Leveraging LLMs to Create a Haptic Devices' Recommendation System

2025-01-22

AI Summary

Grounded force feedback (GFF) device selection lacks systematic guidance, hindering tactile technology advancement. This paper introduces the first large language model (LLM)-driven recommendation agent for haptic hardware, which automatically extracts and structurally models knowledge from both academic literature and product specification data. We propose a novel dynamic retrieval mechanism that synergistically combines conditional retrieval—ensuring parameter-level precision—with semantic retrieval—supporting natural language understanding. The system enables accurate GFF device recommendations via natural language queries. In the User Experience Questionnaire (UEQ) evaluation, our system achieved a composite score consistently within the top 10%, with all six subscales significantly outperforming baseline tools; no statistically significant differences were observed across user groups, demonstrating high usability, robustness, and fairness.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Haptic technology has seen significant growth, yet a lack of awareness of existing haptic device design knowledge hinders development. This paper addresses these limitations by leveraging advancements in Large Language Models (LLMs) to develop a haptic agent, focusing specifically on Grounded Force Feedback (GFF) devices recommendation. Our approach involves automating the creation of a structured haptic device database using information from research papers and product specifications. This database enables the recommendation of relevant GFF devices based on user queries. To ensure precise and contextually relevant recommendations, the system employs a dynamic retrieval method that combines both conditional and semantic searches. Benchmarking against the established UEQ and existing haptic device searching tools, the proposed haptic recommendation agent ranks in the top 10% across all UEQ categories with mean differences favoring the agent in nearly all subscales, and maintains no significant performance bias across different user groups, showcasing superior usability and user satisfaction.

Problem

• Tactile Technology
• Haptic Device Selection
• Ground Force Feedback

Innovation

• Large Language Model
• Tactile Device Recommendation
• User Experience Quality