-18

    IPC分类号: G16H30/20 A61F2/70

    摘要: An approximation method and system are provided for more quickly controlling a prosthetic or other device by reducing computational processing time in a muscle model that can be used to control the prosthetic. For a given muscle, the approximation method can quickly compute polynomial structures for a muscle length and for each associated moment arms, which may be used to generate a torque for a joint position of a physics model. The physics model, in turn, produces a next joint position and velocity data for driving a prosthetic. The approximation method expands the polynomial structures as long as expansion is possible and sufficiently beneficial. The computations canbe performed quickly by expanding the polynomial structures in a way that constrains the muscle length polynomial to the moment arm polynomial structures, and vice versa.

    Systems and methods for controlling a self-paced treadmill using predicted subject velocity

    公开(公告)号:US10751561B2

    公开(公告)日:2020-08-25

    申请号:US15991497

    申请日:2018-05-29

    IPC分类号: A63B22/02 A63B24/00 A63B71/06

    摘要: Systems and methods are provided for enabling a split belt treadmill having two belts to self-pace. A feedback process estimates a first current step speed for a user on each belt by measuring stride length and step duration. A feed-forward process estimates a second current step speed for the user on each belt by measuring three forces and three moment components associated with foot contact with the belt. A command speed for each belt is produced by combining the first and second current step speeds with a Kalman filter. A belt speed associated with each belt is adjusted based upon the command speed.

    SYSTEMS AND METHODS FOR CONTROLLING A SELF-PACED TREADMILL USING PREDICTED SUBJECT VELOCITY

    公开(公告)号:US20180345070A1

    公开(公告)日:2018-12-06

    申请号:US15991497

    申请日:2018-05-29

    IPC分类号: A63B22/02 A63B24/00 A63B71/06

    摘要: Systems and methods are provided for enabling a split belt treadmill having two belts to self-pace. A feedback process estimates a first current step speed for a user on each belt by measuring stride length and step duration. A feed-forward process estimates a second current step speed for the user on each belt by measuring three forces and three moment components associated with foot contact with the belt. A command speed for each belt is produced by combining the first and second current step speeds with a Kalman filter. A belt speed associated with each belt is adjusted based upon the command speed.