I Was Blind but Now I See: Implementing Vision-Enabled Dialogue in Social Robots
This work addresses the problem of limited context awareness in social robots for human-computer interaction, though it appears incremental as an initial implementation building on existing LLMs.
The paper tackled the integration of vision capabilities into conversational agents by implementing a dialogue manager that uses Large Language Models (e.g., GPT-4, IDEFICS) to process both text and real-time visual input, reporting results from six interactions with a Furhat robot.
In the rapidly evolving landscape of human-computer interaction, the integration of vision capabilities into conversational agents stands as a crucial advancement. This paper presents an initial implementation of a dialogue manager that leverages the latest progress in Large Language Models (e.g., GPT-4, IDEFICS) to enhance the traditional text-based prompts with real-time visual input. LLMs are used to interpret both textual prompts and visual stimuli, creating a more contextually aware conversational agent. The system's prompt engineering, incorporating dialogue with summarisation of the images, ensures a balance between context preservation and computational efficiency. Six interactions with a Furhat robot powered by this system are reported, illustrating and discussing the results obtained. By implementing this vision-enabled dialogue system, the paper envisions a future where conversational agents seamlessly blend textual and visual modalities, enabling richer, more context-aware dialogues.