Abstract
Obstacle avoidance in unmanned aerial vehicles (UAVs), as a fundamental capability, has gained increasing attention with the growing focus on spatial intelligence. However, current obstacle-avoidance methods mainly depend on limited field-of-view sensors and are ill-suited for UAV scenarios which require full-spatial awareness when the movement direction differs from the UAV's heading. This limitation motivates us to explore omnidirectional obstacle avoidance for panoramic drones with full-view perception. We first study an under explored problem setting in which a UAV must generate collision-free motion in environments with obstacles from arbitrary directions, and then construct a benchmark that consists of three representative flight tasks. Based on such settings, we propose Fly360, a two-stage perception-decision pipeline with a fixed random-yaw training strategy. At the perception stage, panoramic RGB observations are input and converted into depth maps as a robust intermediate representation. For the policy network, it is lightweight and used to output body-frame velocity commands from depth inputs. Extensive simulation and real-world experiments demonstrate that Fly360 achieves stable omnidirectional obstacle avoidance and outperforms forward-view baselines across all tasks. Our model is available at this https URL
Abstract (translated)
无人机（UAV）中的避障能力作为一项基本技能，随着对空间智能的关注日益增加而受到了更多的重视。然而，目前的避障方法主要依赖于视场有限的传感器，在需要全方位感知的情况下尤其不适合，尤其是在移动方向与无人机航向不一致时。这种局限性促使我们探索适用于全视角无人机的全方位避障问题。 本文首先研究了一个尚待深入探讨的问题设置：即在存在来自任意方向障碍物的环境中生成无碰撞运动的能力，然后构建一个包含三种代表飞行任务的基准测试集。基于这些设定，我们提出了Fly360系统，这是一种两阶段感知-决策管道，并采用了固定随机偏航训练策略。 在感知阶段，全景RGB观察数据作为输入并转换为深度图，以形成一种稳健的中间表示形式。对于策略网络而言，它设计得轻量级且直接从深度图像输入输出体框架的速度命令。 通过广泛的模拟和现实世界实验，Fly360展示出能够实现稳定的全方位避障，并在所有任务中都优于向前视图基准线模型的表现。我们的模型可在指定链接获取（注：原文中的链接未能在此显示，请访问原始文档以获得链接）。
URL
https://arxiv.org/abs/2603.06573
