It remains a formidable challenge to accurately recognize motion intentions of patients thus to control hand exoskeletons according to their volition. Current methods primarily focus on recognition of limited patient’s motion intentions, with the purpose of controlling preconfigured gestures of a hand exoskeleton for grasping objects. These methods exhibit a marked shortfall when encountering scenarios that are unexpected or not designed in advance, such as non-preprogrammed hand movements and object manipulation tasks. To tackle this issue, large language model (LLM) and speech recognition technology are employed in this study to allow the patient to control a hand exoskeleton at will. In particular, two LLMs are tailored to formulate codes of either generating non-preprogrammed gestures or dealing with unencountered objects. Additionally, an incremental learning framework is proposed to enable patients to perform both predefined and non-predefined operation tasks by integrating a natural language parser with the two LLM-based learners. The natural language parser can directly control the hand exoskeleton to perform predefined operations tasks from prestored command set, while the LLM-based learners can incrementally expand the control command set so as to enhance adaptability of the hand exoskeleton to complex activities over daily use. This study is a pioneering work in the field of hand exoskeletons, which will revolutionize the way to control hand exoskeletons. Furthermore, the proposed framework can be easily generalized to any other robots by modifying the prompt of customized LLMs, which provides a new idea to achieve autonomous learning in robotics.Note to Practitioners—The motivation of this article is to tackle the challenge of intention recognition for performing activities of daily living (ADLs) by stroke patients using a multi-degree of freedom hand exoskeleton. Existing methods for intention recognition so far can only be used for several tasks that are predefined in advance, thus none of them allow patients to control the hand exoskeleton completely at will. To surpass this limitation, an LLM-enabled incremental learning framework that integrates a hand exoskeleton controller with Large Language Model (LLM) is proposed and validated in this study. The framework offers patients an intuitive interface via voice interaction and enables patients to perform not only predefined operation tasks by the hand exoskeleton controller but also non-predefined ones that can be learned from the LLM. As a result, the hand exoskeleton controller continues to learn from the LLM, therefore is gradually able to perform all tasks in daily life. This pioneering study paves a new way in building patient-controlled hand exoskeletons with autonomous intelligence that can deal with non-predefined operation tasks in unstructured environments.

Assist-as-needed (AAN) assistance can promote active voluntary participation in rehabilitation and motor function recovery of post-stroke patients. However, different patients have personalized damaged regions and recovery states, causing difficulties to obtain adaptive and customized assistance in robot-assisted rehabilitation. This paper presents a mirror Adaptive Assist-As-Needed (AAAN) scheme, including two modules of Multi-Sensors Fused Estimation (MSFE) and Online Incremental Mirror Adaptation (OIMA), to encourage the subjects to actively participate in rehabilitation. Specifically, the first MSFE module can obtain the needed assistance based on the functional capability of the post-stroke patients via the data fusion of biological and motional signals using Kalman Filter. The second OIMA module fine-tunes the control torques estimated by MSFE to adapt the muscle fatigue and stiffness varieties of the affected limb based on the motion and physiological reference of the mirror healthy limb. The results demonstrate that the AAAN strategy can realize the transparent mode for healthy subjects and promote post-stroke patients to rehabilitate the affected limb with active participation using EMG signals 90.5% similar to those of the mirror healthy limb. The proposed method can be expected to greatly enhance power assistance and rehabilitation outcome of post-stroke patients using exoskeletons by provoking active participation. Note to Practitioners—For robotic rehabilitation, it is crucial to provide suitable assistances that can maximize the participation of post-stroke patients, which can promote the recovery outcome of therapies. The main purpose of this work is to achieve the adaptive assist-as-needed control strategy for upper limb rehabilitation tasks in two steps. Firstly, the elbow joint torques of a post-stroke patient are estimated by data fusion of motion and electromyography (EMG) signals using Kalman Filter, which can make up for the shortcomings of the individual signals, such as poor reliability and low sensitivity. Secondly, the joint motion and EMG signals of the mirror healthy limb are used as the reference to calculate the adaptive needed assistance to rehabilitate the affected limb. The preliminary experiments with healthy and post-stroke subjects demonstrate that this approach can obtain stable motion with the natural physiological states of subjects and enhance active voluntary participation in rehabilitation. In the future study, it will be investigated how to accelerate the adaptation of new patients based on the knowledge of the learned individuals using machine learning methods, such as lifelong learning and incremental learning.

It has been clinically proven that exoskeletons are effective self-training rehabilitation or daily living assistance devices for patients with hand dysfunctions. However, exoskeleton-assisted hand exercises with high degrees-of-freedom are considered as challenging tasks because the digit space, especially the thumb, cannot accommodate enough actuators. In this article, we report a tendon-driven soft hand exoskeleton with a hybrid configuration for thumb actuation. The soft hand exoskeleton system uses the least number of actuators to realize full degrees-of-freedom actuation for all digits. It is tested on a stroke patient with hemiplegia and a healthy subject. The experimental results show that the hand exoskeleton could assist the stroke patient to accomplish various training tasks, such as thumb encircling, grasping, pinching, releasing, and writing. It was found that digit trajectories and joint angle changes of the stroke patient were close to those of the healthy subject. Especially, the range of motion of the stroke patient shows significant improvement with the hand exoskeleton assistance compared to that without the hand exoskeleton assistance. The research in this article paves the way to develop fully actuated soft hand exoskeleton that can be eventually integrated with an electroencephalogram or electromyography for self-training rehabilitation or daily living assistance.