用大模型让无人机自主优化任务计划，实测成功率超96%。
LLM-Driven Self-Refinement for Embodied Drone Task Planning
- 基于连续状态评估和分层行为树，实现任务执行过程的动态反馈与修正。
- 在真实场景中通过自我迭代优化，任务成功率提升至96.25%。
- 适合需要高可靠性的工业级无人机自主决策系统研发者参考。
我们提出SRDrone，一种面向工业级具身无人机的自反思任务规划新系统。该系统包含两项核心技术：其一，采用连续状态评估方法，能够稳健准确地判断任务结果并提供解释性反馈，替代传统单帧终态评估，适用于连续动态的无人机操作；其二，引入分层行为树（BT）修改模型，结合多层级计划分析与受限策略空间，实现从经验中结构化反思学习。实验表明，相较于基线方法，SRDrone在成功率（SR）上提升44.87%。进一步地，利用经过迭代自反思优化的经验库进行真实部署，取得96.25%的高成功率。通过将大语言模型（LLMs）的通用推理智能嵌入工业级行为树规划框架，SRDrone有效融合了大模型的智能与具身无人机严格的物理执行约束。代码已开源：https://github.com/ZXiiiC/SRDrone。
原文摘要 · Abstract (English)
We introduce SRDrone, a novel system designed for self-refinement task planning in industrial-grade embodied drones. SRDrone incorporates two key technical contributions: First, it employs a continuous state evaluation methodology to robustly and accurately determine task outcomes and provide explanatory feedback. This approach supersedes conventional reliance on single-frame final-state assessment for continuous, dynamic drone operations. Second, SRDrone implements a hierarchical Behavior Tree (BT) modification model. This model integrates multi-level BT plan analysis with a constrained strategy space to enable structured reflective learning from experience. Experimental results demonstrate that SRDrone achieves a 44.87% improvement in Success Rate (SR) over baseline methods. Furthermore, real-world deployment utilizing an experience base optimized through iterative self-refinement attains a 96.25% SR. By embedding adaptive task refinement capabilities within an industrial-grade BT planning framework, SRDrone effectively integrates the general reasoning intelligence of Large Language Models (LLMs) with the stringent physical execution constraints inherent to embodied drones. Code is available at https://github.com/ZXiiiC/SRDrone.
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。