In this paper, we present a synchronization approach to trajectory tracking of multiple mobile robots while maintaining time-varying formations. The main idea is to control each robot to track its desired trajectory while synchronizing its motion with those of other robots to keep relative kinematics relationships, as required by the formation. First, we pose the formation-control problem as a synchronization control problem and identify the synchronization control goal according to the formation requirement. The formation error is measured by the position synchronization error, which is defined based on the established robot network. Second, we develop a synchronous controller for each robot's translation to guarantee that both position and synchronization errors approach zero asymptotically. The rotary controller is also designed to ensure that the robot is always oriented toward its desired position. Both translational and rotary controls are supported by a centralized high-level planer for task monitoring and robot global localization. Finally, we perform simulations and experiments to demonstrate the effectiveness of the proposed synchronization control approach in the formation control tasks.

Neural implicit fields are powerful for representing 3D scenes and generating high-quality novel views, but it remains challenging to use such implicit representations for creating a 3D human avatar with a specific identity and artistic style that can be easily animated. Our proposed method, AvatarCraft, addresses this challenge by using diffusion models to guide the learning of geometry and texture for a neural avatar based on a single text prompt. We carefully design the optimization framework of neural implicit fields, including a coarse-to-fine multi-bounding box training strategy, shape regularization, and diffusion-based constraints, to produce high-quality geometry and texture. Additionally, we make the human avatar animatable by deforming the neural implicit field with an explicit warping field that maps the target human mesh to a template human mesh, both represented using parametric human models. This simplifies animation and reshaping of the generated avatar by controlling pose and shape parameters. Extensive experiments on various text descriptions show that AvatarCraft is effective and robust in creating human avatars and rendering novel views, poses, and shapes. Our project page is: https://avatar-craft.github.io/.

In this paper, we propose to use brain-computer interface (BCI) to 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, and walking forward can be performed. We implemented two types of BCIs, one based on steady-state visual evoked potentials, which used canonical correlation analysis to extract the frequency the subject focused on. The other BCI is based on motor imagery, where the common spatial patterns method was employed to extract the features from the EEG signal. Then, the features were classified by support vector machine to recognize the intention of the subject. We invited four healthy subjects to participate in the experiments, including off-line and online. The off-line experiments trained the classifier and then were used online to test the performance of the BCI controlled exoskeleton system. The results showed high accuracy rate in motion intention classification tasks for both BCIs.

Gait phase is widely used for gait trajectory generation, gait control and gait evaluation on lower-limb exoskeletons. So far, a variety of methods have been developed to identify the gait phase for lower-limb exoskeletons. Angular sensors on lower-limb exoskeletons are essential for joint closed-loop controlling; however, other types of sensors, such as plantar pressure, attitude or inertial measurement unit, are not indispensable.Therefore, to make full use of existing sensors, we propose a novel gait phase recognition method for lower-limb exoskeletons using only joint angular sensors. The method consists of two procedures. Firstly, the gait deviation distances during walking are calculated and classified by Fisher’s linear discriminant method, and one gait cycle is divided into eight gait phases. The validity of the classification results is also verified based on large gait samples. Secondly, we build a gait phase recognition model based on multilayer perceptron and train it with the phase-labeled gait data. The experimental result of cross-validation shows that the model has a 94.45% average correct rate of set (CRS) and an 87.22% average correct rate of phase (CRP) on the testing set, and it can predict the gait phase accurately. The novel method avoids installing additional sensors on the exoskeleton or human body and simplifies the sensory system of the lower-limb exoskeleton.

This article presents a graph convolutional network model (GCNM) for gait phase classification to control a lower limb exoskeleton. The GCNM can recognize four leg phases between the foot and ground, including heel strike, foot flat, heel off, and swing. The proposed model can solve the gait phase classification problem from non-Euclidean domain based on a graph mechanism for exoskeletons. Real-time performance of the gait data acquisition system was then verified on a lower limb exoskeleton. The system quantifies the time delay with an optoelectronic system, VICON BONITA 10. Comparison works with some existing state-of-the-art methods from the Euclidean domain, i.e., long short-term memory (LSTM) and deep convolutional neural network (DCNN), were also provided. Experimental works show that the proposed model has a significantly higher prediction accuracy and better robustness in gait phase classification for different people in level, uphill, and downhill environments. Moreover, the label rate is under ${\rm {10}}{\rm {\% }}$ , compared to LSTM and DCNN, which are usually at ${\rm {70}}$ – ${\rm {80}}{\rm {\% }}$ . Finally, the GCNM's maximum accuracy of gait phase classification is ${\rm {97}}{\rm {.43\% }}$ ; thus, the effectiveness of the proposed model is verified.

Continuous joint angle estimation based on a surface electromyography (sEMG) signal can be used to improve the man-machine coordination performance of the exoskeleton. In this study, we proposed a time-advanced feature and utilized long short-term memory (LSTM) with a root mean square (RMS) feature and its time-advanced feature (RMSTAF; collectively referred to as RRTAF) of sEMG to estimate the knee joint angle. To evaluate the effect of joint angle estimation, we used root mean square error (RMSE) and cross-correlation coefficient ρ between the estimated angle and actual angle. We also compared three methods (i.e., LSTM using RMS, BPNN (back propagation neural network) using RRTAF, and BPNN using RMS) with LSTM using RRTAF to highlight its good performance. Five healthy subjects participated in the experiment and their eight muscle (i.e., rectus femoris (RF), biceps femoris (BF), semitendinosus (ST), gracilis (GC), semimembranosus (SM), sartorius (SR), medial gastrocnemius (MG), and tibialis anterior (TA)) sEMG signals were taken as algorithm inputs. Moreover, the knee joint angles were used as target values. The experimental results showed that, compared with LSTM using RMS, BPNN using RRTAF, and BPNN using RMS, the average RMSE values of LSTM using RRTAF were respectively reduced by 8.57%, 46.62%, and 68.69%, whereas the average ρ values were respectively increased by 0.31%, 4.15%, and 18.35%. The results demonstrated that LSTM using RRTAF, which contained the time-advanced feature, had better performance for estimating the knee joint motion.