Gait rehabilitation is essential for chronic stroke patients to regain independent walking ability and quality of life, of which symmetry is regarded as a gold standard of gait quality. In this letter, a cable-driven lower limb exoskeleton powered by series elastic actuators (SEAs) has been developed, and a generalized gait-phase-based assistive strategy has been presented to enhance the gait symmetry of chronic stroke patients in the future. This strategy features a parameterized assistive force generation method that allows individuals customization to achieve more synchronized assistance with their walking gait patterns. A compliant human-robot interaction is guaranteed by SEA, and the exoskeleton exhibits low passive impedance and good transparency. The proposed assistive strategy was evaluated with five able-bodied subjects walking with the assistance from exoskeleton while adding artificial impairments to mimic a pathological gait with deficits (i.e., reduced knee flexion and foot-drop). Experimental results proved its efficacy in enhancing temporal walking gait symmetry to the levels comparable to participants’ normal gait. 

Toward Gait Symmetry Enhancement via a Cable-Driven Exoskeleton Powered by Series Elastic Actuators

Forecasted gait trajectories of children could be used as feedforward input to control lower limb robotic devices, such as exoskeletons and actuated orthotic devices (e.g., Powered Ankle Foot Orthosis—PAFO). Several studies have forecasted healthy gait trajectories, but, to the best of our knowledge, none have forecasted gait trajectories of children with pathological gait yet. These exhibit higher inter- and intra-subject variability compared to typically developing gait of healthy subjects. Pathological trajectories represent the typical gait patterns that rehabilitative exoskeletons and actuated orthoses would target. In this study, we implemented two deep learning models, a Long-Term Short Memory (LSTM) and a Convolutional Neural Network (CNN), to forecast hip, knee, and ankle trajectories in terms of corresponding Euler angles in the pitch, roll, and yaw form for children with neurological disorders, up to 200 ms in the future. The deep learning models implemented in our study are trained on data (available online) from children with neurological disorders collected by Gillette Children’s Speciality Healthcare over the years 1994–2017. The children’s ages range from 4 to 19 years old and the majority of them had cerebral palsy (73%), while the rest were a combination of neurological, developmental, orthopaedic, and genetic disorders (27%). Data were recorded with a motion capture system (VICON) with a sampling frequency of 120 Hz while walking for 15 m. We investigated a total of 35 combinations of input and output time-frames, with window sizes for input vectors ranging from 50–1000 ms, and output vectors from 8.33–200 ms. Results show that LSTMs outperform CNNs, and the gap in performance becomes greater the larger the input and output window sizes are. The maximum difference between the Mean Absolute Errors (MAEs) of the CNN and LSTM networks was 0.91 degrees. Results also show that the input size has no significant influence on mean prediction errors when the output window is 50 ms or smaller. For output window sizes greater than 50 ms, the larger the input window, the lower the error. Overall, we obtained MAEs ranging from 0.095–2.531 degrees for the LSTM network, and from 0.129–2.840 degrees for the CNN. This study establishes the feasibility of forecasting pathological gait trajectories of children which could be integrated with exoskeleton control systems and experimentally explores the characteristics of such intelligent systems under varying input and output window time-frames.

/pdf/performance-of-deep-learning-models-in-forecasting-gait-1yf6zguy.pdf

Performance of Deep Learning Models in Forecasting Gait Trajectories of Children with Neurological Disorders

Exoskeleton robots are electrically, pneumatically, or hydraulically actuated devices that externally support the bones and cartilage of the human body while trying to mimic the human movement capabilities and augment muscle power. The lower extremity exoskeleton device may support specific human joints such as hip, knee, and ankle, or provide support to carry and balance the weight of the full upper body. Their assistive functionality for physically-abled and disabled humans is demanded in medical, industrial, military, safety applications, and other related fields. The vision of humans walking with an exoskeleton without external support is the prospect of the robotics and artificial intelligence working groups. This paper presents a survey on the design and control of lower extremity exoskeletons for bipedal walking. First, a historical view on the development of walking exoskeletons is presented and various lower body exoskeleton designs are categorized in different application areas. Then, these designs are studied from design, modeling, and control viewpoints. Finally, a discussion on future research directions is provided.

