EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Programming-by-Demonstration for Long-Horizon Robot Tasks

Noah Patton, Kia Rahmani, Meghana Missula, Joydeep Biswas, Işıl Dillig

Proceedings of the ACM on Programming Languages · 02.01.2024 · 8 (POPL) · 512-545

DOI: 10.1145/3632860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 05.01.2024. Verfasst von Noah Patton und 4 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 130 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The goal of programmatic Learning from Demonstration (LfD) is to learn a policy in a programming language that can be used to control a robot’s behavior from a set of user demonstrations. This paper presents a new programmatic LfD algorithm that targets long-horizon robot tasks which require synthesizing programs with complex control flow structures, including nested loops with multiple conditionals. Our proposed method first learns a program sketch that captures the target program’s control flow and then completes this sketch using an LLM-guided search procedure that incorporates a novel technique for proving unrealizability of programming-by-demonstration problems. We have implemented our approach in a new tool called prolex and present the results of a comprehensive experimental evaluation on 120 benchmarks involving complex tasks and environments. We show that, given a 120 second time limit, prolex can find a program consistent with the demonstrations in 80% of the cases. Furthermore, for 81% of the tasks for which a solution is returned, prolex is able to find the ground truth program with just one demonstration. In comparison, CVC5, a syntaxguided synthesis tool, is only able to solve 25% of the cases even when given the ground truth program sketch , and an LLM-based approach, GPT-Synth, is unable to solve any of the tasks due to the environment complexity.

Förderung

  • NSF

Zitieren

APA

Patton, N., Rahmani, K., Missula, M., Biswas, J., & Dillig, I. (2024). Programming-by-Demonstration for Long-Horizon Robot Tasks. Proceedings of the ACM on Programming Languages, 8(POPL), 512-545. https://doi.org/10.1145/3632860

Vancouver

Patton N, Rahmani K, Missula M, Biswas J, Dillig I. Programming-by-Demonstration for Long-Horizon Robot Tasks. Proceedings of the ACM on Programming Languages. 2024;8(POPL):512-545. doi:10.1145/3632860

BibTeX
@article{Patton2024,
  author = {Patton, Noah and Rahmani, Kia and Missula, Meghana and Biswas, Joydeep and Dillig, Işıl},
  title = {Programming-by-Demonstration for Long-Horizon Robot Tasks},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2024},
  volume = {8},
  number = {POPL},
  pages = {512--545},
  doi = {10.1145/3632860}
}
Kostenlos starten →