Directly controlling robot motion through human–robot interaction enables the integration of human expertise into robot control. However, this requires efficient interaction methods. While previous work has shown that hand gestures offer potential for natural control, the lack of haptic feedback remains a key challenge. One solution is partial automation, in which the contact force is autonomously controlled. We implemented force automation enhanced gesture control, as well as the state-of-the-art baseline of hand-guiding, to systematically investigate hand gesture interaction for robot control. A user study (n=28) was conducted to investigate the efficiency and workload of these interaction concepts. As the interaction method efficiency may depend on task demands, two tasks with different precision requirements were evaluated in the context of robotic ultrasound. The results indicate that force automation significantly reduces perceived workload and task duration when using hand gestures. Moreover, gesture-based interaction can match the efficiency of hand-guiding for broad tasks and even outperform it in precise tasks. These findings highlight the potential of gesture-based interaction for robot control, particularly when the absence of haptic feedback is compensated by partial automation.

Robotic systems have the potential to enhance a wide range of domains, such as medical workflows, by automating individual steps of complex processes. However, human-robot interaction (HRI) is of critical importance, as effective collaboration between humans and robots is essential even in highly automated environments. Recent research has predominantly focused on the development of interaction methods rather than systematically comparing existing approaches. Therefore, we conducted a user study (n=20) to compare different HRI concepts for end effector manipulation combined with clutching mechanisms for manip-ulation activation in an alignment task using the example of robotic ultrasound (US). Manipulation methods included hand-guiding, teleoperation, and touchless interaction, while clutching mechanisms were realized through hand, voice, and foot interaction. The results indicate advantages of hand-guiding for manipulation. While no significant differences were observed between clutching mechanisms, strong evidence suggests comparable performance across these modalities. Notably, significant interaction effects on perceived workload reveal that the optimal clutching mechanism depends on the selected manipulation technique. This work underscores the critical importance of selecting appropriate HRI concepts and understanding the dependencies of manipulation techniques with clutching mechanisms. While our study included the usage of a robotic US, the insights gained are broadly transferable across various domains involving robotic manipulation tasks in human-robot collaboration.

Augmented Reality (AR) offers potential for enhancing human-robot collaboration by enabling intuitive interaction and real-time feedback. A crucial aspect of AR-robot integration is accurate spatial registration to align virtual content with the physical robotic workspace. This paper systematically investigates the effects of different tracking techniques and registration parameters on AR-to-robot registration accuracy, focusing on paired-point methods. We evaluate four marker detection algorithms - ARToolkit, Vuforia, ArUco, and retroreflective tracking - analyzing the influence of viewing distance, angle, marker size, point distance, distribution, and quantity. Our results show that ARToolkit provides the highest registration accuracy. While larger markers and positioning registration point centroids close to target locations consistently improved accuracy, other factors such as point distance and quantity were highly dependent on the tracking techniques used. Additionally, we propose an effective refinement method using point cloud registration, significantly improving accuracy by integrating data from points recorded between registration locations. These findings offer practical guidelines for enhancing AR-robot registration, with future work needed to assess the transferability to other AR devices and robots.

While collaborative robots effectively combine robotic precision with human capabilities, traditional control methods such as button presses or hand guidance can be slow and physically demanding. This has led to an increasing interest in natural user interfaces that integrate hand gesturebased interactions for more intuitive and flexible robot control. Therefore, this paper systematically explores mid-air robot control by comparing position and rate control modes with different state-of-the-art and novel sensor placements. A user study was conducted to evaluate each combination in terms of accuracy, task duration, perceived workload, and physical exertion. Our results indicate that position control is more efficient than rate control. Traditional desk-mounted sensors can provide a good balance between accuracy and comfort. However, robot-mounted sensors are a viable alternative for short-term, accurate control with less spatial requirements. Legmounted sensors, while comfortable, pose challenges to handeye coordination. Based on these findings, we provide design implications for improving the usability and comfort of midair human-robot interaction. Future research should extend this evaluation to a wider range of tasks and environments.

Extended Reality (XR) has the potential to improve efficiency and safety in the user-centered development of human-robot interaction. However, the validity of using XR prototyping for user studies for contact-intensive robotic tasks remains underexplored. These in-contact tasks are particularly relevant due to challenges arising from indirect force perception in robot control. Therefore, in this work, we investigate a representative example of such a task: robotic ultrasound. A user study was conducted to assess the transferability of results from a simulated user study to real-world conditions, comparing two force-assistance approaches. The XR simulation replicates the physical study set-up employing a virtual robotic arm, its control interface, ultrasound imaging, and two force-assistance methods: automation and force visualization. Our results indicate that while differences in force deviation, perceived workload, and trust emerge between real and simulated setups, the overall findings remain consistent. Specifically, partial automation of robot control improves performance and trust while reducing workload, and visual feedback decreases force deviation in both real and simulated conditions. These findings highlight the potential of XR for comparative studies, even in complex robotic tasks.

