Paper Reading AI Learner

LLM-Driven Self-Refinement for Embodied Drone Task Planning

2025-08-21 12:29:01
Deyu Zhang, Xicheng Zhang, Jiahao Li, Tingting Long, Xunhua Dai, Yongjian Fu, Jinrui Zhang, Ju Ren, Yaoxue Zhang

Abstract

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 this https URL.

Abstract (translated)

我们介绍了SRDrone,这是一种为工业级具身无人机的自我完善任务规划设计的新系统。SRDrone包含两个关键技术贡献:首先,它采用了一种连续状态评估方法来稳健且准确地确定任务结果,并提供解释性反馈。这种方法超越了传统的单帧最终状态评估方式,适用于持续、动态的无人机操作。其次,SRDrone实施了一个分层行为树(BT)修改模型。此模型结合多层次的行为树计划分析和受限策略空间,使结构化经验反思学习成为可能。 实验结果表明,与基线方法相比,SRDrone在成功率(SR)方面提高了44.87%。此外,利用迭代自我完善优化的经验库进行真实世界部署后,达到了96.25%的SR。通过将自适应任务改进功能嵌入到工业级行为树规划框架中,SRDrone有效地结合了大型语言模型(LLM)的一般推理智能与具身无人机固有的严格物理执行限制。 代码可在[提供的URL]获取。

URL

https://arxiv.org/abs/2508.15501

PDF

https://arxiv.org/pdf/2508.15501.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot