ChatGPT for Robotics: Design Principles and Model Abilities
Keywords:
Robotics, Artificial intelligence, Computer science, Dialog box, Human–computer interaction, Robot, Robotic paradigms, UploadAbstract
This paper presents an experimental study regarding the use of OpenAI’s ChatGPT [1] for robotics applications. We outline a strategy that combines design principles for prompt engineering and the creation of a high-level function library which allows ChatGPT to adapt to different robotics tasks, simulators, and form factors. We focus our evaluations on the effectiveness of different prompt engineering techniques and dialog strategies towards the execution of various types of robotics tasks. We explore ChatGPT’s ability to use free-form dialog, parse XML tags, and to synthesize code, in addition to the use of task-specific prompting functions and closed-loop reasoning through dialogues. Our study encompasses a range of tasks within the robotics domain, from basic logical, geometrical, and mathematical reasoning all the way to complex domains such as aerial navigation, manipulation, and embodied agents. We show that ChatGPT can be effective at solving several of such tasks, while allowing users to interact with it primarily via natural language instructions. In addition to these studies, we introduce an open-sourced research tool calledPromptCraft, which contains a platform where researchers can collaboratively upload and vote on examples of good prompting schemes for robotics applications, as well as a sample robotics simulator with ChatGPT integration, making it easier for users to get started with using ChatGPT for robotics. Videos and blog: aka.ms/ChatGPT-Robotics PromptCraft, AirSim-ChatGPT code: https://github.com/microsoft/PromptCraft-Robotics.
Source and licence. Open-access article originally published as “ChatGPT for Robotics: Design Principles and Model Abilities” in IEEE Access, 2024. DOI: 10.1109/access.2024.3387941. © Sai Vemprala, Rogerio Bonatti, Arthur Bucker, Ashish Kapoor. Reproduced unchanged under the Creative Commons Attribution 4.0 licence.
References
Nilsson, N. (1996). Artificial intelligence: A modern approach. Artificial Intelligence. https://doi.org/10.1016/0004-3702(96)00007-0
Shah, S., Dey, D., Lovett, C. et al. (2017). AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles. Springer proceedings in advanced robotics. https://doi.org/10.1007/978-3-319-67361-5_40
Tellex, S., Gopalan, N., Kress‐Gazit, H. et al. (2020). Robots That Use Language. Annual Review of Control Robotics and Autonomous Systems. https://doi.org/10.1146/annurev-control-101119-071628
Arkin, J., Park, D., Roy, S. et al. (2020). Multimodal estimation and communication of latent semantic knowledge for robust execution of robot instructions. The International Journal of Robotics Research. https://doi.org/10.1177/0278364920917755
Walter, M., Patki, S., Daniele, A. et al. (2022). Language Understanding for Field and Service Robots in a Priori Unknown Environments. Field Robotics. https://doi.org/10.55417/fr.2022040
Chen, M., Tworek, J., Jun, H. et al. (2021). Evaluating Large Language Models Trained on Code. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2107.03374
Brohan, A., Brown, N. et al. (2022). Do As I Can, Not As I Say: Grounding Language in Robotic Affordances. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2204.01691
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Sai Vemprala, Rogerio Bonatti, Arthur Bucker, Ashish Kapoor
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles are published under the Creative Commons Attribution 4.0 International licence (CC BY 4.0).