The lack of haptic feedback in touchless human-robot interaction is critical in applications such as robotic ultrasound, where force perception is crucial to ensure image quality. Augmented reality (AR) is a promising tool to address this limitation by providing sensory substitution through visual or vibrotactile feedback. The implementation of visual force feedback requires consideration not only of feedback design but also of positioning. Therefore, we implemented two different visualization types at three different positions and investigated the effects of vibrotactile feedback on these approaches. Furthermore, we examined the effects of multimodal feedback compared to visual or vibrotactile output alone. Our results indicate that sensory substitution eases the interaction in contrast to a feedback-less baseline condition, with the presence of visual support reducing average force errors and being subjectively preferred by the participants. However, the more feedback was provided, the longer users needed to complete their tasks. Regarding visualization design, a 2D bar visualization reduced force errors compared to a 3D arrow concept. Additionally, the visualizations being displayed directly on the ultrasound screen were subjectively preferred. With findings regarding feedback modality and visualization design our work represents an important step toward sensory substitution for touchless human-robot interaction.

This paper takes a closer look at Git Re-Basin, an interesting new approach to merge trained models.We propose a hierarchical model merging scheme that significantly outperforms the standard MergeMany algorithm.With our new algorithm, we find that Re-Basin induces adversarial and perturbation robustness into the merged models, with the effect becoming stronger the more models participate in the hierarchical merging scheme.However, in our experiments Re-Basin induces a much bigger performance drop than reported by the original authors.

Where traditional media and methods reach their limits in anatomy education, mixed-reality (MR) environments can provide effective learning support because of their high interactivity and spatial visualization capabilities. However, the underlying design and pedagogical requirements are as diverse as the technologies themselves. This paper examines the effectiveness of individual- and collaborative learning environments for anatomy education, using embryonic heart development as an example. Both applications deliver the same content using identical visualizations and hardware but differ in interactivity and pedagogical approach. The environments were evaluated in a user study with medical students (n = 90) during their examination phase, assessing usability, user experience, social interaction/co-presence, cognitive load, and personal preference. Additionally, we conducted a knowledge test before and after an MR learning session to determine educational effects compared to a conventional anatomy seminar. Results indicate that the individual learning environment was generally preferred. However, no significant difference in learning effectiveness could be shown between the conventional approach and the MR applications. This suggests that both can effectively complement traditional seminars despite their different natures. Our study contributes to understanding how different MR settings could be tailored for anatomical education.

Recent developments and research advances contribute to an ever-increasing trend towards quality levels close to what we experience in reality. In this work, we investigate how different degrees of these quality characteristics affect user performance, qualia of user experience (UX), and sense of presence in an example medical task. To this end, a two-way within-subjects design user study was conducted, in which three different levels of visual fidelity were compared. In addition, two different interaction modalities were considered: (1) the use of conventional VR controllers and (2) natural hand interaction using 3D-printed, spatially-registered replicas of medical devices, to interact with their virtual representations. Consistent results indicate that higher degrees of visual fidelity evoke a higher sense of presence and UX. However, user performance was less affected. Moreover, no differences were detected between both interaction modalities for the examined task. Future work should investigate the discovered interaction effects between quality levels and interaction modalities in more detail and examine whether these results can be reproduced in tasks that require more precision. This work provides insights into the implications to consider when studying interactions in VR and paves the way for investigations into early phases of medical product development and workflow analysis.

Presenting medical volume data using augmented reality (AR) can facilitate the identification of anatomical structures, the perception of their spatial relations and the development of mental maps compared to more commonly used monitors. However, interaction methods explored in these conventional settings may not be applicable in AR environments, or perform differently. In terms of mode activation, gestural interaction was shown to be a viable, touchless alternative to traditional input devices, which is desirable in sterile medical use cases. Therefore, we present a user study (n = 21) comparing hand and foot gestures with voice commands for the activation of interaction modes within a projector-based, spatial AR prototype to visualize medical volume data. Interaction itself was performed via hand movements captured by a data glove. Consistent, statistically significant results across measured variables suggest advantages of voice commands. In addition, a second experiment (n = 17) compared the hand-based interaction with two motion-sensitive devices held in power and in precision grip respectively. All modes were activated using voice commands. No considerable differences between tested grip styles could be determined. The findings suggest that the choice of preferable interaction devices is user and use case dependent.

In the embryonic human heart, complex dynamic shape changes take place in a short period of time on a microscopic scale, making this development difficult to visualize. However, spatial understanding of these processes is essential for students and future cardiologists to properly diagnose and treat congenital heart defects. Following a user centered approach, the most crucial embryological stages were identified and translated into a virtual reality learning environment (VRLE) to enable the understanding of the morphological transitions of these stages through advanced interactions. To address individual learning types, we implemented different features and evaluated the application regarding usability, perceived task load, and sense of presence in a user study. We also assessed spatial awareness and knowledge gain, and finally obtained feedback from domain experts. Overall, students and professionals rated the application positively. To minimize distraction from interactive learning content, such VRLEs should consider features for different learning types, allow for gradual habituation, and at the same time provide enough playful stimuli. Our work previews how VR can be integrated into a cardiac embryology education curriculum.

