LogisticsVLN：基于智能体无人机的低空终端配送视觉-语言导航
LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs
- School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）
- Department of Engineering Science, Faculty of Innovation Engineering, Macau University of Science and Technology（澳门科技大学创新工程学院工程科学系）
- China Ship Research and Development Academy（中国船舶科研 Academy）
- Obuda University（奥布达大学）
- State Key Laboratory for Management and Control of Complex Systems, Chinese Academy of Sciences（中国科学院复杂系统管理与控制国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对无人机终端配送中现有VLN任务过于粗粒度的问题，本文提出基于多模态大语言模型的LogisticsVLN系统，并在CARLA中构建VLD数据集验证其可行性。
AI中文摘要：
智能物流需求的日益增长，尤其是细粒度终端配送，凸显了对基于自主无人机（UAV）配送系统的需求。然而，现有大多数最后一公里配送研究依赖地面机器人，而当前基于无人机的视觉-语言导航（VLN）任务主要关注粗粒度、长距离目标，使其不适合精确的终端配送。为弥合这一差距，我们提出LogisticsVLN，一个基于多模态大语言模型（MLLMs）构建的可扩展空中配送系统，用于自主终端配送。LogisticsVLN将轻量级大语言模型（LLMs）和视觉-语言模型（VLMs）集成到模块化流程中，用于请求理解、楼层定位、目标检测和动作决策。为支持这一新场景下的研究与评估，我们在CARLA模拟器中构建了视觉-语言配送（VLD）数据集。在VLD数据集上的实验结果表明了LogisticsVLN系统的可行性。此外，我们对系统各模块进行了子任务级评估，为提高基于基础模型的视觉-语言配送系统的鲁棒性和真实世界部署提供了有价值的见解。
英文摘要：
The growing demand for intelligent logistics, particularly fine-grained terminal delivery, underscores the need for autonomous UAV (Unmanned Aerial Vehicle)-based delivery systems. However, most existing last-mile delivery studies rely on ground robots, while current UAV-based Vision-Language Navigation (VLN) tasks primarily focus on coarse-grained, long-range goals, making them unsuitable for precise terminal delivery. To bridge this gap, we propose LogisticsVLN, a scalable aerial delivery system built on multimodal large language models (MLLMs) for autonomous terminal delivery. LogisticsVLN integrates lightweight Large Language Models (LLMs) and Visual-Language Models (VLMs) in a modular pipeline for request understanding, floor localization, object detection, and action-decision making. To support research and evaluation in this new setting, we construct the Vision-Language Delivery (VLD) dataset within the CARLA simulator. Experimental results on the VLD dataset showcase the feasibility of the LogisticsVLN system. In addition, we conduct subtask-level evaluations of each module of our system, offering valuable insights for improving the robustness and real-world deployment of foundation model-based vision-language delivery systems.
