TR2024-052

Interactive Planning Using Large Language Models for Partially Observable Robotic Tasks


    •  Sun, L., Jha, D.K., Hori, C., Jain, S., Corcodel, R., Zhu, X., Tomizuka, M., Romeres, D., "Interactive Planning Using Large Language Models for Partially Observable Robotic Tasks", IEEE International Conference on Robotics and Automation (ICRA), DOI: 10.1109/​ICRA57147.2024.10610981, May 2024, pp. 14054-14061.
      BibTeX TR2024-052 PDF Video
      • @inproceedings{Sun2024may,
      • author = {Sun, Lingfeng and Jha, Devesh K. and Hori, Chiori and Jain, Siddarth and Corcodel, Radu and Zhu, Xinghao and Tomizuka, Masayoshi and Romeres, Diego}},
      • title = {Interactive Planning Using Large Language Models for Partially Observable Robotic Tasks},
      • booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
      • year = 2024,
      • pages = {14054--14061},
      • month = may,
      • publisher = {IEEE},
      • doi = {10.1109/ICRA57147.2024.10610981},
      • isbn = {979-8-3503-8457-4},
      • url = {https://www.merl.com/publications/TR2024-052}
      • }
  • MERL Contacts:
  • Research Area:

    Robotics

Abstract:

Designing robotic agents to perform open vocabulary tasks has been the long-standing goal in robotics and AI. Recently, Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary tasks. However, planning for these tasks in the presence of uncertainties is challenging as it requires “chain-of-thought” reasoning, aggregating information from the environment, updating state estimates, and generating actions based on the updated state estimates. In this paper, we present an interactive planning technique for partially observable tasks using LLMs. In the proposed method, an LLM is used to collect missing information from the environment using a robot, and infer the state of the underlying problem from collected observations while guiding the robot to perform the required actions. We also use a fine-tuned Llama 2 model via self-instruct and compare its performance against a pre-trained LLM like GPT-4. Results are demonstrated on several tasks in simulation as well as real-world environments.

 

  • Related News & Events

  • Related Video

  • Related Publications

  •  Sun, L., Jha, D.K., Hori, C., Jain, S., Corcodel, R., Zhu, X., Tomizuka, M., Romeres, D., "Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks", Advances in Neural Information Processing Systems (NeurIPS) Workshop on Instruction Tuning and Instruction Following, December 2023.
    BibTeX TR2023-148 PDF Video
    • @inproceedings{Sun2023dec,
    • author = {Sun, Lingfeng and Jha, Devesh K. and Hori, Chiori and Jain, Siddarth and Corcodel, Radu and Zhu, Xinghao and Tomizuka, Masayoshi and Romeres, Diego},
    • title = {Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks},
    • booktitle = {Advances in Neural Information Processing Systems (NeurIPS) Workshop on Instruction Tuning and Instruction Following},
    • year = 2023,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2023-148}
    • }
  •  Sun, L., Jha, D.K., Hori, C., Jain, S., Corcodel, R., Zhu, X., Tomizuka, M., Romeres, D., "Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks", arXiv, December 2023.
    BibTeX arXiv
    • @article{Sun2023dec2,
    • author = {Sun, Lingfeng and Jha, Devesh K. and Hori, Chiori and Jain, Siddarth and Corcodel, Radu and Zhu, Xinghao and Tomizuka, Masayoshi and Romeres, Diego},
    • title = {Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks},
    • journal = {arXiv},
    • year = 2023,
    • month = dec,
    • url = {https://arxiv.org/abs/2312.06876}
    • }