Surgical procedures requiring needle navigation assistance suffer from complicated hand-eye coordination and are mentally demanding. Augmented reality (AR) can help overcome these issues. How-ever, only an insufficient amount of fundamental research has focused on the design and hardware selection of such AR needle navigation systems. This work contributes to this research area by presenting a user study (n=24) comparing three state-of-the-art navigation concepts displayed by an optical see-through head-mounted display and a stereoscopic projection system. A two-dimensional glyph visualization resulted in higher targeting accuracy but required more needle insertion time. In contrast, punctures guided by a three-dimensional see-through vision concept were less accurate but faster and were favored in a qualitative interview. The third concept, a static representation of the correctly positioned needle, showed too high target errors for clinical accuracy needs. This concept per-formed worse when displayed by the projection system. Besides that, no meaningful differences between the evaluated AR display devices were detected. User preferences and use case restrictions, e.g., sterility requirements, seem to be more crucial selection criteria. Future work should focus on improving the accuracy of the see-through vision concept. Until then, the glyph visualization is recommended.

Augmented reality (AR) may be a useful technique to overcome issues of conventionally used navigation systems supporting medical needle insertions, like increased mental workload and complicated hand-eye coordination. Previous research primarily focused on the development of AR navigation systems designed for specific displaying devices, but differences between employed methods have not been investigated before. To this end, a user study involving a needle insertion task was conducted comparing different AR display techniques with a monitor-based approach as baseline condition for the visualization of navigation information. A video see-through stationary display, an optical see-through head-mounted display and a spatial AR projector-camera-system were investigated in this comparison. Results suggest advantages of using projected navigation information in terms of lower task completion time, lower angular deviation and affirmative subjective participant feedback. Techniques requiring the intermediate view on screens, i.e. the stationary display and the baseline condition, showed less favorable results. Thus, benefits of providing AR navigation information compared to a conventionally used method could be identified. Significant objective measures results, as well as an identification of advantages and disadvantages of individual display techniques contribute to the development and design of improved needle navigation systems.

Augmented reality (AR) is a promising tool to convey useful information at the place where it is needed. However, perceptual issues with augmented reality visualizations affect the estimation of distances and depth and thus can lead to critically wrong assumptions. These issues have been successfully investigated for video see-through modalities. Moreover, advanced visualization methods encoding depth information by displaying additional depth cues were developed. In this work, state-of-the-art visualization concepts were adopted for a projective AR setup. We conducted a user study to assess the concepts’ suitability to convey depth information. Participants were asked to sort virtual cubes by using the provided depth cues. The investigated visualization concepts consisted of conventional Phong shading, a virtual mirror, depth-encoding silhouettes, pseudo-chromadepth rendering and an illustrative visualization using supporting line depth cues. Besides different concepts, we altered between a monoscopic and a stereoscopic display mode to examine the effects of stereopsis. Consistent results across variables show a clear ranking of examined concepts. The supporting lines approach and the pseudo-chromadepth rendering performed best. Stereopsis was shown to provide significant advantages for depth perception, while the current visualization technique had only little effect on investigated measures in this condition. However, similar results were achieved using the supporting lines and the pseudo-chromadepth concepts in a monoscopic setup. Our study showed the suitability of advanced visualization concepts for the rendering of virtual content in projective AR. Specific depth estimation results contribute to the future design and development of applications for these systems.

The estimation of distances and spatial relations between surgical instruments and surrounding anatomical structures is a challenging task for clinicians in image-guided surgery. Using augmented reality (AR), navigation aids can be displayed directly at the intervention site to support the assessment of distances and reduce the risk of damage to healthy tissue. To this end, four distance-encoding visualisation concepts were developed using a head-mounted optical see-through AR setup and evaluated by conducting a comparison study. Results suggest the general advantage of the proposed methods compared to a blank visualisation providing no additional information. Using a Distance Sensor concept signalising the proximity of nearby structures resulted in the least time the instrument was located below 5mm to surrounding risk structures and yielded the least amount of collisions with them.

Augmented reality (AR) is a promising tool to improve instrument navigation in needle-based interventions. Limited research has been conducted regarding suitable navigation visualizations. In this work, three navigation concepts based on existing approaches were compared in a user study using a projective AR setup. Each concept was implemented with three different scales for accuracy-to-color mapping and two methods of navigation indicator scaling. Participants were asked to perform simulated needle insertion tasks with each of the resulting 18 prototypes. Insertion angle and insertion depth accuracies were measured and analyzed, as well as task completion time and participants' subjectively perceived task difficulty. Results show a clear ranking of visualization concepts across variables. Less consistent results were obtained for the color and indicator scaling factors. Results suggest that logarithmic indicator scaling achieved better accuracy, but participants perceived it to be more difficult than linear scaling. With specific results for angle and depth accuracy, our study contributes to the future composition of improved navigation support and systems for precise needle insertion or similar applications.