Massage therapy is helpful for the rehabilitation of various diseases, such as headaches caused by migraines and stress. Existing robotic systems have focused on massage therapy on the torso and limbs, but performing massage motions through suitable actuation on a person’s head has been a challenge. In this paper, we present MiBOT, a head-worn massage robot that actuates two soft tactors to produce touch motions mimicking human massage. A key design principle behind MiBOT is its silent actuation, which we achieve through pneumatic artificial muscles in conjunction with a controller loop to respond to contact pressure. We evaluated the effectiveness of MiBOT in a controlled study and assessed subjects’ blood pressure and heart rate levels while applying MiBOT. We found that our mechanical system generated positive and conclusive quantitative outcomes that are similar to the human-administered massage, decreasing participants’ mean systolic and diastolic blood pressure by 2.8 mmHg and 1.7 mmHg, respectively, as well as calming their heart rate by 8–10% on average.

In mobile eye-tracking, visual attention is commonly evaluated using fixation-based measures, which can be mapped to predefined objects of interest for task-specific attention analysis. Even though attention can be directed independently from the fovea, little research can be found on the quantification of peripheral vision for attention analysis. In this work, we discuss the benefits of enhancing traditional mapping methods with near-peripheral information and expand previous research by presenting a novel machine learning-based gaze measure, the visual attention index (VAI), for the analysis of visual attention using dynamic stimuli. Results are discussed using the data of two multi-object mobile eye tracking use cases and visualized using radar graphs.

Abstract Deep learning models have shown remarkable performances in egocentric video-based action recognition (EAR), but rely heavily on a large quantity of training data. In specific applications with only limited data available, eye movement data may provide additional valuable sensory information to achieve accurate classification performances. However, little is known about the effectiveness of gaze data as a modality for egocentric action recognition. We, therefore, propose the new Peripheral Vision-Based HMM (PVHMM) classification framework, which utilizes context-rich and object-related gaze features for the detection of human action sequences. Gaze information is quantified using two features, the object-of-interest hit and the object–gaze distance, and human action recognition is achieved by employing a hidden Markov model. The classification performance of the framework is tested and validated on a safety-critical medical device handling task sequence involving seven distinct action classes, using 43 mobile eye tracking recordings. The robustness of the approach is evaluated using the addition of Gaussian noise. Finally, the results are then compared to the performance of a VGG-16 model. The gaze-enhanced PVHMM achieves high classification performances in the investigated medical procedure task, surpassing the purely image-based classification model. Consequently, this gaze-enhanced EAR approach shows the potential for the implementation in action sequence-dependent real-world applications, such as surgical training, performance assessment, or medical procedural tasks.

Emerging Augmented Reality headsets incorporate gaze and hand tracking and can, thus, observe the user’s behavior without interfering with ongoing activities. In this paper, we analyze hand-eye coordination in real-time to predict hand actions during target selection and warn users of potential errors before they occur. In our first user study, we recorded 10 participants playing a memory card game, which involves frequent hand-eye coordination with little task-relevant information. We found that participants’ gaze locked onto target cards 350ms before the hands touched them in 73.3% of all cases, which coincided with the peak velocity of the hand moving to the target. Based on our findings, we then introduce a closed-loop support system that monitors the user’s fingertip position to detect the first card turn and analyzes gaze, hand velocity and trajectory to predict the second card before it is turned by the user. In a second study with 12 participants, our support system correctly displayed color-coded visual alerts in a timely manner with an accuracy of 85.9%. The results indicate the high value of eye and hand tracking features for behavior prediction and provide a first step towards predictive real-time user support.

Mechanical compliance is important for a robust and safe physical interaction of robots with humans and unstructured environments. Using adjustable stiffness, the advantages of compliant and stiff systems can be combined and thus the versatility of a robot increased. The realisation of adjustable stiffness in robot joints through compliant mechanisms shows several advantages over active control approaches, especially in terms of robustness. The compactness of adjustable stiffness mechanisms (ASMs) is important for their integration in robotic systems. An important aspect of compactness in ASMs is the storable work per volume, i.e. the work density. Therefore we propose a set of benchmarks to analyse the work density of elastic mechanisms on different design levels. The application of these benchmarks is demonstrated on a novel ASM, which is part of the adjustable impedance element AIE Uno, and on DLR's FSJ. The analysis of these ASMs demonstrates the application and the benefit of the proposed benchmarks. The benchmarks support the choice between alternative solutions and the identification of improvement potential in an existing design.