BeSimulator: A Large Language Model Powered Text-based Behavior Simulator
This addresses the need for more efficient and adaptable behavior simulation in robotics, particularly for preliminary evaluation before using resource-intensive simulators, though it is incremental as it builds on existing LLM and simulation concepts.
The paper tackles the problem of inefficient and computationally expensive robot simulators by proposing BeSimulator, a large language model-powered text-based behavior simulator that improves simulation efficiency, achieving performance gains of 13.60% to 24.80% over baselines on a behavior-tree-based benchmark.
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.