ProgPrompt: program generation for situated robot task planning using large language models
Autonomous Robots · 2023-12 · 47 (8) · 999-1012
DOI: 10.1007/s10514-023-10135-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Autonomous Robots, online erschienen am 28.08.2023. Verfasst von Ishika Singh und 8 weiteren Autor:innen. Die Arbeit wurde bisher 95-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Southern California.
Abstract (Originalsprache)
Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks. Our key insight is to prompt the LLM with program-like specifications of the available actions and objects in an environment, as well as with example that can be executed. We make concrete recommendations about prompt structure and generation constraints through ablation experiments, demonstrate state of the art success rates in VirtualHome household tasks, and deploy our method on a physical robot arm for tabletop tasks. Website and code at progprompt.github.io
Förderung
- University of Southern California
Zitieren
APA
Singh, I., Blukis, V., Mousavian, A., Goyal, A., Xu, D., Tremblay, J., Fox, D., Thomason, J., & Garg, A. (2023). ProgPrompt: program generation for situated robot task planning using large language models. Autonomous Robots, 47(8), 999-1012. https://doi.org/10.1007/s10514-023-10135-3
Vancouver
Singh I, Blukis V, Mousavian A, Goyal A, Xu D, Tremblay J, et al. ProgPrompt: program generation for situated robot task planning using large language models. Autonomous Robots. 2023;47(8):999-1012. doi:10.1007/s10514-023-10135-3
BibTeX
@article{Singh2023,
author = {Singh, Ishika and Blukis, Valts and Mousavian, Arsalan and Goyal, Ankit and Xu, Danfei and Tremblay, Jonathan and Fox, Dieter and Thomason, Jesse and Garg, Animesh},
title = {ProgPrompt: program generation for situated robot task planning using large language models},
journal = {Autonomous Robots},
year = {2023},
volume = {47},
number = {8},
pages = {999--1012},
doi = {10.1007/s10514-023-10135-3}
}
EUVIMED