In wearable robots, the application of surface electromyography (sEMG) signals in motion intention recognition is a hot research issue. To improve the viability of human–robot interactive perception and to reduce the complexity of the knee joint angle estimation model, this paper proposed an estimation model for knee joint angle based on the novel method of multiple kernel relevance vector regression (MKRVR) through offline learning. The root mean square error, mean absolute error, and R2_score are used as performance indicators. By comparing the estimation model of MKRVR and least squares support vector regression (LSSVR), the MKRVR performs better on the estimation of the knee joint angle. The results showed that the MKRVR can estimate the knee joint angle with a continuous global MAE of 3.27° ± 1.2°, RMSE of 4.81° ± 1.37°, and R2 of 0.8946 ± 0.07. Therefore, we concluded that the MKRVR for the estimation of the knee joint angle from sEMG is viable and could be used for motion analysis and the application of recognition of the wearer’s motion intentions in human–robot collaboration control.
2 September 2023 in Journal of Intelligent & Robotic Systems
End effectors like firearms, cameras and fire water guns can be classified as pointing end effectors. When installed on wearable manipulators, a new function can be given to the wearer. Different from gripper end effectors (GEEs), target pointing end effectors (TPEEs) have different working tasks, and the requirements for path planning are also different. There is very limited research on wearable manipulators with TPEEs. Meanwhile, manipulator with GEE path planning tends to be mature, but with a relatively low efficiency concerning its algorithm in solving high-dimensional problems. In this paper, a degree of freedom (DOF) allocation scheme and a path planning strategy (unlike manipulator with gripper end effector) were proposed for manipulators with a target pointing end effector in order to reduce the difficulty of path planning. Besides, this paper describes a new algorithm-dimension rapid-exploration random tree (dimension-RRT) to divide the manipulator DOFs into groups and unify DOFs groups by adding a fake time. The dimension-RRT was compared with the rapid-exploration random tree star algorithm (RRT*) in the same simulation environment; when there are 500 random points, the dimension-RRT time consumption is 0.556 of RRT* and the path length is 0.5 of RRT *. To quickly obtain a path that can avoid the human body, dynamic movement primitives (DMPs) were used to simulate typical spatial motion path and obstacle avoidance path efficiently.
8 May 2023 in Journal of Electrical Engineering & Technology
A novel hand gesture recognition framework based on surface electromyography (sEMG) is proposed for soldier operational scenarios under small-sample conditions. The framework integrates Empirical Mode Decomposition (EMD) for signal reconstruction, histogram-based features, and the Deep Forest (DF) classifier. Evaluations are conducted under two protocols: subject-wise evaluation and mixed-subject nested 8-fold cross-validation. Under subject-wise evaluation, the proposed EMD-HIST-DF method achieves 99.94% accuracy with 0.00027 ms per sample. Under mixed-subject nested 8-fold cross-validation, 98.41% accuracy is maintained with 0.00053 ms per sample. Ablation studies confirm the significant contribution of EMD-based signal enhancement in the mixed-subject setting (approximately 10.6 percentage points, p < 0.001). Parameter sensitivity analysis guides optimal parameter selection, and statistical tests confirm significant performance gains over baseline methods. Confusion matrices illustrate high per-class accuracy with minimal inter-class confusion. The framework shows potential as a promising solution for accurate, efficient, and sample-sparing gesture recognition in resource-constrained environments such as supernumerary robotic limb control.
This study presents a methodology for the extraction of Mechanomyography (MMG) signals and their subsequent application in estimating the rotational angles of the shoulder and elbow joints. To mitigate modal aliasing artifacts during the extraction of MMG signals, an enhanced version of the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (denoted as ICEEMDAN) has been introduced. Comparative analysis of ICEEMDAN and six decomposition algorithms revealed that ICEEMDAN yielded the lowest envelope entropy at 8.033. Consequently, the ICEEMDAN algorithm effectively isolated MMG signals from the raw acceleration signals, achieving an optimal balance between maximizing artifact rejection and minimizing signal distortion. To mitigate the economic burden associated with the training of estimation models, the Broad Learning System (BLS) has been introduced. This system facilitates iterative training through the incremental addition of nodes to both the feature layer and the enhancement layer, thereby enhancing the efficiency of the training process. The estimation precision of the BLS model was enhanced through the optimization of its parameters via the application of the Slime Mould Algorithm (SMA). This investigation revealed that the typical center frequency for MMG ranged between 10 and 100 Hz. Moreover, the estimation model founded on the SMA-BLS technique exhibited a minimum coefficient of determination (R2) value of 0.971. This model effectively estimated the rotational angles of the shoulder joints.