Across-user adaptation for a powered lower limb prosthesis

Machine Learning-Based Gait Mode Prediction for Hybrid Knee Prosthesis Control

Recently, hybrid prosthetic knees, which can combine the advantages of passive and active prosthetic knees, have been proposed for individuals with a transfemoral amputation. Users could potentially take advantage of the passive knee mechanics during walking and the active power generation during stair ascent. One challenge in controlling the hybrid knees is accurate gait mode prediction for seamless transitions between passive and active modes. However, data imbalance between passive and active modes may impact the performance of a classifier. In this study, we used a dataset collected from nine individuals with a unilateral transfemoral amputation as they ambulated over level ground, inclines, and stairs. We evaluated several machine learning-based classifiers on the prediction of passive (level-ground walking, incline walking, descending stairs, and donning and doffing the prosthesis) and active mode (ascending stairs). In addition, we developed a generative adversarial network (GAN) to create synthetic data for improving classification performance. The results indicated that linear discriminant analysis and random forest might be the best classifiers regarding sensitivity to the active mode and overall accuracy, respectively. Further, we demonstrated that using the GAN-based synthetic data for training improves the sensitivity of classifiers.

Ambulation Mode Classification of Individuals with Transfemoral Amputation through A-Mode Sonomyography and Convolutional Neural Networks

Many people struggle with mobility impairments due to lower limb amputations. To participate in society, they need to be able to walk on a wide variety of terrains, such as stairs, ramps, and level ground. Current lower limb powered prostheses require different control strategies for varying ambulation modes, and use data from mechanical sensors within the prosthesis to determine which ambulation mode the user is in. However, it can be challenging to distinguish between ambulation modes. Efforts have been made to improve classification accuracy by adding electromyography information, but this requires a large number of sensors, has a low signal-to-noise ratio, and cannot distinguish between superficial and deep muscle activations. An alternative sensing modality, A-mode ultrasound, can detect and distinguish between changes in superficial and deep muscles. It has also shown promising results in upper limb gesture classification. Despite these advantages, A-mode ultrasound has yet to be employed for lower limb activity classification. Here we show that A- mode ultrasound can classify ambulation mode with comparable, and in some cases, superior accuracy to mechanical sensing. In this study, seven transfemoral amputee subjects walked on an ambulation circuit while wearing A-mode ultrasound transducers, IMU sensors, and their passive prosthesis. The circuit consisted of sitting, standing, level-ground walking, ramp ascent, ramp descent, stair ascent, and stair descent, and a spatial-temporal convolutional network was trained to continuously classify these seven activities. Offline continuous classification with A-mode ultrasound alone was able to achieve an accuracy of 91.8±3.4%, compared with 93.8±3.0%, when using kinematic data alone. Combined kinematic and ultrasound produced 95.8±2.3% accuracy. This suggests that A-mode ultrasound provides additional useful information about the user's gait beyond what is provided by mechanical sensors, and that it may be able to improve ambulation mode classification. By incorporating these sensors into powered prostheses, users may enjoy higher reliability for their prostheses, and more seamless transitions between ambulation modes.

Real-Time Adaptation of an Artificial Neural Network for Transfemoral Amputees using a Powered Prosthesis

OBJECTIVE

We evaluated a two-step method to improve control accuracy for a powered prosthetic leg using machine learning and adaptation, while reducing subject training time.

METHODS

First, information from three transfemoral amputees was grouped together, to create a baseline control system that was subsequently tested using data from a fourth subject (user-independent classification). Second, online adaptation was investigated, whereby the fourth subjects data were used to improve the baseline control system in real-time. Results were compared for user-independent classification and for user-dependent classification (data collected from and tested in the same subject), with and without adaptation.

RESULTS

The combination of a user-independent classifier with real-time adaptation based on a unique individuals data produced a classification error rate as low as 1.61% [0.15 standard error of the mean (SEM)] without requiring collection of initial training data from that individual. Training/testing using a subjects own data (user-dependent classification), combined with adaptation, resulted in a classification error rate of 0.9% [0.12 SEM], which was not significantly different (P > 0.05) but required, on average, an additional 7.52 hours [0.92 SEM] of training sessions.

CONCLUSION AND SIGNIFICANCE

We found that the combination of a user-independent dataset with adaptation resulted in error rates that were not significantly different from using a user-dependent dataset. Furthermore, this method eliminated the need for individual training sessions, saving many hours of data collection time.

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

Locomotion assistive devices equipped with a microprocessor can potentially automatically adapt their behavior when the user is transitioning from one locomotion mode to another. Many developments in the field have come from machine learning driven controllers on locomotion assistive devices that recognize/predict the current locomotion mode or the upcoming one. This review synthesizes the machine learning algorithms designed to recognize or to predict a locomotion mode in order to automatically adapt the behavior of a locomotion assistive device. A systematic review was conducted on the Web of Science and MEDLINE databases (as well as in the retrieved papers) to identify articles published between 1 January 2000 to 31 July 2020. This systematic review is reported in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines and is registered on Prospero (CRD42020149352). Study characteristics, sensors and algorithms used, accuracy and robustness were also summarized. In total, 1343 records were identified and 58 studies were included in this review. The experimental condition which was most often investigated was level ground walking along with stair and ramp ascent/descent activities. The machine learning algorithms implemented in the included studies reached global mean accuracies of around 90%. However, the robustness of those algorithms seems to be more broadly evaluated, notably, in everyday life. We also propose some guidelines for homogenizing future reports.

Autonomous multi-joint soft exosuit with augmentation-power-based control parameter tuning reduces energy cost of loaded walking

BACKGROUND

Soft exosuits are a recent approach for assisting human locomotion, which apply assistive torques to the wearer through functional apparel. Over the past few years, there has been growing recognition of the importance of control individualization for such gait assistive devices to maximize benefit to the wearer. In this paper, we present an updated version of autonomous multi-joint soft exosuit, including an online parameter tuning method that customizes control parameters for each individual based on positive ankle augmentation power.

METHODS

The soft exosuit is designed to assist with plantarflexion, hip flexion, and hip extension while walking. A mobile actuation system is mounted on a military rucksack, and forces generated by the actuation system are transmitted via Bowden cables to the exosuit. The controller performs an iterative force-based position control of the Bowden cables on a step-by-step basis, delivering multi-articular (plantarflexion and hip flexion) assistance during push-off and hip extension assistance in early stance. To individualize the multi-articular assistance, an online parameter tuning method was developed that customizes two control parameters to maximize the positive augmentation power delivered to the ankle. To investigate the metabolic efficacy of the exosuit with wearer-specific parameters, human subject testing was conducted involving walking on a treadmill at 1.50 m s- 1 carrying a 6.8-kg loaded rucksack. Seven participants underwent the tuning process, and the metabolic cost of loaded walking was measured with and without wearing the exosuit using the individualized control parameters.

RESULTS

The online parameter tuning method was capable of customizing the control parameters, creating a positive ankle augmentation power map for each individual. The subject-specific control parameters and resultant assistance profile shapes varied across the study participants. The exosuit with the wearer-specific parameters significantly reduced the metabolic cost of load carriage by 14.88 ± 1.09% (P = 5 × 10- 5) compared to walking without wearing the device and by 22.03 ± 2.23% (P = 2 × 10- 5) compared to walking with the device unpowered.

CONCLUSION

The autonomous multi-joint soft exosuit with subject-specific control parameters tuned based on positive ankle augmentation power demonstrated the ability to improve human walking economy. Future studies will further investigate the effect of the augmentation-power-based control parameter tuning on wearer biomechanics and energetics.