This study examines the efficacy of gesture-based versus touch-based control interfaces in managing unanticipated scenarios in human-robot collaborative assembly (HRCA). As collaborative robots (cobots) become increasingly integrated into industrial environments, there is a need for control interfaces that enable workers to respond to unanticipated deviations from the assembly process. Such control interfaces must be intuitive to use, acceptable to the worker, and not result in an increased workload. We conducted a controlled experiment with 30 participants, comparing the performance of gesture-based against touch-based control interfaces in an assembly task, which included simulated disruptions. Workload was evaluated using the NASA Task Load Index (NASA-TLX), and acceptance via a Technology Acceptance Model (TAM), adapted for HRCA. The results demonstrate no statistically significant differences between the two measures. However, they indicate that touch control results in a lower workload and higher user acceptance, which may be attributed to users' familiarity with touch interfaces.

Human-Robot Collaboration (HRC) in dynamic assembly environments requires intuitive communication for seamless interactions. Eye gaze, a nonverbal cue, is critical for interpreting human intent and enhancing robot adaptability. This research introduces a three-tier framework categorizing eye gaze into fixation, scanning, and task-switching behaviors, aiming to improve real-time robot responsiveness. Preliminary evaluations with multiple human subjects demonstrated the potential of this classification to enhance task alignment and detect anomalies in human behavior. Future work will explore automated personalization of the algorithm for individuals and integrate multimodal data to refine adaptability in human-robot collaborative systems.

In nonlinear regression with machine learning methods, neural networks (NNs) are ideally suited due to their universal approximation property, which states that arbitrary nonlinear functions can thereby be approximated arbitrarily well. Unfortunately, this property also poses the problem that data points with measurement errors can be approximated too well and unknown parameter subspaces in the estimation can deviate far from the actual value (so-called overfitting). Various developed methods aim to reduce overfitting through modifications in several areas of the training. In this work, we pursue the question of how an NN behaves in training with respect to overfitting when linear and nonlinear transfer functions (TF) are alternated in different hidden layers (HL). The presented approach is applied to a generated dataset and contrasted to established methods from the literature, both individually and in combination. Comparable results are obtained, whereby the common use of purely nonlinear transfer functions proves to be not recommended generally.