OBJECTIVE: Real-time measurement of biological joint moment could enhance clinical assessments and generalize exoskeleton control. Accessing joint moments outside clinical and laboratory settings requires harnessing non-invasive wearable sensor data for indirect estimation. Previous approaches have been primarily validated during cyclic tasks, such as walking, but these methods are likely limited when translating to non-cyclic tasks where the mapping from kinematics to moments is not unique. METHODS: We trained deep learning models to estimate hip and knee joint moments from kinematic sensors, electromyography (EMG), and simulated pressure insoles from a dataset including 10 cyclic and 18 non-cyclic activities. We assessed estimation error on combinations of sensor modalities during both activity types. RESULTS: Compared to the kinematics-only baseline, adding EMG reduced RMSE by 16.9% at the hip and 30.4% at the knee (p<0.05) and adding insoles reduced RMSE by 21.7% at the hip and 33.9% at the knee (p<0.05). Adding both modalities reduced RMSE by 32.5% at the hip and 41.2% at the knee (p<0.05) which was significantly higher than either modality individually (p<0.05). All sensor additions improved model performance on non-cyclic tasks more than cyclic tasks (p<0.05). CONCLUSION: These results demonstrate that adding kinetic sensor information through EMG or insoles improves joint moment estimation both individually and jointly. These additional modalities are most important during non-cyclic tasks, tasks that reflect the variable and sporadic nature of the real-world. SIGNIFICANCE: Improved joint moment estimation and task generalization is pivotal to developing wearable robotic systems capable of enhancing mobility in everyday life.
Robotic lower-limb exoskeletons can augment human mobility, but current systems require extensive, context-specific considerations, limiting their real-world viability. Here, we present a unified exoskeleton control framework that autonomously adapts assistance on the basis of instantaneous user joint moment estimates from a temporal convolutional network (TCN). When deployed on our hip exoskeleton, the TCN achieved an average root mean square error of 0.142 newton-meters per kilogram across 35 ambulatory conditions without any user-specific calibration. Further, the unified controller significantly reduced user metabolic cost and lower-limb positive work during level-ground and incline walking compared with walking without wearing the exoskeleton. This advancement bridges the gap between in-lab exoskeleton technology and real-world human ambulation, making exoskeleton control technology viable for a broad community.
Exoskeleton Device , Robotics , Humans , Biomechanical Phenomena , Walking , Lower Extremity
Autonomous lower-limb exoskeletons must modulate assistance based on locomotion mode (e.g., ramp or stair ascent) to adapt to the corresponding changes in human biological joint dynamics. However, current mode classification strategies for exoskeletons often require user-specific tuning, have a slow update rate, and rely on additional sensors outside of the exoskeleton sensor suite. In this study, we introduce a deep convolutional neural network-based locomotion mode classifier for hip exoskeleton applications using an open-source gait biomechanics dataset with various wearable sensors. Our approach removed the limitations of previous systems as it is 1) subject-independent (i.e., no user-specific data), 2) capable of continuously classifying for smooth and seamless mode transitions, and 3) only utilizes minimal wearable sensors native to a conventional hip exoskeleton. We optimized our model, based on several important factors contributing to overall performance, such as transition label timing, model architecture, and sensor placement, which provides a holistic understanding of mode classifier design. Our optimized DL model showed a 3.13% classification error (steady-state: 0.80 ± 0.38% and transitional: 6.49 ± 1.42%), outperforming other machine learning-based benchmarks commonly practiced in the field (p<0.05). Furthermore, our multi-modal analysis indicated that our model can maintain high performance in different settings such as unseen slopes on stairs or ramps. Thus, our study presents a novel locomotion mode framework, capable of advancing robotic exoskeleton applications toward assisting community ambulation.
Exoskeleton Device , Robotic Surgical Procedures , Gait , Humans , Locomotion , Walking
Step length is a critical gait parameter that allows a quantitative assessment of gait asymmetry. Gait asymmetry can lead to many potential health threats such as joint degeneration, difficult balance control, and gait inefficiency. Therefore, accurate step length estimation is essential to understand gait asymmetry and provide appropriate clinical interventions or gait training programs. The conventional method for step length measurement relies on using foot-mounted inertial measurement units (IMUs). However, this may not be suitable for real-world applications due to sensor signal drift and the potential obtrusiveness of using distal sensors. To overcome this challenge, we propose a deep convolutional neural network-based step length estimation using only proximal wearable sensors (hip goniometer, trunk IMU, and thigh IMU) capable of generalizing to various walking speeds. To evaluate this approach, we utilized treadmill data collected from sixteen able-bodied subjects at different walking speeds. We tested our optimized model on the overground walking data. Our CNN model estimated the step length with an average mean absolute error of 2.89 ± 0.89 cm across all subjects and walking speeds. Since wearable sensors and CNN models are easily deployable in real-time, our study findings can provide personalized real-time step length monitoring in wearable assistive devices and gait training programs.
