Recent advancements in lower limb exoskeleton control have predominantly focused on enhancing walking capabilities across diverse terrains, such as level ground, stairs, and ramps. However, achieving seamless transitions between these terrains remains a significant challenge due to the unpredictability of the environment, which hampers adaptive control. In this paper, we propose a Hierarchical Interactive Learning (HIL) control method based on gait phase and locomotion pattern recognition. The method comprises two layers: high-level learning and low-level control. The high-level learning is based on gait phase and locomotion pattern recognition, utilizing the Dynamic Movement Primitives (DMP) to piecewise learn the desired joint torque curves. The low-level control utilizes the learned DMP to output torque based on the gait phase and locomotion pattern, while reinforcement learning is employed to dynamically adjust the control parameters of DMP in real-time with the goal of minimizing human-exoskeleton interaction forces. The experiments collected gait data of lower limb movement from active exoskeletons. The results show that our method significantly reduces human-exoskeleton interaction forces across diverse terrains. In order to verify the feasibility and effectiveness of the proposed method, 15 healthy subjects were tested with the lower limb exoskeleton of these 3 generations. The experimental results show that the proposed HIL control method gives a valuable tool for smooth transitions among different terrains, reduces the reliance on accurate dynamic models and the average oxygen consumption decreased by about 12%, underscoring its potential to improve exoskeleton-assisted mobility.

Gait phase detection is essential for the wearable powered exoskeletons. This paper proposes an online gait phase detection method based on dynamic time warping mean (DTW-MEAN) templates using ground contact forces (GCFs). There are two important methods of gait phase detection, which are the template matching and statistical method. Template matching methods such as DTW are robust and have been widely used in the field of gait phase detection. However, the template matching is a kind of method based on distance measure, and the gait phase detection will ignore the coupling connections between the gait sequences; on the contrary, the statistical method can fuse these connections well. In this paper, a statistical mean method based on DTW is proposed to solve the problem of recognizing phases between gait sequences that are not correctly detected by single template methods. We tested our approach in complex environment (such as different terrains, different payloads, and different speeds) and gained over 95% accuracy and time difference below 25ms. Our proposed approach obtained better detection results with the advantage of no need to retrain templates.

This paper presents a novel methodology for detecting the gait phase of human walking on level ground. The previous threshold method (TM) sets a threshold to divide the ground contact forces (GCFs) into on-ground and off-ground states. However, the previous methods for gait phase detection demonstrate no adaptability to different people and different walking speeds. Therefore, this paper presents a self-tuning triple threshold algorithm (STTTA) that calculates adjustable thresholds to adapt to human walking. Two force sensitive resistors (FSRs) were placed on the ball and heel to measure GCFs. Three thresholds (i.e., high-threshold, middle-threshold andlow-threshold) were used to search out the maximum and minimum GCFs for the self-adjustments of thresholds. The high-threshold was the main threshold used to divide the GCFs into on-ground and off-ground statuses. Then, the gait phases were obtained through the gait phase detection algorithm (GPDA), which provides the rules that determine calculations for STTTA. Finally, the STTTA reliability is determined by comparing the results between STTTA and Mariani method referenced as the timing analysis module (TAM) and Lopez–Meyer methods. Experimental results show that the proposed method can be used to detect gait phases in real time and obtain high reliability when compared with the previous methods in the literature. In addition, the proposed method exhibits strong adaptability to different wearers walking at different walking speeds.

In recent years, with the rapid advancements in deep learning technologies, particularly deep neural networks, signature verification has seen significant improvements in accuracy. Despite the significant progress made in using deep learning technologies, there remains several challenges that affect their practical application, such as insufficient feature extraction, long neural network computation time, and high resource consumption. In this paper, an online handwritten signature verification algorithm is proposed, which mainly uses the CAE-MV-based feature dimensionality reduction method to compress and select features of the original signature data to construct a signature feature set. The Depth-wise Separable Convolutional Neural Network(DWSCNN) based on Depth-wise separable convolution is used to classify and verify the signature feature set. Compared with CNN, the DWSCNN can significantly reduce the number of neural network parameters while the classification effect is not much different, thus greatly shortening the running time and resource occupation. Through the analysis of the verification results on two publicly available signature databases, MCYT-100 and SVC-2004, the proposed algorithm improves the accuracy, reduces the False Acceptance Rate (FAR) and False Rejection Rate (FRR). The average verification accuracy reaches 98.92%, which is superior to the current mainstream online signature verification frameworks, demonstrating the effectiveness and efficiency of the proposed framework.

This paper proposed a new novel method to adaptively detect gait patterns in real time through the ground contact forces (GCFs) measured by load cell. The curve similarity model (CSM) is used to identify the division of off-ground and on-ground statuses, and differentiate gait patterns based on the detection rules. Traditionally, published threshold-based methods detect gait patterns by means of setting a fixed threshold to divide the GCFs into on-ground and off-ground statuses. However, the threshold-based methods in the literature are neither an adaptive nor a real-time approach. In this paper, the curve is composed of a series of continuous or discrete ordered GCF data points, and the CSM is built offline to obtain a training template. Then, the testing curve is compared with the training template to figure out the degree of similarity. If the computed degree of similarity is less than a given threshold, they are considered to be similar, which would lead to the division of off-ground and on-ground statuses. Finally, gait patterns could be differentiated according to the status division based on the detection rules. In order to test the detection error rate of the proposed method, a method in the literature is introduced as the reference method to obtain comparative results. The experimental results indicated that the proposed method could be used for real-time gait pattern detection, detect the gait patterns adaptively, and obtain a low error rate compared with the reference method.