24RobotGPT: A Voice-Based Robot Integrated with Edge Computing Technology

Van Dai Pham1*, Ba Anh Luu2, Tan Dat Ly3, Khang Minh Vuong1, Thai Anh Bui1 and Anh Ngoc Le1

1Swinburne Vietnam, FPT University, Hanoi, Vietnam

2University of Science and Technology of Hanoi, Hanoi, Vietnam

3University of Transport and Communications, Hanoi, Vietnam

Abstract

Voice-based interactive systems have become increasingly popular in recent years, particularly with the advent of large language models (LLMs) that can generate human-like responses. In this study, we propose RobotGPT, a voice-based robot that leverages LLMs to provide natural language question-and-answer (Q&A) interactions with users. In addition, we integrated RobotGPT with edge computing technology to reduce the response time and improve the overall system performance. Our system is designed to learn from frequently asked questions and answers generated by the GPT model and can be fine-tuned for specific domain requirements. We evaluated the performance of RobotGPT through a series of experiments on a prototype system, focusing on the response time, accuracy, and user satisfaction. Our results demonstrate that RobotGPT has the potential to be an effective and efficient tool for voice-based Q&A applications, particularly in contexts in which quick responses and personalized interactions are essential.

Keywords: Robot, LLM, OpenAI, GPT, edge computing, Internet of Things

24.1 Introduction

Generative Pre-trained Transformers (GPT) ...

Get Creative Approaches Towards Development of Computing and Multidisciplinary IT Solutions for Society now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.