LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs

TL;DR

LogisticsVLN introduces a novel UAV-based vision-language navigation system for precise terminal delivery, utilizing multimodal large language models and a new dataset to demonstrate feasibility and guide future improvements.

Contribution

The paper presents LogisticsVLN, a scalable aerial delivery system integrating multimodal large language models for autonomous terminal delivery, and introduces the VLD dataset for research and evaluation.

Findings

Feasibility demonstrated on the VLD dataset

Effective modular pipeline for request understanding and action decision

Insights into robustness and deployment challenges

Abstract

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.