Robot Behavior-Tree-Based Task Generation with Large Language Models
Robot Behavior-Tree-Based Task Generation with Large Language Models
复制标题
DOI：
10.48550/arxiv.2302.12927
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
Yue Cao-;C. S. Lee
中科院分区：
文献类型：
--
作者：
Yue Cao-;C. S. Lee
目前，行为树作为机器人任务的表示方法，由于其模块化和可重用性而越来越受欢迎。手动设计行为树任务是耗时的机器人终端用户，因此有必要调查自动行为树为基础的任务生成。现有的基于行为树的任务生成方法主要集中在固定的原始任务上，缺乏对新任务域的推广能力。为了科普这个问题，我们提出了一种新的基于行为树的任务生成方法，利用国家的最先进的大型语言模型。我们提出了一个阶段步骤提示设计，使层次结构的机器人任务生成，并进一步将其与行为树嵌入为基础的搜索，以建立适当的提示。通过这种方式，我们实现了自动和跨域的行为树任务生成。我们的基于行为树的任务生成方法不需要一组预定义的原始任务。最终用户只需要描述一个抽象的期望任务，我们提出的方法可以快速生成相应的行为树。一个全过程的案例研究，以证明我们提出的方法。进行消融研究，以评估我们的阶段步骤提示的有效性。对阶段-步骤提示的评估和大型语言模型的局限性进行了介绍和讨论。
Nowadays, the behavior tree is gaining popularity as a representation for robot tasks due to its modularity and reusability. Designing behavior-tree tasks manually is time-consuming for robot end-users, thus there is a need for investigating automatic behavior-tree-based task generation. Prior behavior-tree-based task generation approaches focus on fixed primitive tasks and lack generalizability to new task domains. To cope with this issue, we propose a novel behavior-tree-based task generation approach that utilizes state-of-the-art large language models. We propose a Phase-Step prompt design that enables a hierarchical-structured robot task generation and further integrate it with behavior-tree-embedding-based search to set up the appropriate prompt. In this way, we enable an automatic and cross-domain behavior-tree task generation. Our behavior-tree-based task generation approach does not require a set of pre-defined primitive tasks. End-users only need to describe an abstract desired task and our proposed approach can swiftly generate the corresponding behavior tree. A full-process case study is provided to demonstrate our proposed approach. An ablation study is conducted to evaluate the effectiveness of our Phase-Step prompts. Assessment on Phase-Step prompts and the limitation of large language models are presented and discussed.