Search

The lack of intuitive and active human–robot interaction makes it difficult to use upper-limb-assistive devices. In this paper, we propose a novel learning-based controller that intuitively uses onset motion to predict the desired end-point position for an assistive robot. A multi-modal sensing system comprising inertial measurement units (IMUs), electromyographic (EMG) sensors, and mechanomyography (MMG) sensors was implemented. This system was used to acquire kinematic and physiological signals during reaching and placing tasks performed by five healthy subjects. The onset motion data of each motion trial were extracted to input into traditional regression models and deep learning models for training and testing. The models can predict the position of the hand in planar space, which is the reference position for low-level position controllers. The results show that using IMU sensor with the proposed prediction model is sufficient for motion intention detection, which can provide almost the same prediction performance compared with adding EMG or MMG. Additionally, recurrent neural network (RNN)-based models can predict target positions over a short onset time window for reaching motions and are suitable for predicting targets over a longer horizon for placing tasks. This study's detailed analysis can improve the usability of the assistive/rehabilitation robots. [ABSTRACT FROM AUTHOR]

The lack of intuitive and active human–robot interaction makes it difficult to use upper-limb-assistive devices. In this paper, we propose a novel learning-based controller that intuitively uses onset motion to predict the desired end-point position for an assistive robot. A multi-modal sensing system comprising inertial measurement units (IMUs), electromyographic (EMG) sensors, and mechanomyography (MMG) sensors was implemented. This system was used to acquire kinematic and physiological signals during reaching and placing tasks performed by five healthy subjects. The onset motion data of each motion trial were extracted to input into traditional regression models and deep learning models for training and testing. The models can predict the position of the hand in planar space, which is the reference position for low-level position controllers. The results show that using IMU sensor with the proposed prediction model is sufficient for motion intention detection, which can provide almost the same prediction performance compared with adding EMG or MMG. Additionally, recurrent neural network (RNN)-based models can predict target positions over a short onset time window for reaching motions and are suitable for predicting targets over a longer horizon for placing tasks. This study’s detailed analysis can improve the usability of the assistive/rehabilitation robots.

Rehabilitation robots play an increasingly important role in the recovery of motor function for stroke. To ensure a natural physical human-robot interaction (pHRI) and enhance the active participation of subjects, it is necessary for the robots to understand the human intention and cooperate actively with humanlike characteristics. This study proposed a hybrid active control algorithm with human motion intention detection. The motion intention was defined as the desired position and velocity, which were continuously estimated according to the human upper-limb model and minimum jerk model, respectively. The motion intention was then fed into a hybrid force and position controller of an upper-limb cable driven rehabilitation robot (CDRR). And a three-dimensional reaching task without predefined trajectory was employed to validate the effectiveness of the proposed control algorithm. Experimental results showed that the control algorithm could continuously recognize the human motion intention and enabled the robot better movement performance indicated as smaller offset error, smoother trajectory, and lower impact. The proposed method could guarantee a natural pHRI and improve the engagement of the subjects, which has great potential in clinical applications.

For patients with ankle injuries, rehabilitation training is an important and effective way to help patients restore their ankle complex's motor abilities. Aiming to improve the accuracy and performance of ankle rehabilitation, the authors focus on the control strategies of the developed parallel ankle rehabilitation robot with novel 2-UPS/RRR mechanism. Firstly, the kinematics model of the mechanism is established, and they deduce the inverse solution of positions as well as the velocity mapping between the driving speed and the robot's angular velocity, based on which they realise the trajectory tracking control in the process of passive rehabilitation training. Secondly, they set up experiments to determine the torque threshold that can be used to detect the motion intention of ankle joint, and then they propose the active rehabilitation training strategy according to the motion intention detection. Finally, experiments were carried out with healthy subjects, with results showing that the trajectory tracking error during passive rehabilitation training is very small, and the moving platform of the ankle rehabilitation robot can drive the ankle joint to the detected motion intention direction at a constant speed flexibly and smoothly, which verifies the effectiveness of the control strategies for ankle rehabilitation training.

