Abstract
ChatGPT, released by OpenAI, has garnered academic interest due to its powerful natural language processing capabilities. It can accurately understand conversations and generate high-quality responses. This paper explores the potential of applying ChatGPT to two significant research topics in robotics: Human-Robot Interaction and Task Planning. Human-Robot Interaction involves studying the interactions between humans and robots. ChatGPT is well-suited for this purpose as it enables robots to communicate with humans. However, ChatGPT has shortcomings such as outdated knowledge and fabricating answers, making it unsuitable for direct use in Q&A. To address these issues, we propose an architecture called FRC that combines FAQ, retrieval module, and ChatGPT. In this architecture, ChatGPT is used for rephrasing questions and reading comprehension. Experiments show that the architecture can combine multiple rounds of dialogue to answer incomplete questions or questions that need coreference resolution. Task planning involves using an internal model to reason about the world and create a plan of actions to achieve a specific goal. Traditional approaches to robotic task planning rely on search while using ChatGPT for task planning is a novel approach based on generation. Existing methods using ChatGPT do not consider the state of the robot. We propose a method that enables ChatGPT to perform task planning based on the state of the robot and have verified its feasibility through experiments. We also discuss the limitations of ChatGPT in multi-party talk and motion control.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
OpenAI, ChatGPT. https://openai.com/blog/chatgpt. Accessed 10 May 2023
Top 12 Interesting ChatGPT Applications and Examples. https://savvycomsoftware.com/blog/top-interesting-chatgpt-applications-and-examples/. Accessed 17 May 2023
Best ChatGPT Use Cases: 8 Industry Applications with Examples – Emeritus. https://emeritus.org/blog/ai-and-ml-chatgpt-use-cases/. Accessed 17 May 2023
Auto-GPT. https://news.agpt.co/. Accessed 10 May 2023
Shen, Y., Song, K., Tan, X., Li, D.S., Lu, W., Zhuang, Y.T.: HuggingGPT: solving AI tasks with ChatGPT and its friends in HuggingFace. arXiv abs/2303.17580 (2023)
Vemprala, S., Bonatti, R., Bucker, A., Kapoor, A.: Chatgpt for robotics:Design principles and model abilities. Technical report MSR-TR-2023-8, Microsoft,February 2023. https://www.microsoft.com/en-us/research/publication/chatgpt-for-robotics-design-principles-and-model-abilities/
Xi, X., Xie, B., Zhu, S., Jin, T., Ren, J., Song, W.: A general framework of task understanding for tour-guide robots in exhibition environments.In: 2022 WRC Symposium on Advanced Robotics and Automation (WRC SARA), Beijing, Chin, pp. 197-202 (2022). https://doi.org/10.1109/WRCSARA57040.2022.9903960
Robotic Sea Bass, Task Planning in Robotics. https://roboticseabass.com/2022/07/19/task-planning-in-robotics. Accessed 10 May 2023
Jiang, Y., Zhang, S., Khandelwal, P. et al.: Task planning in robotics: an empirical comparison of PDDL- and ASP-based systems. Front. Inf. Technol. Electron. Eng. 20, 363–373 (2019). https://doi.org/10.1631/FITEE.1800514
Yuan, H., et al.: Plan4MC: skill reinforcement learning and planning for open-world minecraft tasks. arXiv abs/2303.16563 (2023)
Reimers, N., Iryna, G.: Sentence-BERT: sentence embeddings using siamese BERT-networks. In: Conference on Empirical Methods in Natural Language Processing (2019)
Vector database – Milvus. https://milvus.io/. Accessed 21 May 2023
Elastic/elasticsearch. https://github.com/elastic/elasticsearch. Accessed 21 May 2023
Baidu. https://www.baidu.com/. Accessed 21 May 2023
Microsoft/PromptCraft-Robotics. https://github.com/microsoft/PromptCraft-Robotics. Accessed 21 May 2023
OpenAI: GPT-4 Technical Report. arXiv abs/2303.08774 (2023)
Vaswani, A.: Attention is All you Need. NIPS (2017)
Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. arXiv abs/2204.02311 (2022)
Touvron, H., et al.: LLaMA: Open and Efficient Foundation Language Models. arXiv abs/2302.13971 (2023)
Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)
Zihao, W., Cai, S., Liu, A., Ma, X., Liang, Y.: Describe, explain, plan and select: interactive planning with large language models enables open-world multi-task agents. arXiv abs/2302.01560 (2023)
Acknowledgment
This paper is supported by the Key Research Project of Zhejiang Lab (No. G2021NB0AL03).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xie, B. et al. (2023). ChatGPT for Robotics: A New Approach to Human-Robot Interaction and Task Planning. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14271. Springer, Singapore. https://doi.org/10.1007/978-981-99-6495-6_31
Download citation
DOI: https://doi.org/10.1007/978-981-99-6495-6_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6494-9
Online ISBN: 978-981-99-6495-6
eBook Packages: Computer ScienceComputer Science (R0)