skip to main content

This content will become publicly available on December 1, 2024

Title: Robust walking control of a lower limb rehabilitation exoskeleton coupled with a musculoskeletal model via deep reinforcement learning
Abstract Background Few studies have systematically investigated robust controllers for lower limb rehabilitation exoskeletons (LLREs) that can safely and effectively assist users with a variety of neuromuscular disorders to walk with full autonomy. One of the key challenges for developing such a robust controller is to handle different degrees of uncertain human-exoskeleton interaction forces from the patients. Consequently, conventional walking controllers either are patient-condition specific or involve tuning of many control parameters, which could behave unreliably and even fail to maintain balance. Methods We present a novel, deep neural network, reinforcement learning-based robust controller for a LLRE based on a decoupled offline human-exoskeleton simulation training with three independent networks, which aims to provide reliable walking assistance against various and uncertain human-exoskeleton interaction forces. The exoskeleton controller is driven by a neural network control policy that acts on a stream of the LLRE’s proprioceptive signals, including joint kinematic states, and subsequently predicts real-time position control targets for the actuated joints. To handle uncertain human interaction forces, the control policy is trained intentionally with an integrated human musculoskeletal model and realistic human-exoskeleton interaction forces. Two other neural networks are connected with the control policy network to predict the interaction forces and muscle coordination. To further increase the robustness of the control policy to different human conditions, we employ domain randomization during training that includes not only randomization of exoskeleton dynamics properties but, more importantly, randomization of human muscle strength to simulate the variability of the patient’s disability. Through this decoupled deep reinforcement learning framework, the trained controller of LLREs is able to provide reliable walking assistance to patients with different degrees of neuromuscular disorders without any control parameter tuning. Results and conclusion A universal, RL-based walking controller is trained and virtually tested on a LLRE system to verify its effectiveness and robustness in assisting users with different disabilities such as passive muscles (quadriplegic), muscle weakness, or hemiplegic conditions without any control parameter tuning. Analysis of the RMSE for joint tracking, CoP-based stability, and gait symmetry shows the effectiveness of the controller. An ablation study also demonstrates the strong robustness of the control policy under large exoskeleton dynamic property ranges and various human-exoskeleton interaction forces. The decoupled network structure allows us to isolate the LLRE control policy network for testing and sim-to-real transfer since it uses only proprioception information of the LLRE (joint sensory state) as the input. Furthermore, the controller is shown to be able to handle different patient conditions without the need for patient-specific control parameter tuning.  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Journal of NeuroEngineering and Rehabilitation
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Powered ankle exoskeletons that apply assistive torques with optimized timing and magnitude can reduce metabolic cost by ∼10% compared to normal walking. However, finding individualized optimal control parameters is time consuming and must be done independently for different walking modes (e.g., speeds, slopes). Thus, there is a need for exoskeleton controllers that are capable of continuously adapting torque assistance in concert with changing locomotor demands. One option is to use a biologically inspired, model-based control scheme that can capture the adaptive behavior of the human plantarflexors during natural gait. Here, based on previously demonstrated success in a powered ankle-foot prosthesis, we developed an ankle exoskeleton controller that uses a neuromuscular model (NMM) comprised of a Hill type musculotendon driven by a simple positive force feedback reflex loop. To examine the effects of NMM reflex parameter settings on (i) ankle exoskeleton mechanical performance and (ii) users’ physiological response, we recruited nine healthy, young adults to walk on a treadmill at a fixed speed of 1.25 m/s while donning bilateral tethered robotic ankle exoskeletons. To quantify exoskeleton mechanics, we measured exoskeleton torque and power output across a range of NMM controller Gain (0.8–2.0) and Delay (10–40 ms) settings, as well as a High Gain/High Delay (2.0/40 ms) combination. To quantify users’ physiological response, we compared joint kinematics and kinetics, ankle muscle electromyography and metabolic rate between powered and unpowered/zero-torque conditions. Increasing NMM controller reflex Gain caused increases in average ankle exoskeleton torque and net power output, while increasing NMM controller reflex Delay caused a decrease in net ankle exoskeleton power output. Despite systematic reduction in users’ average biological ankle moment with exoskeleton mechanical assistance, we found no NMM controller Gain or Delay settings that yielded changes in metabolic rate. Post hoc analyses revealed weak association at best between exoskeleton and biological mechanics and changes in users’ metabolic rate. Instead, changes in users’ summed ankle joint muscle activity with powered assistance correlated with changes in their metabolic energy use, highlighting the potential to utilize muscle electromyography as a target for on-line optimization in next generation adaptive exoskeleton controllers. 
