Learning muscle activation patterns via nonlinear oscillators: Application to lower-limb assistance

Achieving coordination between a lower-limb exoskeleton and its user is challenging because walking is a dynamic process that involves multiple, precisely timed muscle activations. Electromyographical (EMG) feedback, in spite of its drawbacks, provides an avenue for assistance by enabling users to reduce the level of muscle activation required for walking. As an alternative to direct EMG feedback, we present a method for exoskeleton control based on learning the activation pattern of specific muscles during cyclic movements. Using the example of pendular leg motion, the torque profile of one muscle group (hip flexors) is learned in a two-step process. First, the estimated torque profile is indexed to the phase of the swing movement using an adaptive frequency oscillator (AFO). The profile is then encoded using linear weighted regression. In the algorithm´s assistive mode, the learned profile is reconstructed by means of the AFO and without need for additional EMG input. The reconstructed profile is converted into a torque profile to be physically delivered by the exoskeleton. We tested our method on a single-actuator exoskeleton that assists the hip joint during stationary leg swing. The learning and assistance functions were built on top of an admittance controller that enhances the exoskeleton´s mechanical transparency. Initial tests showed a high level of coordination, i.e. simultaneous positive work, between the subjects´ hip flexor torque and the exoskeleton´s assistive torque. This result opens the door for future studies to test the users´ ability to reduce their muscle activation in proportion to the assistance delivered by the exoskeleton.