For patients with ankle injuries, rehabilitation training is an important and effective way to help patients restore their ankle complex's motor abilities. Aiming to improve the accuracy and performance of ankle rehabilitation, the authors focus on the control strategies of the developed parallel ankle rehabilitation robot with novel 2‐UPS/RRR mechanism. Firstly, the kinematics model of the mechanism is established, and they deduce the inverse solution of positions as well as the velocity mapping between the driving speed and the robot's angular velocity, based on which they realise the trajectory tracking control in the process of passive rehabilitation training. Secondly, they set up experiments to determine the torque threshold that can be used to detect the motion intention of ankle joint, and then they propose the active rehabilitation training strategy according to the motion intention detection. Finally, experiments were carried out with healthy subjects, with results showing that the trajectory tracking error during passive rehabilitation training is very small, and the moving platform of the ankle rehabilitation robot can drive the ankle joint to the detected motion intention direction at a constant speed flexibly and smoothly, which verifies the effectiveness of the control strategies for ankle rehabilitation training. [ABSTRACT FROM AUTHOR]

This paper presents the design and development of a low cost robotic knee exoskeleton with mobile interface for active assistance of gait rehabilitation of patients who suffer lower limb impairment. Interaction based on electromyography (EMG) is used for detecting motion intention to recognize muscular activity patterns by applying artificial neural network (ANN) algorithms. A comparison of muscular activity between the rectus femoris of each lower limb is made in order to find which offers better results. Once the system identifies a motion intention, it generates a predefined trajectory that mimics the gait cycle pattern of the knee joint. The actuator of the exoskeleton is required to accomplish this movement based on a position control strategy. The exoskeleton's operation is supervised remotely through a mobile device, which is connected to a database that contains three rehabilitation routines previously set by medical staff. The robotic knee prototype is validated by monitoring its performance while being used, initially by healthy subjects. [ABSTRACT FROM AUTHOR]

Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models.

Active movement-assistive devices aim to increase the quality of life for patients with neuromusculoskeletal disorders. This technology requires interaction between the user and the device through a control interface that detects the user's movement intention. Researchers have explored a wide variety of invasive and non-invasive methods to derive the user's movement. With the goal of illustrating the wide spectrum of strategies, this paper presents a comprehensive review of non-invasive control interfaces used to operate active movementassistive devices. A novel systematic classification method is proposed to categorize the control interfaces based on: (I) the source of the physiological signal, (II) the physiological phenomena responsible for generating the signal, and (III) the sensors used to measure the physiological signal. The proposed classification method can successfully categorize all the existing control interfaces providing a comprehensive overview of the state of the art. Each sensing modality is briefly described in the body of the paper following the same structure used in the classification method. Furthermore, we have discussed several design considerations, challenges, and future directions of non-invasive control interfaces for active movement-assistive devices. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents algorithms for detection of gait initiation and termination using wearable inertial measurement units and pressure-sensitive insoles. Body joint angles, joint angular velocities, ground reaction force and center of plantar pressure of each foot are obtained from these sensors and input into supervised machine learning algorithms. The proposed initiation detection method recognizes two events: gait onset (an anticipatory movement preceding foot lifting) and toe-off. The termination detection algorithm segments gait into steps, measures the signals over a buffer at the beginning of each step, and determines whether this measurement belongs to the final step. The approach is validated with 10 subjects at two gait speeds, using within-subject and subject-independent cross-validation. Results show that gait initiation can be detected timely and accurately, with few errors in the case of within-subject cross-validation and overall good performance in subject-independent cross-validation. Gait termination can be predicted in over 80% of trials well before the subject comes to a complete stop. Results also show that the two sensor types are equivalent in predicting gait initiation while inertial measurement units are generally superior in predicting gait termination. Potential use of the algorithms is foreseen primarily with assistive devices such as prostheses and exoskeletons. [Copyright &y& Elsevier]

Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models. [ABSTRACT FROM AUTHOR]