A Model-Based Analysis of Supraspinal Mechanisms of Inter-Leg Coordination in Human Gait: Toward Model-Informed Robot-Assisted Rehabilitation

Estimation of Muscle Forces of Lower Limbs Based on CNN-LSTM Neural Network and Wearable Sensor System

Estimation of vivo muscle forces during human motion is important for understanding human motion control mechanisms and joint mechanics. This paper combined the advantages of the convolutional neural network (CNN) and long-short-term memory (LSTM) and proposed a novel muscle force estimation method based on CNN-LSTM. A wearable sensor system was also developed to collect the angles and angular velocities of the hip, knee, and ankle joints in the sagittal plane during walking, and the collected kinematic data were used as the input for the neural network model. In this paper, the muscle forces calculated using OpenSim based on the Static Optimization (SO) method were used as the standard value to train the neural network model. Four lower limb muscles of the left leg, including gluteus maximus (GM), rectus femoris (RF), gastrocnemius (GAST), and soleus (SOL), were selected as the studying objects in this paper. The experiment results showed that compared to the standard CNN and the standard LSTM, the CNN-LSTM performed better in muscle forces estimation under slow (1.2 m/s), medium (1.5 m/s), and fast walking speeds (1.8 m/s). The average correlation coefficients between true and estimated values of four muscle forces under slow, medium, and fast walking speeds were 0.9801, 0.9829, and 0.9809, respectively. The average correlation coefficients had smaller fluctuations under different walking speeds, which indicated that the model had good robustness. The external testing experiment showed that the CNN-LSTM also had good generalization. The model performed well when the estimated object was not included in the training sample. This article proposed a convenient method for estimating muscle forces, which could provide theoretical assistance for the quantitative analysis of human motion and muscle injury. The method has established the relationship between joint kinematic signals and muscle forces during walking based on a neural network model; compared to the SO method to calculate muscle forces in OpenSim, it is more convenient and efficient in clinical analysis or engineering applications.

Using robot-assisted stiffness perturbations to evoke aftereffects useful to post-stroke gait rehabilitation

Stroke is a major global issue, affecting millions every year. When a stroke occurs, survivors are often left with physical disabilities or difficulties, frequently marked by abnormal gait. Post-stroke gait normally presents as one of or a combination of unilaterally shortened step length, decreased dorsiflexion during swing phase, and decreased walking speed. These factors lead to an increased chance of falling and an overall decrease in quality of life due to a reduced ability to locomote quickly and safely under one's own power. Many current rehabilitation techniques fail to show lasting results that suggest the potential for producing permanent changes. As technology has advanced, robot-assisted rehabilitation appears to have a distinct advantage, as the precision and repeatability of such an intervention are not matched by conventional human-administered therapy. The possible role in gait rehabilitation of the Variable Stiffness Treadmill (VST), a unique, robotic treadmill, is further investigated in this paper. The VST is a split-belt treadmill that can reduce the vertical stiffness of one of the belts, while the other belt remains rigid. In this work, we show that the repeated unilateral stiffness perturbations created by this device elicit an aftereffect of increased step length that is seen for over 575 gait cycles with healthy subjects after a single 10-min intervention. These long aftereffects are currently unmatched in the literature according to our knowledge. This step length increase is accompanied by kinematics and muscle activity aftereffects that help explain functional changes and have their own independent value when considering the characteristics of post-stroke gait. These results suggest that repeated unilateral stiffness perturbations could possibly be a useful form of post-stroke gait rehabilitation.

Deep reinforcement learning for modeling human locomotion control in neuromechanical simulation

Modeling human motor control and predicting how humans will move in novel environments is a grand scientific challenge. Researchers in the fields of biomechanics and motor control have proposed and evaluated motor control models via neuromechanical simulations, which produce physically correct motions of a musculoskeletal model. Typically, researchers have developed control models that encode physiologically plausible motor control hypotheses and compared the resulting simulation behaviors to measurable human motion data. While such plausible control models were able to simulate and explain many basic locomotion behaviors (e.g. walking, running, and climbing stairs), modeling higher layer controls (e.g. processing environment cues, planning long-term motion strategies, and coordinating basic motor skills to navigate in dynamic and complex environments) remains a challenge. Recent advances in deep reinforcement learning lay a foundation for modeling these complex control processes and controlling a diverse repertoire of human movement; however, reinforcement learning has been rarely applied in neuromechanical simulation to model human control. In this paper, we review the current state of neuromechanical simulations, along with the fundamentals of reinforcement learning, as it applies to human locomotion. We also present a scientific competition and accompanying software platform, which we have organized to accelerate the use of reinforcement learning in neuromechanical simulations. This “Learn to Move” competition was an official competition at the NeurIPS conference from 2017 to 2019 and attracted over 1300 teams from around the world. Top teams adapted state-of-the-art deep reinforcement learning techniques and produced motions, such as quick turning and walk-to-stand transitions, that have not been demonstrated before in neuromechanical simulations without utilizing reference motion data. We close with a discussion of future opportunities at the intersection of human movement simulation and reinforcement learning and our plans to extend the Learn to Move competition to further facilitate interdisciplinary collaboration in modeling human motor control for biomechanics and rehabilitation research