InverseMuscleNET: Alternative Machine Learning Solution to Static Optimization and Inverse Muscle Modeling

InverseMuscleNET, a machine learning model, is proposed as an alternative to static optimization for resolving the redundancy issue in inverse muscle models. A recurrent neural network (RNN) was optimally configured, trained, and tested to estimate the pattern of muscle activation signals. Five biomechanical variables (joint angle, joint velocity, joint acceleration, joint torque, and activation torque) were used as inputs to the RNN. A set of surface electromyography (EMG) signals, experimentally measured around the shoulder joint for flexion/extension, were used to train and validate the RNN model. The obtained machine learning model yields a normalized regression in the range of 88–91% between experimental data and estimated muscle activation. A sequential backward selection algorithm was used as a sensitivity analysis to discover the less dominant inputs. The order of most essential signals to least dominant ones was as follows: joint angle, activation torque, joint torque, joint velocity, and joint acceleration. The RNN model required 0.06 s of the previous biomechanical input signals and 0.01 s of the predicted feedback EMG signals, demonstrating the dynamic temporal relationships of the muscle activation profiles. The proposed approach permits a fast and direct estimation ability instead of iterative solutions for the inverse muscle model. It raises the possibility of integrating such a model in a real-time device for functional rehabilitation and sports evaluation devices with real-time estimation and tracking. This method provides clinicians with a means of estimating EMG activity without an invasive electrode setup.

Research on the Application of Intelligent Choreography for Musical Theater Based on Mixture Density Network Algorithm

Musical choreography is usually completed by professional choreographers, which is very professional and time-consuming. In order to realize the intelligent choreography of musical, based on the mixed density network (MDN), this paper generates the dance matching with the target music through three steps: motion generation, motion screening, and feature matching. The choreography results in this paper have a high degree of matching with music, which makes it possible for the development of motion capture technology and artificial intelligence and computer automatic choreography based on music. In the process of motion generation, the average value of Gaussian model output by MDN is used as the bone position and the consistency of motion is measured according to the change rate of joint velocity in adjacent frames in the process of motion selection. Compared with the existing studies, the dance generated in this paper has improved in motion coherence and realism. In this paper, a multilevel music and action feature matching algorithm combining global feature matching and local feature matching is proposed. The algorithm improves the unity and coherence of music and action. The algorithm proposed in this paper improves the consistency and novelty of movement, the compatibility with music, and the controllability of dance characteristics. Therefore, the algorithm in this paper technically changes the way of artistic creation and provides the possibility for the development of motion capture technology and artificial intelligence.

On the Structural Constraint and Motion of 3-PRS Parallel Kinematic Machines

This paper presents a consistent analytic kinematic formulation of the 3-PRS parallel manipulator (PM) with a parasitic motion by embedding the velocity level structural constraint equation into the motion expression. Inverse rate kinematics (IRK) is solved with a simple constraint compatible velocity profile, which is obtained by projecting the instantaneous restriction space onto the motion space. Moreover, the systematic method to reveal the parasitic motion is introduced. Thus, the parasitic terms are automatically identified from the main motions. Unlike the usual approach, this study does not consider any explicit parasitic motion expression. Consequently, the derivation of constraint compatible input velocity, which comprises the parasitic term, is simplified. To incorporate the parasitic motion into the task velocity, constraint Jacobian of the manipulator is analytically obtained first. The manipulator Jacobian is extended to incorporate the passive joint’s information apart from the active joints and structural constraint. Hence, the dimension of the Jacobian matrix used to solve IRK is 9 × 6. The validity of the IRK is proved by the Bordered Gramian based forward rate kinematics (FRK). Then, an accurate numerical integration, RK4, is applied to the joint velocity of IRK to obtain the manipulator’s joint values. Consequently, the moving plate’s pose is obtained via forward position kinematics computed using integrated active and passive joint values for validation. The projection matrix used to get compatible constraint motion adjusts our input velocity and makes it compatible with the structural constraint policy, and the parasitic motion is embedded easily. Thus, an explicit formulation of the parasitic motion equation is not required, as the usual practice. Finally, the study presented numerical simulations to show the validity of the outlined resolutions. This paper’s result and analysis can be uniformly applied to other parallel manipulators with less than 6 DoFs.

