用大模型生成机器人运动规划，自动纠错确保可行。
T3 Planner: A Self-Correcting LLM Framework for Robotic Motion Planning with Temporal Logic
- 分三步用大模型生成轨迹，再用时序逻辑验证可行性
- 在多个场景中优于基线方法，可部署于轻量级模型
- 适合需要高可靠运动规划的机器人系统
将自然语言指令转化为可执行的运动规划是机器人领域的核心挑战。传统方法依赖领域专业知识定制规划器，常因时空耦合问题导致不可行动作或计划与执行不符。尽管大语言模型（LLM）具备强大的高层语义推理能力，但幻觉可能导致不可行的运动规划。本文提出T3 Planner，一种基于大模型的机器人运动规划框架，通过形式化方法实现自我修正。该框架通过三个级联模块分解时空任务约束，每个模块调用大模型生成候选轨迹序列，并通过信号时序逻辑（STL）验证器检查其可行性，直至找到满足复杂空间、时间及逻辑约束的解。实验表明，T3 Planner在多种场景下显著优于基线方法。所需推理可压缩至轻量级Qwen3-4B模型，支持高效部署。所有补充材料见https://github.com/leeejia/T3_Planner。
原文摘要 · Abstract (English)
Translating natural language instructions into executable motion plans is a fundamental challenge in robotics. Traditional approaches are typically constrained by their reliance on domain-specific expertise to customize planners, and often struggle with spatio-temporal couplings that usually lead to infeasible motions or discrepancies between task planning and motion execution. Despite the proficiency of Large Language Models (LLMs) in high-level semantic reasoning, hallucination could result in infeasible motion plans. In this paper, we introduce the T3 Planner, an LLM-enabled robotic motion planning framework that self-corrects it output with formal methods. The framework decomposes spatio-temporal task constraints via three cascaded modules, each of which stimulates an LLM to generate candidate trajectory sequences and examines their feasibility via a Signal Temporal Logic (STL) verifier until one that satisfies complex spatial, temporal, and logical constraints is found.Experiments across different scenarios show that T3 Planner significantly outperforms the baselines. The required reasoning can be distilled into a lightweight Qwen3-4B model that enables efficient deployment. All supplementary materials are accessible at https://github.com/leeejia/T3_Planner.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。