ABSTRACT
Rehabilitation robots can reproduce the rehabilitation movements of therapists by designed rehabilitation robot control methods to achieve the goal of training the patients' motion abilities. This paper proposes an impedance sliding-mode control method based on stiffness-scheduled law for the rehabilitation robot, which can be applied to rehabilitation training with both active and passive modes. A free-model-based sliding-mode control strategy is developed to avoid model dependence and reduce the system uncertainty caused by limb shaking. Additionally, the stiffness scheduling rule automatically regulates the impedance parameter of the rehabilitation robot based on the force exerted by the patient on the robot such that the rehabilitation training caters to the patient's health condition. The proposed method is compared with the fixed stiffness and variable stiffness impedance methods, and the superiority of the proposed method is proved. Rehabilitation training experiments on an actual rehabilitation robot are provided to demonstrate the feasibility and stability of the proposed method.
ABSTRACT
Anomaly detection has wide applications to help people recognize false, intrusion, flaw, equipment failure, etc. In most practical scenarios, the amount of the annotated data and the trusted labels is low, resulting in poor performance of the detection. In this paper, we focus on the anomaly detection for the text type data and propose a detection network based on biological immunity for few-shot detection, by imitating the working mechanism of the immune system of biological organisms. This network enabling the protected system to distinguish the aggressive behavior of "nonself" from the legitimate behavior of "self" by embedding characters. First, it constructs episodic task sets and extracts data representations at the character level. Then, in the pretraining phase, Word2Vec is used to embed the representations. In the meta-learning phase, a dynamic prototype containing encoder, routing, and relation is designed to identify the data traffic. Compare to the mean-based prototype, the proposed prototype applies a dynamic routing algorithm that assigns different weights to samples in the support set through multiple iterations to obtain a prototype that combines the distribution of samples. The proposed method is validated on 2 real traffic datasets. The experimental results indicate that (a) the proposed anomaly detection prototype outperforms state-of-the-art few-shot techniques with 1.3% to 4.48% accuracy and 0.18% to 4.55% recall; (b) under the premise of ensuring the accuracy and recall, the number of training samples is reduced to 5 or 10; (c) ablation experiments are designed for each module, and the results show that more accurate prototypes can be obtained by using the dynamic routing algorithm.
ABSTRACT
Continuum robots with their inherent compliance provide the potential for crossing narrow unstructured workspace and safely grasping various objects. However, the display gripper increases the size of the robots, and therefore, it tends to get stuck in constrained environments. This paper proposes a versatile continuum grasping robot (CGR) with a concealable gripper. The CGR can capture large objects with respect to the robot's scale using the continuum manipulator and can grasp various objects using the end concealable gripper especially in narrow and unstructured workspaces. To perform the cooperative operation of the concealable gripper and the continuum manipulator, a global kinematic model based on screw theory and a motion planning approach referred to as "multi-node synergy method" for the CGR are presented. The simulation and experimental results show that objects of different shapes and sizes can be captured by the same CGR even in complex and narrow environments. Finally, in the future, the CGR is expected to serve for satellite capture in harsh space environments such as high vacuum, strong radiation, and extreme temperatures.
