Delaying ambulation mode transitions in a powered knee-ankle prosthesis

Abstract

Powered knee and ankle prostheses have the potential to improve the mobility of individuals with a lower limb amputation. As the number of different ambulation modes the prosthesis can be configured for increases, so too does the challenge of how to best transition the prosthesis between these modes. Pattern recognition systems have been suggested as a means to provide seamless and natural transitions, although error rates need to be reduced for these systems to be clinical viable. Delaying mode transitions by a small window may be one way to reduce error rates and improve reliability. The goal of this study was to develop and test a system for powered lower limb prostheses that introduced a delay between mode transitions. Three transfemoral amputees used a knee-ankle prosthesis to stand, walk on level ground, ascend/descend a ramp, and ascend/descend stairs. On Day 1 mode transitions occurred at a gait event (e.g., heel contact), and on Day 2 mode transitions occurred 90 ms following a gait event. A mode-specific pattern recognition system was trained and tested on each day. The 90 ms transition delay did not negatively affect users’ performance ambulating with the prosthesis. Offline classification error results showed that the 90 ms delay reduced overall classification errors from 1.30% [0.29%], mean [SD], for the non-delayed system to 0.42% [0.22%] for the delayed system. These results demonstrate that delaying mode transitions by a small window of time can reduce overall errors, which moves these systems one step closer to clinical viability.

Online adaptive neural control of a robotic lower limb prosthesis

“…Mechanical sensors thresholds were chosen so that mode transitions were triggered in a seamless way without any unnecessary or unnatural movement required by the user. More information about the definition of these gait events and how they were determined from the data can be found in our previous studies [27], [32], [33]. Collecting additional data after the gait event has been shown to improve pattern recognition performance in offline studies [25], [27], and transitioning between modes at this time point did not hinder the subjects’ ability to use the prosthesis.…”

“…First, the robotic prosthesis used in the present study was equipped with additional mechanical sensors [2,5], thus more sensor information was input into our forward prediction algorithm [24]. Second, various studies have investigated defining a critical timing window for mode transitions and found that delaying the timing of these transitions by a small window lowered the error rates of the forward prediction algorithm [25][26][27]. Thus we implemented this delay for the online experiments described in this study.…”

Delaying Ambulation Mode Transition Decisions Improves Accuracy of a Flexible Control System for Powered Knee-Ankle Prosthesis

“…In order to investigate both a delayed mode transition system and a non-delayed mode transition system, steady-state and between-mode transitions were delayed by 90 ms during data collection. Pilot tests revealed that users' performance and stability was not affected by delaying these transitions by 90 ms [27]. The tasks included:

a circuit of level-ground walking approaches to and from ramp ascent and descent on a 10 degree inclined surface and stair ascent and descent on either a 4-step staircase (10 trials) or a 3-step staircase (10 trials);

climbing stairs in a stairwell (4 flights);

climbing up two steps, standing, climbing up two steps, standing, turning around, descending the steps in the same manner (20 trials);

walking at various speeds, straight-line walking, and walking in circles (10 trials total); and

standing including shuffle steps, turning, and quiet standing (5 trials).

…”

Machine Learning Approaches for Activity Recognition and/or Activity Prediction in Locomotion Assistive Devices—A Systematic Review

“…More recently, some researchers did not use analysis windows which ended at classic gait events like foot contact but instead allowed for a delay in the termination of the analysis window. For example, Simon et al [37,69] had an analysis window which ended 90ms after foot contact or foot off. This delay increased the accuracy of a DBN algorithm and did not affect the stability of the users of a powered above-knee prosthesis.…”