Experiment-free exoskeleton assistance via learning in simulation.

Exoskeletons have enormous potential to improve human locomotive performance1-3. However, their development and broad dissemination are limited by the requirement for lengthy human tests and handcrafted control laws2. Here we show an experiment-free method to learn a versatile control policy in simulation. Our learning-in-simulation framework leverages dynamics-aware musculoskeletal and exoskeleton models and data-driven reinforcement learning to bridge the gap between simulation and reality without human experiments. The learned controller is deployed on a custom hip exoskeleton that automatically generates assistance across different activities with reduced metabolic rates by 24.3%, 13.1% and 15.4% for walking, running and stair climbing, respectively. Our framework may offer a generalizable and scalable strategy for the rapid development and widespread adoption of a variety of assistive robots for both able-bodied and mobility-impaired individuals.

Modeling and Stiffness-based Continuous Torque Control of Lightweight Quasi-Direct-Drive Knee Exoskeletons for Versatile Walking Assistance.

State-of-the-art exoskeletons are typically limited by low control bandwidth and small range stiffness of actuators which are based on high gear ratios and elastic components (e.g., series elastic actuators). Furthermore, most exoskeletons are based on discrete gait phase detection and/or discrete stiffness control resulting in discontinuous torque profiles. To fill these two gaps, we developed a portable lightweight knee exoskeleton using quasi-direct drive (QDD) actuation that provides 14 Nm torque (36.8% biological joint moment for overground walking). This paper presents 1) stiffness modeling of torque-controlled QDD exoskeletons and 2) stiffness-based continuous torque controller that estimates knee joint moment in real-time. Experimental tests found the exoskeleton had high bandwidth of stiffness control (16 Hz under 100 Nm/rad) and high torque tracking accuracy with 0.34 Nm Root Mean Square (RMS) error (6.22%) across 0-350 Nm/rad large range stiffness. The continuous controller was able to estimate knee moments accurately and smoothly for three walking speeds and their transitions. Experimental results with 8 able-bodied subjects demonstrated that our exoskeleton was able to reduce the muscle activities of all 8 measured knee and ankle muscles by 8.60%-15.22% relative to unpowered condition, and two knee flexors and one ankle plantar flexor by 1.92%-10.24% relative to baseline (no exoskeleton) condition.

Design and Backdrivability Modeling of a Portable High Torque Robotic Knee Prosthesis With Intrinsic Compliance For Agile Activities.

High-performance prostheses are crucial to enable versatile activities like walking, squatting, and running for lower extremity amputees. State-of-the-art prostheses are either not powerful enough to support demanding activities or have low compliance (low backdrivability) due to the use of high speed ratio transmission. Besides speed ratio, gearbox design is also crucial to the compliance of wearable robots, but its role is typically ignored in the design process. This paper proposed an analytical backdrive torque model that accurately estimate the backdrive torque from both motor and transmission to inform the robot design. Following this model, this paper also proposed methods for gear transmission design to improve compliance by reducing inertia of the knee prosthesis. We developed a knee prosthesis using a high torque actuator (built-in 9:1 planetary gear) with a customized 4:1 low-inertia planetary gearbox. Benchtop experiments show the backdrive torque model is accurate and proposed prosthesis can produce 200 Nm high peak torque (shield temperature <60°C), high compliance (2.6 Nm backdrive torque), and high control accuracy (2.7/8.1/1.7 Nm RMS tracking errors for 1.25 m/s walking, 2 m/s running, and 0.25 Hz squatting, that are 5.4%/4.1%/1.4% of desired peak torques). Three able-bodied subject experiments showed our prosthesis could support agile and high-demanding activities.

Quasi-Direct Drive Actuation for a Lightweight Hip Exoskeleton with High Backdrivability and High Bandwidth.

