Tolerance of neural decoding errors for powered artificial legs: A pilot study

Neural-machine interface (NMI) decoding errors challenge the clinical value of neural control of powered artificial legs, because these errors can dangerously disturb the user's walking balance, cause stumbles or falls, and thus threaten the user's confidence and safety in prosthesis use. Although extensive research efforts have been made to minimize the NMI decoding error rate, none of the current approaches can completely eliminate the errors in NMI. This study aimed at improving the robustness of prosthesis control system against neural decoding errors by introducing a fault-tolerant control (FTC) strategy. A novel reconfiguration mechanism, combined with our previously developed NMI decoding error detector, was designed and implemented into our prototypical powered knee prosthesis. The control system with FTC was preliminarily tested on two transfemoral amputees when they walked with the powered prosthesis on different walking terrains. Various NMI errors were simulated when the FTC was enabled and disabled. The preliminary testing results indicated that the FTC strategy was capable of effectively counteracting the disruptive effects of simulated decoding errors by reducing the mechanical work change around the prosthetic knee joint elicited by the NMI error. The outcomes of this study may provide a potential engineering solution to make the neural control of powered artificial legs safer to use.