BeSimulator: A Large Language Model Powered Text-based Behavior Simulator

TL;DR

BeSimulator introduces a modular, LLM-powered text-based behavior simulation framework for robotics, enabling efficient, long-horizon scenario analysis and validation before deploying resource-intensive physical simulators.

Contribution

It presents a novel behavior simulation framework using large language models, with a four-phase process and code-driven reasoning, improving efficiency and generalization in text-based environments.

Findings

Achieved 13.60% to 24.80% performance improvement over baselines.

Developed a new behavior-tree-based simulation benchmark, BTSIMBENCH.

Demonstrated effective long-horizon complex behavior simulation.

Abstract

Traditional robot simulators focus on physical process modeling and realistic rendering, often suffering from high computational costs, inefficiencies, and limited adaptability. To handle this issue, we concentrate on behavior simulation in robotics to analyze and validate the logic behind robot behaviors, aiming to achieve preliminary evaluation before deploying resource-intensive simulators and thus enhance simulation efficiency. In this paper, we propose BeSimulator, a modular and novel LLM-powered framework, as an attempt towards behavior simulation in the context of text-based environments. By constructing text-based virtual environments and performing semantic-level simulation, BeSimulator can generalize across scenarios and achieve long-horizon complex simulation. Inspired by human cognition paradigm, it employs a ``consider-decide-capture-transfer'' four-phase simulation process, termed Chain of Behavior Simulation (CBS), which excels at analyzing action feasibility and state transition. Additionally, BeSimulator incorporates code-driven reasoning to enable arithmetic operations and enhance reliability, and reflective feedback to refine simulation. Based on our manually constructed behavior-tree-based simulation benchmark, BTSIMBENCH, our experiments show a significant performance improvement in behavior simulation compared to baselines, ranging from 13.60% to 24.80%. Code and data are available at https://github.com/Dawn888888/BeSimulator.