High-performance actuators are crucial to enable mechanical versatility of wearable robots, which are required to be lightweight, highly backdrivable, and with high bandwidth. State-of-the-art actuators, e.g., series elastic actuators (SEAs), have to compromise bandwidth to improve compliance (i.e., backdrivability). We describe the design and human-robot interaction modeling of a portable hip exoskeleton based on our custom quasi-direct drive (QDD) actuation (i.e., a high torque density motor with low ratio gear). We also present a model-based performance benchmark comparison of representative actuators in terms of torque capability, control bandwidth, backdrivability, and force tracking accuracy. This paper aims to corroborate the underlying philosophy of "design for control", namely meticulous robot design can simplify control algorithms while ensuring high performance. Following this idea, we create a lightweight bilateral hip exoskeleton to reduce joint loadings during normal activities, including walking and squatting. Experiments indicate that the exoskeleton is able to produce high nominal torque (17.5 Nm), high backdrivability (0.4 Nm backdrive torque), high bandwidth (62.4 Hz), and high control accuracy (1.09 Nm root mean square tracking error, 5.4% of the desired peak torque). Its controller is versatile to assist walking at different speeds and squatting. This work demonstrates performance improvement compared with state-of-the-art exoskeletons.

Reprogrammable and reconfigurable mechanical computing metastructures with stable and high-density memory.

Mechanical computing encodes information in deformed states of mechanical systems, such as multistable structures. However, achieving stable mechanical memory in most multistable systems remains challenging and often limited to binary information. Here, we report leveraging coupling kinematic bifurcation in rigid cube-based mechanisms with elasticity to create transformable, multistable mechanical computing metastructures with stable, high-density mechanical memory. Simply stretching the planar metastructure forms a multistable corrugated platform. It allows for independent mechanical or magnetic actuation of individual bistable element, serving as pop-up voxels for display or binary units for various tasks such as information writing, erasing, reading, encryption, and mechanologic computing. Releasing the pre-stretched strain stabilizes the prescribed information, resistant to external mechanical or magnetic perturbations, whereas re-stretching enables editable mechanical memory, akin to selective zones or disk formatting for information erasure and rewriting. Moreover, the platform can be reprogrammed and transformed into a multilayer configuration to achieve high-density memory.

Artificial Neural Network-Based Activities Classification, Gait Phase Estimation, and Prediction.

Gait patterns are critical to health monitoring, gait impairment assessment, and wearable device control. Unrhythmic gait pattern detection under community-based conditions is a new frontier in this area. The present paper describes a high-accuracy gait phase estimation and prediction algorithm built on a two-stage artificial neural network. This work targets to develop an algorithm that can estimate and predict the gait cycle in real time using a portable controller with only two IMU sensors (one on each thigh) in the community setting. Our algorithm can detect the gait phase in unrhythmic conditions during walking, stair ascending, and stair descending, and classify these activities with standing. Moreover, our algorithm is able to predict both future intra- and inter-stride gait phases, offering a potential means to improve wearable device controller performance. The proposed data-driven algorithm is based on a dataset consisting of 5 able-bodied subjects and validated on 3 different able-bodied subjects. Under unrhythmic activity situations, validation shows that the algorithm can accurately identify multiple activities with 99.55% accuracy, and estimate ([Formula: see text]: 6.3%) and predict 200-ms-ahead ([Formula: see text]: 8.6%) the gait phase percentage in real time, which are on average 57.7 and 54.0% smaller than the error from the event-based method in the same conditions. This study showcases a solution to estimate and predict gait status for multiple unrhythmic activities, which may be deployed to controllers for wearable robots or health monitoring devices.

Bio-inspired design of a self-aligning, lightweight, and highly-compliant cable-driven knee exoskeleton.

Powered knee exoskeletons have shown potential for mobility restoration and power augmentation. However, the benefits of exoskeletons are partially offset by some design challenges that still limit their positive effects on people. Among them, joint misalignment is a critical aspect mostly because the human knee joint movement is not a fixed-axis rotation. In addition, remarkable mass and stiffness are also limitations. Aiming to minimize joint misalignment, this paper proposes a bio-inspired knee exoskeleton with a joint design that mimics the human knee joint. Moreover, to accomplish a lightweight and high compliance design, a high stiffness cable-tension amplification mechanism is leveraged. Simulation results indicate our design can reduce 49.3 and 71.9% maximum total misalignment for walking and deep squatting activities, respectively. Experiments indicate that the exoskeleton has high compliance (0.4 and 0.1 Nm backdrive torque under unpowered and zero-torque modes, respectively), high control bandwidth (44 Hz), and high control accuracy (1.1 Nm root mean square tracking error, corresponding to 7.3% of the peak torque). This work demonstrates performance improvement compared with state-of-the-art exoskeletons.