Abstract
Image-goal navigation (ImageNav) tasks a robot with autonomously exploring an unknown environment and reaching a location that visually matches a given target image. While prior works primarily study ImageNav for ground robots, enabling this capability for autonomous drones is substantially more challenging due to their need for high-frequency feedback control and global localization for stable flight. In this paper, we propose a novel sim-to-real framework that leverages visual reinforcement learning (RL) to achieve ImageNav for drones. To enhance visual representation ability, our approach trains the vision backbone with auxiliary tasks, including image perturbations and future transition prediction, which results in more effective policy training. The proposed algorithm enables end-to-end ImageNav with direct velocity control, eliminating the need for external localization. Furthermore, we integrate a depth-based safety module for real-time obstacle avoidance, allowing the drone to safely navigate in cluttered environments. Unlike most existing drone navigation methods that focus solely on reference tracking or obstacle avoidance, our framework supports comprehensive navigation behaviors--autonomous exploration, obstacle avoidance, and image-goal seeking--without requiring explicit global mapping. Code and model checkpoints will be released upon acceptance.
Abstract (translated)
图像目标导航(ImageNav)任务要求机器人自主探索未知环境,并到达一个视觉上与给定的目标图像匹配的位置。尽管先前的工作主要研究了地面机器人的ImageNav,但由于无人机需要高频反馈控制和全局定位以实现稳定飞行,因此为它们提供这种能力更具挑战性。在本文中,我们提出了一种新颖的仿真到现实框架,该框架利用视觉强化学习(RL)来实现无人机的ImageNav。 为了增强视觉表示能力,我们的方法通过辅助任务训练视觉骨干网络,包括图像扰动和未来状态预测,从而提高了策略训练的有效性。所提出的算法实现了端到端的ImageNav,并直接使用速度控制,无需外部定位系统。此外,我们整合了一个基于深度信息的安全模块以实现实时避障功能,使得无人机能够在密集环境中安全导航。 与大多数现有仅专注于参考跟踪或障碍物避免的无人机导航方法不同,我们的框架支持全面的导航行为——自主探索、障碍物规避以及图像目标搜索,并且不需要显式的全局地图。在论文被接受后,我们将发布代码和模型检查点。
URL
https://arxiv.org/abs/2508.12394