ProgPrompt: Generating Situated Robot Task Plans using Large Language Models

arxiv(2022)

引用 197|浏览130
暂无评分
摘要
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 at progprompt.github.io
更多
查看译文
关键词
action sequences,additional domain information,available actions,defining myriad domain knowledge,free-form text,generating situated robot task,generation constraints,given robot,language models,natural language,physical robot arm,plan generation,possible next steps,programmatic LLM prompt structure,robot capabilities,score potential,scoring,situated environments,tabletop tasks,task planning,VirtualHome household tasks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要