LLM-BRAIn: AI-driven Fast Generation of Robot Behaviour Tree based on Large Language Model

TL;DR

This paper introduces LLM-BRAIn, a transformer-based large language model fine-tuned to generate robot behavior trees from text commands, enabling autonomous robot control with high accuracy and efficiency on onboard microcomputers.

Contribution

The paper presents a novel LLM fine-tuned for robot behavior generation, capable of producing accurate and complex behavior trees from natural language instructions, suitable for onboard deployment.

Findings

LLM-BRAIn accurately generates complex robot behavior trees.

Generated BTs are structurally and logically correct.

Participants could not reliably distinguish LLM-generated BTs from human-created ones.

Abstract

This paper presents a novel approach in autonomous robot control, named LLM-BRAIn, that makes possible robot behavior generation, based on operator's commands. LLM-BRAIn is a transformer-based Large Language Model (LLM) fine-tuned from Stanford Alpaca 7B model to generate robot behavior tree (BT) from the text description. We train the LLM-BRAIn on 8,5k instruction-following demonstrations, generated in the style of self-instruct using text-davinchi-003. The developed model accurately builds complex robot behavior while remaining small enough to be run on the robot's onboard microcomputer. The model gives structural and logical correct BTs and can successfully manage instructions that were not presented in training set. The experiment did not reveal any significant subjective differences between BTs generated by LLM-BRAIn and those created by humans (on average, participants were able to correctly distinguish between LLM-BRAIn generated BTs and human-created BTs in only 4.53 out of 10 cases, indicating that their performance was close to random chance). The proposed approach potentially can be applied to mobile robotics, drone operation, robot manipulator systems and Industry 4.0.