Exploring a GPT-based large language model for variable autonomy in a VR-based human-robot teaming simulation.

In a rapidly evolving digital landscape autonomous tools and robots are becoming commonplace. Recognizing the significance of this development, this paper explores the integration of Large Language Models (LLMs) like Generative pre-trained transformer (GPT) into human-robot teaming environments to facilitate variable autonomy through the means of verbal human-robot communication. In this paper, we introduce a novel simulation framework for such a GPT-powered multi-robot testbed environment, based on a Unity Virtual Reality (VR) setting. This system allows users to interact with simulated robot agents through natural language, each powered by individual GPT cores. By means of OpenAI's function calling, we bridge the gap between unstructured natural language input and structured robot actions. A user study with 12 participants explores the effectiveness of GPT-4 and, more importantly, user strategies when being given the opportunity to converse in natural language within a simulated multi-robot environment. Our findings suggest that users may have preconceived expectations on how to converse with robots and seldom try to explore the actual language and cognitive capabilities of their simulated robot collaborators. Still, those users who did explore were able to benefit from a much more natural flow of communication and human-like back-and-forth. We provide a set of lessons learned for future research and technical implementations of similar systems.

My Caregiver the Cobot: Comparing Visualization Techniques to Effectively Communicate Cobot Perception to People with Physical Impairments.

Nowadays, robots are found in a growing number of areas where they collaborate closely with humans. Enabled by lightweight materials and safety sensors, these cobots are gaining increasing popularity in domestic care, where they support people with physical impairments in their everyday lives. However, when cobots perform actions autonomously, it remains challenging for human collaborators to understand and predict their behavior, which is crucial for achieving trust and user acceptance. One significant aspect of predicting cobot behavior is understanding their perception and comprehending how they "see" the world. To tackle this challenge, we compared three different visualization techniques for Spatial Augmented Reality. All of these communicate cobot perception by visually indicating which objects in the cobot's surrounding have been identified by their sensors. We compared the well-established visualizations Wedge and Halo against our proposed visualization Line in a remote user experiment with participants suffering from physical impairments. In a second remote experiment, we validated these findings with a broader non-specific user base. Our findings show that Line, a lower complexity visualization, results in significantly faster reaction times compared to Halo, and lower task load compared to both Wedge and Halo. Overall, users prefer Line as a more straightforward visualization. In Spatial Augmented Reality, with its known disadvantage of limited projection area size, established off-screen visualizations are not effective in communicating cobot perception and Line presents an easy-to-understand alternative.