.png){kind=icon}
Return
PROGPROMPT: program generation for situated robot task planning using large language models
.png){kind=icon}
OA
AI
DOI：10.1007/s10514-023-10135-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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 programs 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
Keywords:
Robot task planning
LLM code generation
Planning domain generalization
Symbolic planning
Journal
IF:
4.3
Papers:
1.7K
Citations:
5.0K
Organization
Cited Papers
.png){kind=icon}
ShareSaveComprehensive optical losses investigation of VLSI Silicon optomechanical ring resonator sensors
PREAI
ShareSave
ShareSavePersistent organic pollutant waste in China: a review of past experiences and future challenges
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSave
View more