In this paper, we propose to use brain-computer interface (BCI) control a lower-limb exoskeleton. The exoskeleton follows the wearer's motion intention through decoding of electroencephalography (EEG) signals and multi-modal cognition. Motion patterns as standing up, sitting down, walking forward can be performed. We implemented two types BCIs, one based on steady-state visual evoked potentials, which used canonical correlation analysis extract frequency subject focused on. other BCI is...

In dynamic manufacturing and warehousing environments, the work scene made it impossible for workers to sit, so suffer from muscle fatigue of lower limb caused by standing or squatting a long period time. this paper, semi-active exoskeleton used reduce was designed evaluated. (i) Background: The advantages disadvantages assistive exoskeletons developed industrial purposes were introduced. (ii) Simulation: process simulated in AnyBody.7.1 software, result showed that activity gluteus maximus,...

In the intelligent production line network communication process of Industrial IoT, node congestion will cause quality to decrease, thereby affecting efficiency. Therefore, accurately predicting status and making adjustments in real time is great significance improving communication. Aiming at urgent problem line, this paper proposes a prediction algorithm for line. The uses ARMA model predict data, calculates predicts entire operation through optimized BP neural network. At same time, an...

This paper presents a bioinspired lower extremity exoskeleton robot. The proposed robot can be adjusted in structure to meet the wearer’s height of 150–185 cm and has good gait stability. In control part, method identifying different locomotion modes is proposed; five common are considered this paper, including sitting down, standing up, level‐ground walking, ascending stairs, descending stairs. identification depended on angle information hip, knee, ankle joints. A deep mode model (DLMIM)...

Gait phase estimation is important technology in controlling the exoskeleton robot to assist elderly walking. Several kinds of methods have been proposed, however, previously proposed were mainly aiming at one kind walking task, e.g., level ground There are only a few studies continuous gait during multilocomotion tasks. In this article, we design estimator based on adaptive oscillator (AO) network. order overcome problem that traditional AO does not converge or converges slowly when task...

People who suffer from paraplegia completely lose sensory and locomotor functions; there are no known treatment methods for their recovery at this time. Exoskeleton robots have the potential to dramatically improve ability of these individuals. Although some exoskeleton paraplegic patients been commercialized able restore walking motion present, pilot must acquire maintain balance shift weight using forearm crutches, which is very challenging paraplegics. To make easier, we propose a new...

In the lower limb exoskeleton assistance system, motion intention understanding based on biological signals is human-computer interface's (HMI) key technology. Due to close coupling of human and machine, wheelchair-type control modes (combination intentions switches different actions) are not applicable. For example, right/left-hand motor imagery (MI) controls move forward/stop. There a mismatch between MI-based instructions actual actions because forward process alternates left right....

While walking with fast speed aims to promote health and fitness of individuals, the potential risk on lower limb joint loading across is still unknown. In order determine contact force associated different speeds, fifteen young male female participants performed barefoot speeds (regular = 1.1 m/s, medium 1.4 1.7 m/s). The synchronized motion ground reaction (GRF) data were captured by Codamotion capture system AMTI platform. All kinematics GRF information input AnyBody musculoskeletal model...

Robust gait phase prediction is crucial to exoskeleton robots, as it detects the intention of users and improves lag motion signals. Therefore, this paper predicts phases from two perspectives, including one perspective spatial features other spatio-temporal features. We employ machine learning models perspectives predict. One support vector (SVM) optimized by particle swarm optimization (PSO) algorithm, only focuses on joint information. Another nonlinear autoregressive with external inputs...

Soft lower limb exoskeletons (LLEs) are wearable devices that have good potential in walking rehabilitation and augmentation. While a few studies focused on the structure design assistance force optimization of soft LLEs, rarely work has been conducted hardware circuits design. The main purpose this is to present new LLE for efficiency improvement introduce its A hip flexion system with scalability were proposed. To assess efficacy LLE, experimental tests evaluate sensor data acquisition,...

Motor imagery-based brain-computer interface (MI-BCI) is considered to be the most promising technology, which can help patients with muscle disorders carry out rehabilitation training and assist in activities of daily living. However, time window frequency band ERD/ERS pattern activated by motor imagery vary from person person. In this study, we propose a power spectrum difference-based time-frequency sub-band selection (PSPD) method, further improve classification performance MI EEG. To...

The gait phase classification method is a key technique to control an exoskeleton robot. Different people have different features while wearing robot due the gap between and wearer their operation habits, such as correspondence joint angle moment at which foot contacts ground, amplitude of others. In order enhance performance in using only hip knee joints, kernel recursive least-squares (KRLS) algorithm introduced build model. We also assist torque predictor based on KRLS this work...

Electroencephalography (EEG)-based motor imagery (MI) brain-computer interface (BCI) is a bridge in the instruments of rehabilitation and assistance field to control external assist devices without stimulation. Feature extraction (FE) key improving performance EEG MI decoding. Existing FE methods usually extract single-domain features such as spatial, frequency features, or dual-domain time–frequency features. However, multidomains which describe intent more comprehensively are not...

Multi-sensor based motion tracking is of great interest to the robotics community as it may lessen need for expensive optical capture equipment. However, traditional convolution algorithms have difficulty adapting data due changes joints' relative position during motion. The time-series networks often used in past ignore spatial characteristics sensors. We tackle this challenge by combining long short-term memory (LSTM) with graph network (GCN), adding prior knowledge sensor distribution,...

In this paper, we design a novel knee exoskeleton. The designed exoskeleton has 1 DOF with joint actuated in the sagittal plane. is base on Series Elastic Actuator (SEA) instead of traditonal stiff actuator. SEA compliant actuator, having advantages low output impedance, friction, high quality force control and backdrivability. Thanks to these nice characteristics, it easy realize safe friendly human-machine interaction compare order achieve goal assistance as needed, robust must be...

It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for patients with lower limb disability. Lower extremity exoskeleton has been proven be efficient provide highly repeatable accurate exercise, but most existing exoskeletons' trajectories won't vary users. This paper proposes an algorithm, named as cell based individualized trajectory generation (GC-IGTG), purpose offering reference on body parameters...

The design and development of new exoskeleton robots can help patients with lower limb paralysis realize autonomous walking. During the motion an robot carrying patients, inertia hip joint will have time-varying characteristics, which cause fluctuations in rotation angle affect walking stability robot. In this paper, we present control strategy for assisted by paraplegic BP neural network tuning strategy. First, based on skeleton structure human limbs, 12 degrees freedom is designed...

This study examined the differences of muscle strength, electromyography (EMG) and whole-body kinematics during maximum cross-step table tennis topspin between advanced intermediate players. Ten ten players performed both voluntary isokinetic contraction test forehand strokes with maximum-effort towards cross-court target zone. The results indicated that generated significantly greater racket speeds forward swing phase (P < 0.05). At instant stroke, smaller shoulder horizontal flexion elbow...

Motor imagery brain-computer interface system based on Electroencephalogram (EEG) is an effective way to help the disabled recover part of their motor abilities. However, decoding movement intention contained in EEG signal accurately presents many challenges. In this paper, we propose a time-frequency decomposition-based weighted ensemble learning (TFDWEL) method, which aims improve classification performance signals. The TFDWEL method divides into multiple subsets, and uses four processing...

Abstract Aiming at the issues that affect gait recognition, such as outfit changes and carry-on-objects during this paper proposes a recognition method based on improved GaitSet network, which relies fusion of human posture contour. This introduces key points posture, improves precision contour extraction by introducing posture. At same time, map composed is used synchronous attribute to extract features. Because focus inherent walking characteristics body, they are not affected external...