Biped Gait Stability Classification Based on the Predicted Step Viability.

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.

Shoulder muscles electromyographic responses in automotive workers wearing a commercial exoskeleton.

Work-related musculoskeletal disorders (MSDs) are a major concern in industries and working environments. They cause not only suffering to the employee and decrease in performance, but also high economic losses to the companies and the society. Workers from assembly lines and machine operators are one of the most frequently affected working population. Moreover, one of the main types of MSDs in occupational environments are shoulder injuries. Exoskeletons have been applied and tested in rehabilitation and they are gaining ground in occupational environments as assistive devices to augment human force and minimize loads on muscles and joints. However, more evidence about the effects of several exoskeletons models in assisting different tasks is needed. We measured shoulder muscles activity (AD - anterior deltoid and MD - medial deltoid) of seven automotive workers using the SuitX® upper limb exoskeleton while performing different screwing tasks, at different shoulder levels while handling different tools. We found significant muscle activity reduction for 2 of the 4 proposed tasks, suggesting a task-specificity effectiveness. Therefore, it seems to be a viable option to reduce muscle effort in certain tasks.