    more » « less
  2. Robotic exoskeletons can assist humans with walking by providing supplemental torque in proportion to the user's joint torque. Electromyographic (EMG) control algorithms can estimate a user's joint torque directly using real-time EMG recordings from the muscles that generate the torque. However, EMG signals change as a result of supplemental torque from an exoskeleton, resulting in unreliable estimates of the user's joint torque during active exoskeleton assistance. Here, we present an EMG control framework for robotic exoskeletons that provides consistent joint torque predictions across varying levels of assistance. Experiments with three healthy human participants showed that using diverse training data (from different levels of assistance) enables robust torque predictions, and that a convolutional neural network (CNN), but not a Kalman filter (KF), can capture the non-linear transformations in EMG due to exoskeleton assistance. With diverse training, the CNN could reliably predict joint torque from EMG during zero, low, medium, and high levels of exoskeleton assistance [root mean squared error (RMSE) below 0.096 N-m/kg]. In contrast, without diverse training, RMSE of the CNN ranged from 0.106 to 0.144 N-m/kg. RMSE of the KF ranged from 0.137 to 0.182 N-m/kg without diverse training, and did not improve with diverse training. When participant time is limited, training data should emphasize the highest levels of assistance first and utilize at least 35 full gait cycles for the CNN. The results presented here constitute an important step toward adaptive and robust human augmentation via robotic exoskeletons. This work also highlights the non-linear reorganization of locomotor output when using assistive exoskeletons; significant reductions in EMG activity were observed for the soleus and gastrocnemius, and a significant increase in EMG activity was observed for the erector spinae. Control algorithms that can accommodate spatiotemporal changes in muscle activity have broad implications for exoskeleton-based assistance and rehabilitation following neuromuscular injury. 
    more » « less
  3. null (Ed.)
    Our group is developing a cyber-physical walking system (CPWS) for people paralyzed by spinal cord injuries (SCI). The current CPWS consists of a functional neuromuscular stimulation (FNS) system and a powered lower-limb exoskeleton for walking with leg movements in the sagittal plane. We are developing neural control systems that learn to assist the user of this CPWS to walk with stability. In a previous publication (Liu et al., Biomimetics, 2019, 4, 28), we showed a neural controller that stabilized a simulated biped in the sagittal plane. We are considering adding degrees of freedom to the CPWS to allow more natural walking movements and improved stability. Thus, in this paper, we present a new neural network enhanced control system that stabilizes a three-dimensional simulated biped model of a human wearing an exoskeleton. Results show that it stabilizes human/exoskeleton models and is robust to impact disturbances. The simulated biped walks at a steady pace in a range of typical human ambulatory speeds from 0.7 to 1.3 m/s, follows waypoints at a precision of 0.3 m, remains stable, and continues walking forward despite impact disturbances and adapts its speed to compensate for persistent external disturbances. Furthermore, the neural network controller stabilizes human models of different statures from 1.4 to 2.2 m tall without any changes to the control parameters. Please see videos at the following link: 3D biped walking control . 
    more » « less
  4. 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. 
    more » « less
  5. Proportional myoelectric controller (PMC) has been one of the most common assistance strategies for robotic exoskeletons due to its ability to modulate assistance level directly based on the user's muscle activation. However, existing PMC strategies (static or user-adaptive) scale torque linearly with muscle activation level and fail to address complex and non-linear mapping between muscle activation and joint torque. Furthermore, previously presented adaptive PMC strategies do not allow for environmental changes (such as changes in ground slopes) and modulate the system's assistance level over many steps. In this work, we designed a novel user- and environment-adaptive PMC for a knee exoskeleton that modulates the peak assistance level based on the slope level during locomotion. We recruited nine able-bodied adults to test and compare the effects of three different PMC strategies (static, user-adaptive, and user- and environment-adaptive) on the user's metabolic cost and the knee extensor muscle activation level during load-carriage walking (6.8 kg) in three inclination settings (0°, 4.5°, and 8.5°). The results showed that only the user- and environment-adaptive PMC was effective in significantly reducing user's metabolic cost (5.8% reduction) and the knee extensor muscle activation (19% reduction) during 8.5° incline walking compared to the unpowered condition while other PMCs did not have as large of an effect. This control framework highlights the viability of implementing an assistance paradigm that can dynamically adjust to the user's biological demand, allowing for a more personalized assistance paradigm. 
    more » « less