Locomotion Decoding ( LocoD ): An Open‐Source and Modular Platform for Researching Control Algorithms for Lower Limb Assistive Devices

Background and Objective Commercially available motorized prosthetic legs use exclusively nonbiological signals to control movements, such as those provided by load cells, pressure sensors, and inertial measurement units (IMUs). Although the use of biological signals of neuromuscular origin can provide more natural control of leg prostheses, these signals cannot yet be captured and decoded reliably enough to be used in daily life. Indeed, decoding motor intention from bioelectric signals obtained from the residual limb holds great potential, and therefore, the study of decoding algorithms has increased in the past years, with standardized methods lacking. Methods In the absence of shared tools to record and process lower limb bioelectric signals, such as electromyography (EMG), we developed an open‐source software platform to unify the recording and processing (preprocessing, feature extraction, and classification) of EMG and nonbiological signals amongst researchers with the goal of investigating and benchmarking control algorithms. We validated our locomotion decoding (LocoD) software by comparing the accuracy in the classification of locomotion mode using three different combinations of sensors (1 = IMU + pressure sensor + EMG, 2 = EMG, 3 = IMU + pressure sensor). EMG and nonbiological signals (from the IMU and pressure sensor) were recorded while able‐bodied participants ( n = 21) walked on different surfaces, such as stairs and ramps, and this data set is also released publicly along with this publication. LocoD was used for all recording, preprocessing, feature extraction, and classification of the recorded signals. We tested the statistical hypothesis that there was a difference in predicted locomotion mode accuracy between sensor combinations using the Wilcoxon signed‐rank test. Results We found that the sensor combination 1 (IMU + pressure sensor + EMG) led to significantly more accurate and improved locomotion mode prediction (Accuracy = 93.4 ± 3.9) than using EMG (Accuracy = 74.56 ± 5.8) or IMU + pressure sensor alone (Accuracy = 90.77 ± 4.6) with p ‐value <0.001. Conclusions In this study, we introduced and validated the functionality of LocoD as an open‐source and modular platform to research control algorithms for prosthetic legs that incorporate bioelectric signals.