CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation

TL;DR

This paper introduces CABTO, a framework that automates the grounding of behavior trees for robot manipulation by leveraging large language models and contextual feedback, reducing manual effort and improving reliability.

Contribution

CABTO is the first framework to automate the construction of complete behavior tree systems using pre-trained models and contextual information, enhancing robot manipulation capabilities.

Findings

CABTO effectively generates complete behavior trees across multiple tasks.

The framework demonstrates efficiency in diverse robotic manipulation scenarios.

Experimental results show improved reliability and reduced manual effort.

Abstract

Behavior Trees (BTs) offer a powerful paradigm for designing modular and reactive robot controllers. BT planning, an emerging field, provides theoretical guarantees for the automated generation of reliable BTs. However, BT planning typically assumes that a well-designed BT system is already grounded -- comprising high-level action models and low-level control policies -- which often requires extensive expert knowledge and manual effort. In this paper, we formalize the BT Grounding problem: the automated construction of a complete and consistent BT system. We analyze its complexity and introduce CABTO (Context-Aware Behavior Tree grOunding), the first framework to efficiently solve this challenge. CABTO leverages pre-trained Large Models (LMs) to heuristically search the space of action models and control policies, guided by contextual feedback from BT planners and environmental observations. Experiments spanning seven task sets across three distinct robotic manipulation scenarios demonstrate CABTO's effectiveness and efficiency in generating complete and consistent behavior tree systems.