A method is disclosed for using an artificial intelligence engine to modify resistance of pedals of an exercise device. The method includes generating, by the artificial intelligence engine, a machine learning model trained to receive measurements as input, and outputting, based on the measurements, a control instruction that causes the exercise device to modify, independently from each other, the resistance of the pedals. While a user performs an exercise using the exercise device, the method includes receiving the measurements from sensors associated with the pedals. The method includes determining, based on the measurements, a quantifiable or qualitative modification to the resistance provided by a pedal of the pedals. The resistance provided by another pedal of the pedals is not modified. The method includes transmitting the control instruction to the exercise device to cause the resistance provided by the pedal to be modified.

A method and apparatus for automated arm training includes at least one therapeutic device that includes a handle, a sensor assembly, and a display. The handle is configured to move along a path. The sensor assembly is configured to provide a measured time series made up of multiple handle location measurements at a corresponding multiple of measured time instances. The display is configured to present an image based on the measured time series. A robot motor can be configured to keep the handle moving near a tolerance of a target trajectory.

An exercise equipment device includes an exercise device body including a load applying unit configured to add, reduce, or maintain a load according to a set exercise level, a user manipulation unit moving according to a movement of a user, and a load transmitting unit configured to transmit the load applied by the load applying unit to the user manipulation unit, a sensor configured to detect movement information of the user manipulation unit, a user input unit configured to input user information, and a processor configured to determine a first user motion range based on a detection result of the sensor and the user information, wherein the processor is further configured to determine the first user motion range based on the user information, an upper limit movement range and a lower limit movement range.

Provided herein are embodiments of a barbell spotting apparatus having all the benefits of a free-floating, unconstrained barbell in both the horizontal and vertical axes with the safety of a dedicated spotting mechanism, while addressing safety, noise, and space concerns raised by typical barbell apparatus. The embodiments herein permit a loaded barbell to be positioned in line with the axis of motion of the lift to be performed at both the beginning and end of the lift.

An exercise machine may include a frame, a resistance mechanism supported by the frame, first and second pull cables supported by the frame and linked to the resistance mechanism, a power rack attached to the frame, first and second handles selectively attachable to the first and second pull cable, and first and second pulleys. The power rack includes upright posts configured to have barbell holders adjustably attached thereto such that the barbell holders are configured to be adjusted in various positions between highest positions and lowest positions on the upright posts. The pulleys are configured to selectively receive the pull cables to enable the pull cables to be selectively attached to a barbell to assist or hinder a user in lifting the barbell in a combined cableand free weight workout, the pull cables decoupled from the pulleys for cable workouts.

An exercise apparatus includes a motor configured to generate a force experienced by a user of the exercise apparatus, a video monitor, and circuitry. The circuitry is configured to obtain an augmented video file from a remote streaming service. The augmented video file comprises a video and a plurality of settings. The augmented video file associates the plurality of settings with a plurality of time steps during a runtime of the video. The circuitry is also configured to cause the video monitor to display the video, and, at each of the plurality of time steps during the runtime of the video, control the motor in accordance with the setting associated with the time step.

An exercise machine is disclosed. The exercise machine comprises a pancake motor. The exercise machine comprises a torque controller coupled to the pancake motor. The exercise machine comprises a high resolution encoder coupled to the pancake motor.

An exercise machine comprises an actuator, a motor coupled to the actuator, and a motor controller coupled to the motor. The motor controller is configured to receive an indication of a characteristic of a workout on the actuator, wherein the workout comprises a next exercise movement, determine a suggested weight for the next exercise movement, based at least in part on a physiological analysis of the workout characteristic, and control torque of the motor for the next exercise movement, based at least in part on the suggested weight.

A computer-implemented system may include an electromechanical machine configured to be manipulated by a user while the user performs a treatment plan, an interface comprising a display configured to present information associated with the treatment plan, and a processing device configured to receive, from one or more data sources, information associated with the user, wherein the information comprises one or more risk factors associated with a cardiac condition or a cardiac outcome, generate, using one or more trained machine learning models, the treatment plan for the user, wherein the treatment plan is generated based on the information associated with the user, and the treatment plan comprises one or more exercises associated with managing the one or more risk factors in order to reduce a probability of a cardiac intervention for the user, and transmit the treatment plan to cause the electromechanical machine to implement the one or more exercises.

A wearable device may include a motor, a motor driver circuit, a frame connected to the motor, the frame to be worn on the body of the user to support the body, a processor configured to generate a control signal to control an electrical connection in the motor driver circuit, and a sensor configured to sense a body motion of the user. The processor is further configured to provide an exercise load through the frame according to a speed of the sensed body motion by controlling, based on the speed of the body motion, a changing ratio per time between a first control state in which the electrical connection in the motor driver circuit is a closed loop and a second control state in which the electrical connection in the motor driver circuit is an open loop.