This paper investigates how predictions of a convolutional neural network (CNN) suited for myoelectric simultaneous and proportional control (SPC) are affected when training and testing conditions differ. We used a dataset composed of electromyogram (EMG) signals and joint angular accelerations measured from volunteers drawing a star. This task was repeated multiple times using different combinations of motion amplitude and frequency. CNNs were trained with data from a given combination and tested under different combinations. Predictions were compared between situations in which training and testing conditions matched versus when there was a training-testing mismatch. Changes in predictions were assessed through three metrics: normalized root mean squared error (NRMSE), correlation, and slope of the linear regression between targets and predictions. We found that predictive performance declined differently depending on whether the confounding factors (amplitude and frequency) increased or decreased between training and testing. Correlations dropped as the factors decreased, whereas slopes deteriorated when factors increased. NRMSEs worsened when factors increased or decreased, with more accentuated deterioration for increasing factors. We argue that worse correlations could be related to differences in EMG signal-to-ratio (SNR) between training and testing, which affected the noise robustness of the CNNs' learned internal features. Slope deterioration could be a result of the networks' inability to predict accelerations outside the range seen during training. These two mechanisms may also asymmetrically increase NRMSE. Finally, our findings open further possibilities to develop strategies to mitigate the negative impact of confounding factor variability on myoelectric SPC devices.

In this paper, we address the challenge of ensuring stability in bipedal walking robots and exoskeletons. We explore the feasibility of real-time implementation for the Predicted Step Viability algorithm (PSV), a complex multi-step optimization criterion for planning future steps in bipedal gait. To overcome the high computational cost of the PSV algorithm, we performed an analysis using 11 classification algorithms and a stacking strategy to predict if a step will be stable or not. We generated three datasets of increasing complexity through PSV simulations to evaluate the classification performance. Among the classifiers, k Nearest Neighbors, Support Vector Machine with Radial Basis Function Kernel, Decision Tree, and Random Forest exhibited superior performance. Multi-Layer Perceptron also consistently performed well, while linear-based algorithms showed lower performance. Importantly, the use of stacking did not significantly improve performance. Our results suggest that the feature vector applied with this approach is applicable across various robotic models and datasets, provided that training data is balanced and sufficient points are used. Notably, by leveraging classifiers, we achieved rapid computation of results in less than 1 ms, with minimal computational cost.

The prediction of the stability of future steps taken by a biped robot is a very important task, since it allows the robot controller to adopt the necessary measures in order to minimize damages if a fall is predicted. We present a classifier to predict the viability of a given planned step taken by a biped robot, i.e., if it will be stable or unstable. The features of the classifier are extracted from a feature engineering process exploiting the useful information contained in the time series generated in the trajectory planning of the step. In order to state the problem as a supervised classification one, we need the ground truth class for each planned step. This is obtained using the Predicted Step Viability (PSV) criterion. We also present a procedure to obtain a balanced and challenging training/testing dataset of planned steps that contains many steps in the border between stable and non stable regions. Following this trajectory planning strategy for the creation of the dataset we are able to improve the robustness of the classifier. Results show that the classifier is able to obtain a 95% of ROC AUC for this demanding dataset using only four time series among all the signals required by PSV to check viability. This allows to replace the PSV stability criterion, which is safe, robust but impossible to apply in real-time, by a simple, fast and embeddable classifier that can run in real time consuming much less resources than the PSV.

Robot locomotion relies on real-time decision-making to preserve stability and ensure continuous movement even in the presence of disturbances. In this work, we present a modular machine learning (ML)–based framework by developing methods to apply the Predicted Step Viability (PSV) algorithm in real-time to generate suboptimal gaits for a bipedal robot. PSV is an optimal stability criterion and trajectory planning algorithm that uses the complete robot model to solve a multi-stage optimization problem, ensuring not only the optimal current step but also the existence and stability of future steps. Due to its computational complexity, PSV cannot be used in real-time control. We address the leg trajectory planning problem by introducing three interconnected ML models: (i) a multilayer perceptron estimates the probability that a configuration is recoverable, optimized under physical constraints, which is used to find the most stable configuration that can be reached at the end of the step; (ii) a bidirectional long short‑term memory (LSTM) network predicts the step duration from partial time-series observations; and (iii) another LSTM predicts the control trajectory required to execute a step, conditioned on start and target configurations and the predicted duration. Simulations on a planar, five‑segment bipedal robot demonstrate high predictive accuracy and the ability to generate dynamically feasible trajectories that ensure stability in real-time. Compared with baseline PSV control simulated without real-time constraints, the proposed ML framework provides real-time embeddable, modular, and versatile trajectory planning and stability assessment modules that can be applied to different bipedal robots.

Control remains a challenge in precision applications in robotics, particularly when combined with execution in small time intervals. This study employed a two-degree-of-freedom (2-DoF) planar robotic arm driven by a detailed human musculoskeletal model for actuation, incorporating nonlinear control techniques to execute a precision task through simulation. Then, we compared these simulations with real experimental data from healthy subjects performing the same task. Our results show that the Feedback Linearization Control (FLC) applied performed satisfactorily within the task execution constraints compared to a robust nonlinear control technique, i.e., Sliding Mode Control (SMC). On the other hand, differences can be observed between the behavior of the simulated model and the real experimental data, where discrepancies in terms of errors were found. The model errors increased with the amplitude and remained unchanged with any increase in the task execution frequency. However, in human trials, the errors increased both with the amplitude and, notably, with a drastic rise in frequency.