RobotGPT: From ChatGPT to Robot Intelligence

Hongmei Mary He

Keywords: ChatGPT, Generative Pre-trained Model, Tuning, Reinforcement Learning, Robot Perception, Robot Intelligence, RobotGPT

TL;DR: The author proposes a multimodal approach that takes advantage of GPT-3 to implement the seven types of robot intelligence, and provides a framework for RobotGPT.

Abstract: ChatGPT, a language model developed by OpenAI, has triggered a new wave of AI development. This article reviews the principles of ChatGPT, analyzes five types of robot perception related to human perception (visual, auditory, tactile, olfactory, and gustatory), and seven types of robot intelligence (logical-mathematical, linguistic, spatial, musical, bodily-kinesthetic, interpersonal, and naturalistic), but excludes intrapersonal intelligence as a type of robot intelligence, distinguishing robots from human individuals. The author proposes a multimodal approach that takes advantage of GPT-3 to implement the seven types of robot intelligence and provides a framework for implementing an intelligent robotic system, called RobotGPT.