Conditionally Combining Robot Skills using Large Language Models

被引:0
|
作者
Zentner, K. R. [1 ,3 ]
Julian, Ryan [2 ]
Ichter, Brian [2 ]
Sukhatme, Gaurav S. [1 ]
机构
[1] Univ Southern Calif, Los Angeles, CA 90007 USA
[2] Google DeepMind, London, England
[3] Google Brain, Mountain View, CA USA
来源
2024 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2024) | 2024年
关键词
D O I
10.1109/ICRA57147.2024.10611275
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper combines two contributions. First, we introduce an extension of the Meta-World benchmark, which we call "Language-World," which allows a large language model to operate in a simulated robotic environment using semi-structured natural language queries and scripted skills described using natural language. By using the same set of tasks as Meta-World, Language-World results can be easily compared to Meta-World results, allowing for a point of comparison between recent methods using Large Language Models (LLMs) and those using Deep Reinforcement Learning. Second, we introduce a method we call Plan Conditioned Behavioral Cloning (PCBC), that allows finetuning the behavior of high-level plans using end-to-end demonstrations. Using Language-World, we show that PCBC is able to achieve strong performance in a variety of few-shot regimes, often achieving task generalization with as little as a single demonstration. We have made Language-World available as open-source software at https://github.com/krzentner/language-world/.
引用
收藏
页码:14046 / 14053
页数:8
相关论文
共 50 条
  • [21] Human-robot interaction through joint robot planning with large language models
    Asuzu, Kosi
    Singh, Harjinder
    Idrissi, Moad
    INTELLIGENT SERVICE ROBOTICS, 2025, : 261 - 277
  • [22] Assessing Language Skills Using Diagnostic Classification Models: An Example Using a Language Instrument
    Sideridis, Georgios D.
    Tsaousis, Ioannis
    Al-Harbi, Khaleel
    INTERNATIONAL JOURNAL OF PSYCHOLOGICAL RESEARCH, 2022, 15 (02): : 109 - 119
  • [23] Use of large language models might affect our cognitive skills
    Heersmink, Richard
    NATURE HUMAN BEHAVIOUR, 2024, 8 (05) : 805 - 806
  • [24] Comuniqa : Exploring Large Language Models for Improving English Speaking Skills
    Mhasakar, Manas
    Sharma, Shikhar
    Mehra, Apurv
    Venaik, Utkarsh
    Singhal, Ujjwal
    Kumar, Dhruv
    Mittal, Kashish
    PROCEEDINGS OF THE ACM SIGCAS/SIGCHI CONFERENCE ON COMPUTING AND SUSTAINABLE SOCIETIES 2024, COMPASS 2024, 2024, : 256 - 267
  • [25] Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL
    Fan, Ju
    Gu, Zihui
    Zhang, Songyue
    Zhang, Yuxin
    Chen, Zui
    Cao, Lei
    Li, Guoliang
    Madden, Samuel
    Du, Xiaoyong
    Tang, Nan
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2024, 17 (11): : 2750 - 2763
  • [26] Large Language Models in Robot Programming Potential in the programming of industrial robots
    Syniawa, Daniel
    Ates, Baris
    Boshoff, Marius
    Kuhlenkoetter, Bernd
    ATP MAGAZINE, 2024, (6-7):
  • [27] RoCo: Dialectic Multi-Robot Collaboration with Large Language Models
    Mandi, Zhao
    Jain, Shreeya
    Song, Shuran
    2024 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2024, 2024, : 286 - 299
  • [28] Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding
    Mariotti, Luca
    Guidetti, Veronica
    Mandreoli, Federica
    Belli, Andrea
    Lombardi, Paolo
    FRONTIERS IN ARTIFICIAL INTELLIGENCE, 2024, 7
  • [29] Using Large Language Models for Robot-Assisted Therapeutic Role-Play: Factuality is not enough!
    Hohn, Sviatlana
    Nasir, Jauwairia
    Paikan, Ali
    Ziafati, Pouyan
    Andre, Elisabeth
    PROCEEDINGS OF THE 6TH CONFERENCE ON ACM CONVERSATIONAL USER INTERFACES, CUI 2024, 2024,
  • [30] Real-time emotion generation in human-robot dialogue using large language models
    Mishra, Chinmaya
    Verdonschot, Rinus
    Hagoort, Peter
    Skantze, Gabriel
    FRONTIERS IN ROBOTICS AND AI, 2023, 10