A novel energy-motion model for continuous sEMG decoding: from muscle
energy to motor pattern
Abstract
Myoelectric prosthetic hands create the possibility for amputees to
control their prosthetics like native hands. However, user acceptance of
the extant myoelectric prostheses is low. Unnatural control, lack of
sufficient feedback, and insufficient functionality are cited as primary
reasons. Recently, although many multiple degrees-of-freedom (DOF)
prosthetic hands and tactile-sensitive electronic skins have been
developed, no non-invasive myoelectric interfaces can decode both forces
and motions for five-fingers independently and simultaneously. This
paper proposes a myoelectric interface based on energy allocation and
fictitious forces hypothesis by mimicking the natural neuromuscular
system. The energy-based interface uses a kind of continuous “energy
mode” in the level of the entire hand. According to tasks itself, each
energy mode can adaptively and simultaneously implement multiple hand
motions and exerting continuous forces for a single finger. Also, a few
learned energy modes could extend to the unlearned energy mode,
highlighting the extensibility of this interface. We evaluate the
proposed system through off-line analysis and operational experiments
performed on the expression of the unlearned hand motions, the amount of
finger energy, and real-time control. With active exploration, the
participant was proficient at exerting just enough energy to five
fingers on “fragile” or “heavy” objects independently,
proportionally, and simultaneously in real-time. The main contribution
of this paper is proposing the bionic energy-motion model of hand:
decoding a few muscle-energy modes of the human hand (only ten modes in
this paper) map massive tasks of bionic hand.