Motion Planning of Nonholonomic Mobile Manipulators with Manipulability Maximization Considering Joints Physical Constraints and Self-Collision Avoidance

The motion of nonholonomic mobile manipulators (NMMs) is inherently constrained by joint limits, joint velocity limits, self-collisions and singularities. Most motion planning algorithms consider some of the aforementioned constraints, however, a unified framework to deal with all of them is lacking. This paper proposes a motion planning solution for the kinematic trajectory tracking of redundant NMMs that include all the constraints needed for practical implementation, which improves the manipulability of both the entire system and the manipulator to prevent singularities. Experiments using a 10-DOF NMM demonstrate the good performance of the proposed method for executing 6-DOF trajectories while satisfying all the constraints and simultaneously maximizing manipulability.

MuscleNET: Mapping Electromyography to kinematic and dynamic biomechanical variables by machine learning

Objective: This paper proposes machine learning models for mapping surface electromyography (sEMG) signals to regression of joint angle, joint velocity, joint acceleration, joint torque, and activation torque. Approach: The regression models, collectively known as MuscleNET, take one of four forms: ANN (Forward Artificial Neural Network), RNN (Recurrent Neural Network), CNN (Convolutional Neural Network), and RCNN (Recurrent Convolutional Neural Network). Inspired by conventional biomechanical muscle models, delayed kinematic signals were used along with sEMG signals as the machine learning model's input; specifically, the CNN and RCNN were modeled with novel configurations for these input conditions. The models' inputs contain either raw or filtered sEMG signals, which allowed evaluation of the filtering capabilities of the models. The models were trained using human experimental data and evaluated with different individual data. Main results: Results were compared in terms of regression error (using the root-mean-square) and model computation delay. The results indicate that the RNN (with filtered sEMG signals) and RCNN (with raw sEMG signals) models, both with delayed kinematic data, can extract underlying motor control information (such as joint activation torque or joint angle) from sEMG signals in pick-and-place tasks. The CNNs and RCNNs were able to filter raw sEMG signals. Significance: All forms of MuscleNET were found to map sEMG signals within 2 ms, fast enough for real-time applications such as the control of exoskeletons or active prostheses. The RNN model with filtered sEMG and delayed kinematic signals is particularly appropriate for applications in musculoskeletal simulation and biomechatronic device control.

A Robot-Centered Path-Planning Algorithm for Multidirectional Additive Manufacturing for WAAM Processes and Pure Object Manipulation

Previous algorithms for slicing, path planning or trajectory planning of additive manufacturing cannot be used consistently for multidirectional additive manufacturing with pure object manipulation in wire-arc additive manufacturing. This work presents a novel path planning approach that directly takes robot kinematics into account and thus ensures the reachability of all critical path poses. In an additional step, the planned path segments are smoothed so that joint velocity limits are respected. It is shown that the implemented path planner generates executable robot paths and at the same time maintains the process quality (in this case, sufficient coverage of the slice area). While the introduced method enables the generation of reachable printing paths, the smoothing algorithm allows for the execution of the path with respect to the robot’s velocity limits and at the same time improves the slice coverage. Future experiments will show the realization of the real robot setup presented.

The Human walking kinematic model combined with upper and lower limb movement

The purpose of this study is to build a relatively complete human walking kinematic model. This model is combined with the rolling-foot model (lower limb) and multi-rod swinging model (upper limb) connected by COM. We calculated the velocity of COM and other critical joints of the upper limb by marker point capture experiment using the high-speed camera. This research shows that the hand joint velocity measured through the experiment can achieve high coincidence with that calculated by the theoretical model given specific inputs. Moreover, the common pattern of upper limb angles is also studied for an accurate description. The proposed kinematic model is expected to forecast desired motion intention for better compliance by the rehabilitation and assistive robots.