/pdf/a-survey-on-design-and-control-of-lower-extremity-2f6vlw9t.pdf

A Survey on Design and Control of Lower Extremity Exoskeletons for Bipedal Walking

Inertial sensors have gained relevance as wearable sensors to acquire the kinematics of human limbs through fusion sensor algorithms and biomechanical models. However, there are some limitations to the use of Inertial Measurement Units in the control of wearable robotic devices: 1) Some approaches use magnetometer readings to estimate the orientation of the sensor, and, as a result, they are prone to errors due to electromagnetic interferences; 2) Biomechanical model-based approaches require complex and time-consuming calibration procedures. In order to address these issues, this paper proposes an Extended Kalman Filter to estimate sagittal lower limb kinematics during gait, based on gyroscopes and accelerometers and without requiring any calibration or sensor alignment process. As magnetometer measurements are not involved, this method is not affected by electromagnetic disturbances. Our approach calculates the knee rotation axis in real-time, and it estimates hip and ankle sagittal axes considering that the movements in that plane occur around parallel axes. We carried out an experimental validation with eight healthy subjects walking on a treadmill at different velocities. We obtained waveform RMS errors about 3.8°, 3.6°, and 4.8° for hip, knee, and ankle in the sagittal plane. We also assessed the performance of this method as a tool for controlling lower-limb robotic exoskeletons by detecting gait events or estimating the phase and frequency of the gait in real-time through an Adaptive Frequency Oscillator. The average RMS delay in the detection of gait events was lower than 60 ms, and the RMSE in the estimation of the gait phase was about 3% of the gait cycle. We conclude that the described method could be used as a controller for wearable robotic devices.

An IMUs-Based Extended Kalman Filter to Estimate Gait Lower Limb Sagittal Kinematics for the Control of Wearable Robotic Devices

With the emerging of wearable robots, the safety and effectiveness of human-robot physical interaction have attracted extensive attention. Recent studies suggest that online measurement of the interaction force between the robot and the human body is essential to the aspects above in wearable exoskeletons. However, a large proportion of existing wearable exoskeletons monitor and sense the delivered force and torque through an indirect-measure method, in which the torque is estimated by the motor current. Direct force/torque measuring through low-cost and compact wearable sensors remains an open problem. This paper presents a compact soft sensor system for wearable gait assistance exoskeletons. The contact force is converted into a voltage signal by measuring the air pressure within a soft pneumatic chamber. The developed soft force sensor system was implemented on a robotic hip exoskeleton, and the real-time interaction force between the human thigh and the exoskeleton was measured through two differential soft chambers. The delivered torque of the hip exoskeleton was calculated based on a characterization model. Experimental results suggested that the sensor system achieved direct force measurement with an error of 10.3 ± 6.58%, and torque monitoring for a hip exoskeleton which provided an understanding for the importance of direct force/torque measurement for assistive performance. Compared with traditional rigid force sensors, the proposed system has several merits, as it is compact, low-cost, and has good adaptability to the human body due to the soft structure.

Differential Soft Sensor-Based Measurement of Interactive Force and Assistive Torque for a Robotic Hip Exoskeleton.

Background Many lower-limb exoskeletons have been developed to assist gait, exhibiting a large range of control methods. The goal of this paper is to review and classify these control strategies, that determine how these devices interact with the user. Methods In addition to covering the recent publications on the control of lower-limb exoskeletons for gait assistance, an effort has been made to review the controllers independently of the hardware and implementation aspects. The common 3-level structure (high, middle, and low levels) is first used to separate the continuous behavior (mid-level) from the implementation of position/torque control (low-level) and the detection of the terrain or user's intention (high-level). Within these levels, different approaches (functional units) have been identified and combined to describe each considered controller. Results 291 references have been considered and sorted by the proposed classification. The methods identified in the high-level are manual user input, brain interfaces, or automatic mode detection based on the terrain or user's movements. In the mid-level, the synchronization is most often based on manual triggers by the user, discrete events (followed by state machines or time-based progression), or continuous estimations using state variables. The desired action is determined based on position/torque profiles, model-based calculations, or other custom functions of the sensory signals. In the low-level, position or torque controllers are used to carry out the desired actions. In addition to a more detailed description of these methods, the variants of implementation within each one are also compared and discussed in the paper. Conclusions By listing and comparing the features of the reviewed controllers, this work can help in understanding the numerous techniques found in the literature. The main identified trends are the use of pre-defined trajectories for full-mobilization and event-triggered (or adaptive-frequency-oscillator-synchronized) torque profiles for partial assistance. More recently, advanced methods to adapt the position/torque profiles online and automatically detect terrains or locomotion modes have become more common, but these are largely still limited to laboratory settings. An analysis of the possible underlying reasons of the identified trends is also carried out and opportunities for further studies are discussed.

/pdf/review-of-control-strategies-for-lower-limb-exoskeletons-to-2rtwoa8l16.pdf

Ali Reza Manzoori

Papers

Review of control strategies for lower-limb exoskeletons to assist gait