Integrating curious behavior traits into robots is essential for them to learn and adapt to new tasks over their lifetime and to enhance human-robot interaction. However, the effects of robots expressing curiosity on user perception, user interaction, and user experience in collaborative tasks are unclear. In this work, we present a Multimodal Large Language Model-based system that equips a robot with non-verbal and verbal curiosity traits. We conducted a user study ($N=20$) to investigate how these traits modulate the robot's behavior and the users' impressions of sociability and quality of interaction. Participants prepared cocktails or pizzas with a robot, which was either curious or non-curious. Our results show that we could create user-centric curiosity, which users perceived as more human-like, inquisitive, and autonomous while resulting in a longer interaction time. We contribute a set of design recommendations allowing system designers to take advantage of curiosity in collaborative tasks.
Use Cases of Large Language Models driven Multi-Modal Human-Robot Interaction
The system with our curious character utilizes available capabilities to engage with the surroundings. The MM-LLM agent can actively employ functions to capture images, communicate intentions through speech and facial expression, and manipulate items.
The system with our curious character utilizes available capabilities to engage with the surroundings. The MM-LLM agent can actively employ functions to capture images, communicate intentions through speech and facial expression, and manipulate items.
An illustration of an interaction sequence with the curious robot. 1. Prior to a human entering the scene, the robot looks around the objects on the table with curiosity; 2. When a person appears, the robot greets them and asks for their name; 3. The robot inquires about the next task based on the visible objects, and the person instructs it to make a gin and tonic; 4. Before using the gin, the robot pokes the non-transparent gin container to check for emptiness; 5. The robot pours the gin into a glass; 6. The robot shakes the non-transparent container out of curiosity; 7. The robot requests the person to remove the cap as it cannot do so itself; 8. After the cap is taken off, the robot grasps the container and inspects its contents; 9. Upon discovering the ingredient, the robot asks the person for their preferred ingredient and adds it to the drink.
