[TOC]

  1. Title: Translating Natural Language to Planning Goals With LLM
  2. Author: Yaqi Xie et. al.
  3. Publish Year: 10 Feb 2023
  4. Review Date: Mon, May 22, 2023
  5. url: https://arxiv.org/pdf/2302.05128.pdf

Summary of paper

Motivation

  • Unfortunately, recent work has also shown that LLMs are unable to perform accurate reasoning nor solve planning problem
  • LLM can act as a natural interface between the planner and human users
  • Our empirical results on GPT 3.5 variants show that LLMs are much better suited towards translation rather than planning.

Contribution

  • We find that LLMs are able to leverage commonsense knowledge and reasoning to furnish missing details from under-specified goals (as is often the case in natural language)

Some key terms

Architecture

  • image-20230522123337734

Potential future work

image-20230522124507086

  • the experiment is only about generating PDDL goal from the PDDL texts
    • however, in ALFRED environment, PDDL problem file will not be provided during testing.