论文/arXiv 2610.18381·15 天前

异构环境下面向交互的空中移动能力基准测试

CrossFly用统一仿真与评估框架评测异构环境长程空中移动，并在多类轨迹和VLA智能体上验证。

AI 整理

• 感知与导航
• 仿真与训练
• 具身模型

原文链接：Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments（arXiv 2610.18381 · 发布日期：2026-10-13）

Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments

CrossFly用统一仿真与评估框架评测异构环境长程空中移动，并在多类轨迹和VLA智能体上验证。

核心要点

• 现有空中基准多限于单一环境，且交互评测常从目标附近开始，难以评估连续环境过渡。
• CrossFly包含超过20个重建场景中的15K条轨迹，覆盖室内、室外和Indoor↔Outdoor设置。
• 该工作提出Interaction Readiness Rate，评估终端导航状态是否适合后续交互。
• 五个代表性空中VLA智能体与CrossFly-Agent实验显示，Indoor↔Outdoor更具挑战，未见场景最高成功率为9.7%。

验证范围与局限：验证范围为统一仿真框架中的室内、室外及Indoor↔Outdoor轨迹，并包含一个下游操作案例研究。

英文摘要 (Abstract)

Aerial mobile manipulation requires unmanned aerial vehicles (UAVs) to traverse heterogeneous environments such as indoor and outdoor domains, and connect navigation with subsequent physical interaction within the same trajectories. Existing aerial benchmarks are typically confined to single-environment settings, limiting evaluation of agents across continuous environmental transitions. When interaction is evaluated, agents are often initialized near the target, leaving the transition from navigation to interaction largely unassessed. This work introduces CrossFly, a benchmark for long-horizon interaction-oriented aerial mobility across heterogeneous environments. CrossFly contains 15K trajectories across more than 20 reconstructed scenes under a unified simulation and evaluation framework, covering Indoor, Outdoor, and Indoor$\leftrightarrow$Outdoor trajectories. It further introduces Interaction Readiness Rate (IRR) to assess whether terminal navigation states provide suitable conditions for downstream interaction without assuming a specific manipulation policy. Experiments with five representative aerial vision-language-action (VLA) agents and the proposed CrossFly-Agent show that Indoor$\leftrightarrow$Outdoor settings are more challenging than single-environment settings, with the highest success rate reaching 9.7% on unseen scenes. A downstream manipulation case study further validates the relevance of interaction-oriented arrival to subsequent physical interaction. We hope CrossFly helps advance aerial embodied intelligence toward unified mobility and physical interaction in heterogeneous environments.

作者：Zhibo Duan, Hanlin Kong, Tianran Ma, Yuze Wu, Yuxuan Xu, Kenghou Hoi, Changheng Xie, Xin Zhou, Jianzhe Gao, Fei Gao

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.18381：Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous Environments访问 2026-10-21