Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents

TL;DR

This paper introduces a multi-level LLM conversational interface for supermarket robots that improves customer interaction by using specialized smaller models, outperforming a large GPT-4 Turbo benchmark in key areas.

Contribution

The paper proposes a novel multi-LLM architecture for supermarket robots, demonstrating its effectiveness over a large GPT model through comprehensive evaluation and a new navigation method.

Findings

Multi-LLM architecture outperforms GPT-4 Turbo in key criteria

Significant improvements in performance, satisfaction, and partnership

Method for mapping chatbot responses to robot navigation commands

Abstract

This paper presents the design and evaluation of a novel multi-level LLM interface for supermarket robots to assist customers. The proposed interface allows customers to convey their needs through both generic and specific queries. While state-of-the-art systems like OpenAI's GPTs are highly adaptable and easy to build and deploy, they still face challenges such as increased response times and limitations in strategic control of the underlying model for tailored use-case and cost optimization. Driven by the goal of developing faster and more efficient conversational agents, this paper advocates for using multiple smaller, specialized LLMs fine-tuned to handle different user queries based on their specificity and user intent. We compare this approach to a specialized GPT model powered by GPT-4 Turbo, using the Artificial Social Agent Questionnaire (ASAQ) and qualitative participant feedback in a counterbalanced within-subjects experiment. Our findings show that our multi-LLM chatbot architecture outperformed the benchmarked GPT model across all 13 measured criteria, with statistically significant improvements in four key areas: performance, user satisfaction, user-agent partnership, and self-image enhancement. The paper also presents a method for supermarket robot navigation by mapping the final chatbot response to correct shelf numbers, enabling the robot to sequentially navigate towards the respective products, after which lower-level robot perception, control, and planning can be used for automated object retrieval. We hope this work encourages more efforts into using multiple, specialized smaller models instead of relying on a single powerful, but more expensive and slower model.