The Voice-To-Text Implementation with ChatGPT in Unitree Go1 Programming.
Disciplines
Robotics
Abstract (300 words maximum)
The application of large language models (LLMs) has become more widespread as they are increasingly being integrated in various ways. LLMs, such as ChatGPT, are revolutionary models capable of processing large amounts of data to output human-like texts as well as executable code. This research explores these applications as it investigates the implementation of ChatGPT with the Unitree Go1 Robot Dog, specifically focusing on integrating voice prompts to instruct the Unitree Go1 robot dog. The methodology involves creating an interface to facilitate communication between the ChatGPT API and the Unitree Go1 SDK. To achieve this integration, a second WiFi adapter was utilized to bridge the communication between the robot dog and LLM. The code is then generated for user inspection and executed upon approval. This connection simplifies the process to control the robot dog allowing users with limited knowledge to execute commands. Additionally, those with coding experience can utilize this to expedite the process of software development. Research in this technology holds immense potential for enabling users to explore and experiment with different functionalities of the robot dog, contributing to enhanced comprehension and testing capabilities within the field of robotics.
Academic department under which the project should be listed
SPCEET - Robotics and Mechatronics Engineering
Primary Investigator (PI) Name
Muhammad Hassan Tanveer
The Voice-To-Text Implementation with ChatGPT in Unitree Go1 Programming.
The application of large language models (LLMs) has become more widespread as they are increasingly being integrated in various ways. LLMs, such as ChatGPT, are revolutionary models capable of processing large amounts of data to output human-like texts as well as executable code. This research explores these applications as it investigates the implementation of ChatGPT with the Unitree Go1 Robot Dog, specifically focusing on integrating voice prompts to instruct the Unitree Go1 robot dog. The methodology involves creating an interface to facilitate communication between the ChatGPT API and the Unitree Go1 SDK. To achieve this integration, a second WiFi adapter was utilized to bridge the communication between the robot dog and LLM. The code is then generated for user inspection and executed upon approval. This connection simplifies the process to control the robot dog allowing users with limited knowledge to execute commands. Additionally, those with coding experience can utilize this to expedite the process of software development. Research in this technology holds immense potential for enabling users to explore and experiment with different functionalities of the robot dog, contributing to enhanced comprehension and testing capabilities within the field of robotics.