Detection of critical errors of locomotion mode recognition for volitional control of powered transfemoral prostheses

Combination of intrinsic control and volitional control that recognizes the user's locomotion mode (LM) has been applied to powered prosthetic legs, which enables lower limb amputees to adapt to varying terrains seamlessly. However, errors in volitional control may disrupt the user's walking balance. This study aimed to determine whether the critical errors in volitional control could be detected before they disturbed the user's walking. The positive answer might lead to more robust volitional control for powered prosthetic legs. To achieve this goal, volitional control and intrinsic control were connected hierarchically to operate a powered transfemoral prosthesis. Critical errors for recognizing the user's LM were introduced artificially when transfemoral amputees walked with the powered prosthesis. Intrinsic measurements from the prosthesis were explored first in order to select effective data sources for error detection. Then a phase-dependent outlier detector was designed and offline evaluated. The results demonstrated that the designed detector can detect the tested critical errors with a high sensitivity and a low false alarm ratio before the errors disrupted the amputees' balance. Additional engineering efforts were still necessary to test the detector on more error types and design a control strategy that can make volitional control of powered lower limb prosthesis robust and safe to use.