ProgPrompt: Generating Situated Robot Task Plans using Large Language ModelsDownload PDF

Published: 21 Oct 2022, Last Modified: 26 Mar 2024LaReL 2022Readers: Everyone
Keywords: task planning, instruction following, LLM planner, task plans as programs
TL;DR: Adapting LLMs to generate task plans with given robot capabilities and context using specific programming language features
Abstract: 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 executable example programs. 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.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2209.11302/code)
3 Replies

Loading