An exoskeleton robot is a kind of wearable mechanical instrument designed according to the shape and function of the human body. The main purpose of its design and manufacture is to enhance human strength, assist human walking and to help patients recover. The walking state of the exoskeleton robot should be highly consistent with the state of the human, so the accurate locomotion pattern recognition is the premise of the flexible control of the exoskeleton robot. In this paper, a simulated annealing (SA) algorithm-based support vector machine model is proposed for the recognition of different locomotion patterns. In order to improve the overall performance of the support vector machine (SVM), the simulated annealing algorithm is adopted to obtain the optimal parameters of support vector machine. The pressure signal measured by the force sensing resistors integrated on the sole of the shoe is fused with the position and pose information measured by the inertial measurement units attached to the thigh, shank and foot, which are used as the input information of the support vector machine. The max-relevance and min-redundancy algorithm was selected for feature extraction based on the window size of 300 ms and the sampling frequency of 100 Hz. Since the signals come from different types of sensors, normalization is required to scale the input signals to the interval (0,1). In order to prevent the classifier from overfitting, five layers of cross validation are used to train the support vector machine classifier. The support vector machine model was obtained offline in MATLAB. The finite state machine is used to limit the state transition and improve the recognition accuracy. Experiments on different locomotion patterns show that the accuracy of the algorithm is 97.47% ± 1.16%. The SA-SVM method can be extended to industrial robots and rehabilitation robots.

Exoskeleton robots can provide support and protection to the human body as well as be able to perform a series of tasks under control. Locomotion mode recognition is an essential prerequisite for assisted control of lower limb exoskeleton robots. A system is designed to be applied to a variety of individuals with quick and accurate identification. In this article, we propose a novel real-time locomotion mode recognition algorithm based on Gaussian mixture model (GMM) features aligned by dynamic time warping (DTW). The spatial distribution of the sensor data is represented by the GMM features, which emphasize the coupling between joints. This peculiarity promotes the distinction of similarity judgment and shows superior generalization performance. Furthermore, we expand the study of the warping path. We further validate the reasonableness of the DTW algorithm for feature matching to improve the recognition rate. The data of several inertial measurement units (IMUs) and pressure sensors were collected by 17 subjects in three terrains, including level ground, stairs, and ramp. We define the five locomotion modes as walking on level ground, stair ascent (SA), stair descent, ramp ascent, and ramp descent. Compared with the algorithms in previous papers, the GMM-DTW algorithm can achieve substantial recognition rates and good generalization performance with low latency. This work establishes the groundwork for the soft control of exoskeleton robots in the future.

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.

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.