Xuefeng Bao’s research while affiliated with University of Wisconsin–Milwaukee and other places

The role of the human ankle joint in activities of daily living, including walking, maintaining balance, and participating in sports, is of paramount importance. Ankle joint dorsiflexion and plantarflexion functionalities mainly account for ground clearance and propulsion power generation during locomotion tasks, where those functionalities are driven by the contraction of ankle joint skeleton muscles. Studies of corresponding muscle contractility during ankle dynamic functions will facilitate us to better understand the joint torque/power generation mechanism, better diagnose potential muscular disorders on the ankle joint, or better develop wearable assistive/rehabilitative robotic devices that assist in community ambulation. This data descriptor reports a new dataset that includes the ankle joint kinematics/kinetics, associated muscle surface electromyography, and ultrafast ultrasound images with various annotations, such as pennation angle, fascicle length, tissue displacements, echogenicity, and muscle thickness, of ten healthy participants when performing volitional isometric, isokinetic, and dynamic ankle joint functions (walking at multiple treadmill speeds, including 0.50 m/s, 0.75 m/s, 1.00 m/s, 1.25 m/s, and 1.50 m/s). Data were recorded by a research-use ultrasound machine, a self-designed ankle testbed, an inertia measurement unit system, a Vicon motion capture system, a surface electromyography system, and an instrumented treadmill. The descriptor in this work presents the results of a data curation or collection exercise from previous works, rather than describing a novel primary/experimental data collection.

This article presents an assist-as-needed (AAN) control framework for exoskeleton assistance based on human volitional effort prediction via a Hill-type neuromuscular model. A sequential processing algorithm-based multirate observer is applied to continuously estimate muscle activation levels by fusing surface electromyography (sEMG) and ultrasound (US) echogenicity signals from the ankle muscles. An adaptive impedance controller manipulates the exoskeleton's impedance for a more natural behavior by following a desired intrinsic impedance model. Two neural networks provide robustness to uncertainties in the overall ankle joint-exoskeleton model and the prediction error in the volitional ankle joint torque. A rigorous Lyapunov-based stability analysis proves that the AAN control framework achieves uniformly ultimately bounded tracking for the overall system. Experimental studies on five participants with no neurological disabilities walking on a treadmill validate the effectiveness of the designed ankle exoskeleton and the proposed AAN approach. Results illustrate that the AAN control approach with fused sEMG and US echogenicity signals maintained a higher human volitional effort prediction accuracy, less ankle joint trajectory tracking error, and less robotic assistance torque than the AAN approach with the sEMG-based volitional effort prediction alone. The findings support our hypotheses that the proposed controller increases human motion intent prediction accuracy, improves the exoskeleton's control performance, and boosts voluntary participation from human subjects. The new framework potentially paves a foundation for using multimodal biological signals to control rehabilitative or assistive robots.

B-mode ultrasound (US) is often used to noninvasively measure skeletal muscle architecture, which contains human intent information. Extracted features from B-mode images can help improve closed-loop human–robotic interaction control when using rehabilitation/assistive devices. The traditional manual approach to inferring the muscle structural features from US images is laborious, time-consuming, and subjective among different investigators. This paper proposes a clustering-based detection method that can mimic a well-trained human expert in identifying fascicle and aponeurosis and, therefore, compute the pennation angle. The clustering-based architecture assumes that muscle fibers have tubular characteristics. It is robust for low-frequency image streams. We compared the proposed algorithm to two mature benchmark techniques: UltraTrack and ImageJ. The performance of the proposed approach showed higher accuracy in our dataset (frame frequency is 20 Hz), that is, similar to the human expert. The proposed method shows promising potential in automatic muscle fascicle orientation detection to facilitate implementations in biomechanics modeling, rehabilitation robot control design, and neuromuscular disease diagnosis with low-frequency data stream.

