Improving the performance of a neural-machine interface for artificial legs using prior knowledge of walking environment

Abstract

A previously developed neural-machine interface (NMI) based on neuromuscular-mechanical fusion has showed promise for recognizing user locomotion modes; however, errors of NMI during mode transitions were observed, which may challenge its real application. This study aimed to investigate whether or not the prior knowledge of walking environment could further improve the NMI performance. Linear Discriminant Analysis (LDA)-based classifiers were designed to identify user intent based on electromyographic (EMG) signals from residual muscles of leg amputees and ground reaction force (GRF) measured from the prosthetic leg. The prior knowledge of the terrain in front of the user adjusted the prior possibility in the discriminant function. Therefore, the boundaries of LDA were adaptive to the prior knowledge of the walking environment. This algorithm was evaluated on a dataset collected from one patient with a transfemoral (TF) amputation. The preliminary results showed that the NMI with adaptive prior possibilities outperformed the NMI without using the prior knowledge; it produced 98.7% accuracy for identifying tested locomotion modes, accurately predicted all the task transitions with 261–390 ms prediction time, and generated stable decision during task transitions. These results indicate the potential of using prior knowledge about walking environment to further improve the NMI for prosthetic legs.

ExoNet Database: Wearable Camera Images of Human Locomotion Environments

“…Inspired by previous work (Du et al, 2012; Huang et al, 2011; Khademi and Simon, 2019; Liu et al, 2016; Wang et al, 2013), the hierarchical labelling architecture included both static (S) and transition (T) states. A static state describes an environment where an exoskeleton or prosthesis user would continuously perform the same locomotion mode (e.g., only level-ground terrain).…”

“…Several researchers have combined mechanical sensors with surface EMG for automated locomotion mode recognition. Such neuromuscular-mechanical data fusion has improved the locomotion mode recognition accuracies and decision times compared to implementing either system individually (Du et al, 2012; Huang et al, 2011; Liu et al, 2016; Wang et al, 2013). However, these measurements are still patient-dependent, and surface EMG are susceptible to fatigue, changes in electrode-skin conductivity, and crosstalk from adjacent muscles (Tucker et al, 2015).…”

“…Environment sensing can also be used to adapt low-level reference trajectories (e.g., changing toe clearance corresponding to an obstacle height) (Zhang et al, 2020) and optimal path planning (e.g., identifying opportunities for energy regeneration) (Laschowski et al, 2019a; 2020a). Preliminary research has shown that supplementing a locomotion mode recognition system with environment information can improve the classification accuracies and decision times compared to excluding terrain information (Huang et al, 2011; Liu et al, 2016; Wang et al, 2013). Several researchers have explored using radar detectors (Kleiner et al, 2018) and laser rangefinders (Liu et al, 2016; Wang et al, 2013; Zhang et al, 2011) for environment sensing.…”

ExoNet Database: Wearable Camera Images of Human Locomotion Environments

“…Several researchers have combined mechanical sensors with surface EMG for automated locomotion mode recognition. Such neuromuscular-mechanical data fusion has improved the locomotion mode recognition accuracies and decision times compared to implementing either system individually (Huang et al, 2011;Du et al, 2012;Wang et al, 2013;Liu et al, 2016). However, these measurements are still patient-dependent, and surface EMG are susceptible to fatigue, changes in electrode-skin conductivity, and crosstalk from adjacent muscles (Tucker et al, 2015).…”

“…Environment sensing could also be used to adapt low-level reference trajectories (e.g., changing toe clearance corresponding to an obstacle height) (Zhang et al, 2020) and optimal path planning (e.g., identifying opportunities for energy regeneration) (Laschowski et al, 2019a(Laschowski et al, , 2020a. Preliminary research has shown that supplementing an automated locomotion mode recognition system with environment information can improve the classification accuracies and decision times compared to excluding terrain information (Huang et al, 2011;Wang et al, 2013;Liu et al, 2016). Several researchers have explored using radar detectors (Kleiner et al, 2018) and laser rangefinders (Zhang et al, 2011;Wang et al, 2013;Liu et al, 2016) for environment sensing.…”