arXiv 2505.128352025-05-19cs.CLcs.CV

FlightGPT：面向具备泛化性与可解释性的无人机视觉语言导航的视觉语言模型研究

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models

School of Intelligent Systems Engineering, Sun Yat-Sen University（中山大学智能系统工程学院）；DP Technology（DP技术公司）；Beijing University Of Posts and Telecommunications（北京邮电大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tongji University（同济大学）；School of Integrated Innovation, Chulalongkorn University（朱拉隆功大学创新学院）

Hengxing Cai, Jinhan Dong, Jingjun Tan, Jingcheng Deng, Sihang Li, Zhifeng Gao, Haidong Wang, Zicheng Su, Agachai Sumalee, Renxin Zhong

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对无人机视觉语言导航现有方法多模态融合不足、泛化性弱、可解释性差的问题，提出基于VLM的FlightGPT框架，通过两阶段训练与CoT推理机制，在CityNav数据集上实现SOTA性能， unseen环境成功率较最强基线高9.22%。

摘要：

无人机（UAV）视觉语言导航（VLN）在灾害响应、物流配送、城市巡检等应用中至关重要。然而现有方法普遍存在多模态融合不足、泛化能力弱、可解释性差的问题。为应对这些挑战，我们提出FlightGPT——一种基于具备强大多模态感知能力的视觉语言模型（VLM）的新型无人机VLN框架。我们设计了两阶段训练流程：第一阶段使用高质量演示数据进行有监督微调（SFT），以优化初始化效果与结构化推理能力；第二阶段采用Group Relative Policy Optimization（GRPO，组相对策略优化）算法，在综合考虑目标准确率、推理质量与格式合规性的复合奖励引导下，提升模型的泛化性与适应性。此外，FlightGPT引入了基于Chain-of-Thought（CoT，思维链）的推理机制，以提升决策的可解释性。在城市规模数据集CityNav上开展的大量实验表明，FlightGPT在所有场景下均取得了当前最优性能，在未见过的环境中，其成功率比最强基线高出9.22%。我们的实现代码已公开。

英文摘要：

Unmanned Aerial Vehicle (UAV) Vision-and-Language Navigation (VLN) is vital for applications such as disaster response, logistics delivery, and urban inspection. However, existing methods often struggle with insufficient multimodal fusion, weak generalization, and poor interpretability. To address these challenges, we propose FlightGPT, a novel UAV VLN framework built upon Vision-Language Models (VLMs) with powerful multimodal perception capabilities. We design a two-stage training pipeline: first, Supervised Fine-Tuning (SFT) using high-quality demonstrations to improve initialization and structured reasoning; then, Group Relative Policy Optimization (GRPO) algorithm, guided by a composite reward that considers goal accuracy, reasoning quality, and format compliance, to enhance generalization and adaptability. Furthermore, FlightGPT introduces a Chain-of-Thought (CoT)-based reasoning mechanism to improve decision interpretability. Extensive experiments on the city-scale dataset CityNav demonstrate that FlightGPT achieves state-of-the-art performance across all scenarios, with a 9.22\% higher success rate than the strongest baseline in unseen environments. Our implementation is publicly available.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。