Robotic assistive or rehabilitative devices are promising aids for people with neurological disorders as they help regain normative functions for both upper and lower limbs. However, it remains challenging to accurately estimate human intent or residual efforts non-invasively when using these robotic devices. In this article, we propose a deep learning approach that uses a brightness mode, that is, B-mode, of ultrasound (US) imaging from skeletal muscles to predict the ankle joint net plantarflexion moment while walking. The designed structure of customized deep convolutional neural networks (CNNs) guarantees the convergence and robustness of the deep learning approach. We investigated the influence of the US imaging’s region of interest (ROI) on the net plantarflexion moment prediction performance. We also compared the CNN-based moment prediction performance utilizing B-mode US and sEMG spectrum imaging with the same ROI size. Experimental results from eight young participants walking on a treadmill at multiple speeds verified an improved accuracy by using the proposed US imaging + deep learning approach for net joint moment prediction. With the same CNN structure, compared to the prediction performance by using sEMG spectrum imaging, US imaging significantly reduced the normalized prediction root mean square error by 37.55% ( p < .001) and increased the prediction coefficient of determination by 20.13% ( p < .001). The findings show that the US imaging + deep learning approach personalizes the assessment of human joint voluntary effort, which can be incorporated with assistive or rehabilitative devices to improve clinical performance based on the assist-as-needed control strategy.

In this paper, we proposed an assist-as-needed (AAN) control strategy that incorporated the continuous volition ankle joint torque prediction for a cable-driven ankle exoskeleton. The volitional torque was predicted via an sEMG-US imaging-driven Hill-type neuromuscular model (HNM) with the shank muscle activation estimation by fusing sEMG and US imaging signals. This volitional torque prediction was embedded in an adaptive impedance control (AIC) framework to facilitate the AAN control. The AIC algorithm tracks a reference impedance model and automatically adjusts the assistance from a cable-driven ankle exoskeleton. Experimental studies of three participants with no disabilities walking on a treadmill were conducted to verify the effectiveness of the proposed AIC approach. Results showed that the AIC approach maintained an accurate trajectory tracking while providing compliant assistance from the exoskeleton as it responded in real-time to impedance changes.

A hybrid exoskeleton comprising a powered exoskeleton and functional electrical stimulation (FES) is a promising technology for restoration of standing and walking functions after a neurological injury. Its shared control remains challenging due to the need to optimally distribute joint torques among FES and the powered exoskeleton while compensating for the FES-induced muscle fatigue and ensuring performance despite highly nonlinear and uncertain skeletal muscle behavior. This study develops a bi-level hierarchical control design for shared control of a powered exoskeleton and FES to overcome these challenges. A higher-level neural network–based iterative learning controller (NNILC) is derived to generate torques needed to drive the hybrid system. Then, a low-level model predictive control (MPC)-based allocation strategy optimally distributes the torque contributions between FES and the exoskeleton’s knee motors based on the muscle fatigue and recovery characteristics of a participant’s quadriceps muscles. A Lyapunov-like stability analysis proves global asymptotic tracking of state-dependent desired joint trajectories. The experimental results on four non-disabled participants validate the effectiveness of the proposed NNILC-MPC framework. The root mean square error (RMSE) of the knee joint and the hip joint was reduced by 71.96 and 74.57%, respectively, in the fourth iteration compared to the RMSE in the 1st sit-to-stand iteration.

A hybrid exoskeleton that combines functional electrical stimulation (FES) and a powered exoskeleton is an emerging technology for assisting people with mobility disorders. The cooperative use of FES and the exoskeleton allows active muscle contractions through FES while robustifying torque generation to reduce FES-induced muscle fatigue. In this article, a switched distribution of allocation ratios between FES and electric motors in a closed-loop adaptive control design is explored for the first time. The new controller uses an iterative learning neural network (NN)-based control law to compensate for structured and unstructured parametric uncertainties in the hybrid exoskeleton model. A discrete Lyapunov-like stability analysis that uses a common energy function proves asymptotic stability for the switched system with iterative learning update laws. Five human participants, including a person with complete spinal cord injury, performed sit-to-stand tasks with the new controller. The experimental results showed that the synthesized controller, in a few iterations, reduced the root mean square error between desired positions and actual positions of the knee and hip joints by 46.20% and 53.34%, respectively. The sit-to-stand experimental results also show that the proposed NN-based iterative learning control (NNILC) approach can recover the asymptotically trajectory tracking performance despite the switching of allocation levels between FES and electric motor. Compared to a proportional-derivative controller and traditional iterative learning control, the findings showed that the new controller can potentially simplify the clinical implementation of the hybrid exoskeleton with minimal parameters tuning.