Augmented reality shows great promise for supporting human-robot collaboration. However, investigating this “in the wild” with participants from industry is mostly uncharted territory. Addressing this, we report on a field study evaluation of ARTHUR, an open-source authoring tool for augmented reality-assisted human-robot collaboration. To facilitate this domain-specific study, we extended ARTHUR with additional design components, improved the authoring experience, and support for collaborative authoring. The study took place at a local company, with 16 participants from three stakeholder groups: robot engineers, UX designers, and operators. The task was to assemble and disassemble a subset of an injection mould together with a collaborative robot, while supported by an AR-interface created in ARTHUR. The study revealed a strong desire of operators to be assisted in their daily tasks by robot(s) that serve as an extra (strong) set of hands, and augmented reality to guide the process and communicate robot intent. Engineers confirmed the feasibility of integrating ARTHUR in future semi-automated workflows and UX designers appreciated the authoring capabilities and proposed further features.

We introduce RoboVisAR, an immersive augmented reality (AR) authoring tool for in-situ robot visualisations. AR robot visualisations, such as the robot's movement path, status, and safety zones, have been shown to benefit human-robot collaboration. However, their creation requires extensive skills in both robotics and AR programming. To address this, RoboVisAR allows users to create custom AR robot visualisations without programming. By recording an example robot behaviour, users can design, combine, and test visualisations in-situ within a mixed reality environment. RoboVisAR currently supports six types of visualisations (Path, Point of Interest, Safety Zone, Robot State, Message, Force/Torque) and four types of conditions for when they are displayed (Robot State, Proximity, Box, Force/Torque). With this tool, users can easily present different visualisations on demand and make them context-aware to avoid visual clutter. An expert user study with three participants suggests that users appreciate the customizability of the visualisations, which could easily be authored in less than ten minutes.

While technologies for human-robot collaboration are rapidly advancing, plenty of aspects still need further investigation, such as ensuring workspace awareness, enabling the operator to reschedule tasks on the fly, and how users prefer to coordinate and collaborate with robots. To address these, we propose an Augmented Reality interface that supports human-robot collaboration in an assembly task by (1) enabling the inspection of planned and ongoing robot processes through dynamic task lists and a path visualization, (2) allowing the operator to also delegate tasks to the robot, and (3) presenting step-by-step assembly instructions. We evaluate our AR interface in comparison to a state-of-the-art tablet interface in a user study, where participants collaborated with a robot arm in a shared workspace to complete an assembly task. Our findings confirm the feasibility and potential of AR-assisted human-robot collaboration, while pointing to some central challenges that require further work.