Walking , Wearable Electronic Devices , Gait , Humans , Neural Networks, Computer , Walking Speed
We developed and validated a gait phase estimator for real-time control of a robotic hip exoskeleton during multimodal locomotion. Gait phase describes the fraction of time passed since the previous gait event, such as heel strike, and is a promising framework for appropriately applying exoskeleton assistance during cyclic tasks. A conventional method utilizes a mechanical sensor to detect a gait event and uses the time since the last gait event to linearly interpolate the current gait phase. While this approach may work well for constant treadmill walking, it shows poor performance when translated to overground situations where the user may change walking speed and locomotion modes dynamically. To tackle these challenges, we utilized a convolutional neural network-based gait phase estimator that can adapt to different locomotion mode settings to modulate the exoskeleton assistance. Our resulting model accurately predicted the gait phase during multimodal locomotion without any additional information about the user's locomotion mode, with a gait phase estimation RMSE of 5.04 ± 0.79%, significantly outperforming the literature standard (p < 0.05). Our study highlights the promise of translating exoskeleton technology to more realistic settings where the user can naturally and seamlessly navigate through different terrain settings.
The solid waste collection industry is one of the most common occupations resulting in low back pain (LBP). Lumbar peak joint reaction forces and peak and integrated moments are strong correlates of LBP. To investigate these risks, this study compared three common waste collection throwing techniques of varying lumbar symmetry: the symmetric (SYM) technique, the asymmetric fixed stance (AFS) technique, and the asymmetric with pivot (AWP) technique. Lumbar moments and joint reaction loads were computed for throwing garbage bags of 3, 7, and 11 kg to quantify the effects that technique and object weight have on LBP risk. LBP risk factors were computed using a full-body musculoskeletal model in OpenSim. Muscle activations were estimated using two methods: the EMG-assisted method, which included electromyography data in the solution, and the conventional static optimization method, which did not. The EMG-assisted method more accurately reproduced measured muscle activation, resulting in significantly larger peak compressive and shear forces (p < 0.05) of magnitudes indicative of LBP risk. Risk factors associated with the SYM technique were either larger or not statistically different compared to the asymmetric techniques for the 3 kg condition; however, the opposite result occurred for the 7 and 11 kg conditions (p < 0.05). These results suggest using rapid, asymmetric techniques when handling lightweight objects and slower, symmetric techniques for heavier objects to reduce LBP risk during waste collection throwing techniques. Results indicating increased risk between asymmetric techniques were mostly inconclusive. As expected, increasing bag mass generally increased LBP risk factors, regardless of technique (p < 0.05).
Muscle, Skeletal , Solid Waste , Biomechanical Phenomena , Electromyography , Humans , Lumbar Vertebrae , Movement , Occupational Health
Human augmentation through robotic exoskeleton technology can enhance the user's mobility for a wide range of ambulation tasks. This is done by providing assistance that is in line with the user's movement during different locomotion modes (e.g., ramps and stairs). Several machine learning techniques have been applied to classify such tasks on lower limb prostheses, but these strategies have not been applied extensively to exoskeleton systems which often rely on similar control inputs. Additionally, conventional methods often identify modes at a discrete time during the gait cycle which can delay the corresponding assistance to the user and potentially reduce overall exoskeleton benefit. We developed a gait phase-based Bayesian classifier that can classify five ambulation modes continuously throughout the gait cycle using only mechanical sensors on the device. From our five able-bodied subject experiment with a robotic hip exoskeleton, we found that implementing multiple models within the gait cycle can reduce the classification error rate by 35% compared to using a single model (p < 0.05). Furthermore, we found that utilizing bilateral sensor information can reduce the error by 43% compared to using a unilateral information (p < 0.05). Our study findings provide valuable information for future exoskeleton developers to utilize different on-board mechanical sensors to enhance mode classification for a faster update rate in the controller and provide more natural and seamless exoskeleton assistance between locomotion modes.
Machine learning (ML) algorithms present an opportunity to estimate joint kinetics using a limited set of mechanical sensors. These estimates could be used as a continuous reference signal for exoskeleton control, able to modulate exoskeleton assistance in real-world environments. In this study, sagittal plane biological hip torque during level ground, incline and decline walking was calculated using inverse dynamics of human subject data. Subsequently, this torque was estimated using neural network (NN) and XGBoost ML models. Model inputs consisted solely of mechanical sensor data onboard a robotic hip exoskeleton. These results were compared to a baseline method of estimating hip torque as the mean torque profile during ambulation. On average across conditions, the NN and XGBoost models estimated biological hip torque with an RMSE of 0.116±0.015 and 0.108±0.011 Nm/kg, respectively, which was significantly less than the baseline estimation that had an RMSE of 0.300±0.145 Nm/kg (p<0.05). Fitting the baseline method to ambulation mode specific data significantly reduced overall RMSE by 59.3%; however, the ML models were still significantly better than the baseline method (p<0.05). These results show that machine learning algorithms can estimate biological hip torque using only mechanical sensors onboard a hip exoskeleton better than simply using an average torque profile. This suggests that these estimation models could be suitable for modulating exoskeleton assistance. Additionally, no evidence suggested the need to train separate ML models for each ambulation mode as estimation RMSE was not significantly different across unified and separated ML models.
