Automatic Behavior Tree Expansion with LLMs for Robotic Manipulation

TL;DR

This paper introduces BETR-XP-LLM, a method that uses large language models to automatically expand and adapt behavior trees for robotic manipulation, improving flexibility and transparency in task execution.

Contribution

The paper presents a novel approach that leverages LLMs to dynamically expand behavior trees, enabling robots to handle errors and adapt policies in real-time.

Findings

Successfully solves diverse manipulation tasks

Automatically updates policies for future errors

Enhances robot adaptability and transparency

Abstract

Robotic systems for manipulation tasks are increasingly expected to be easy to configure for new tasks or unpredictable environments, while keeping a transparent policy that is readable and verifiable by humans. We propose the method BEhavior TRee eXPansion with Large Language Models (BETR-XP-LLM) to dynamically and automatically expand and configure Behavior Trees as policies for robot control. The method utilizes an LLM to resolve errors outside the task planner's capabilities, both during planning and execution. We show that the method is able to solve a variety of tasks and failures and permanently update the policy to handle similar problems in the future.