PencilNet: Zero-Shot Sim-to-Real Transfer Learning for Robust Gate Perception in Autonomous Drone Racing
PencilNet: Zero-Shot Sim-to-Real Transfer Learning for Robust Gate Perception in Autonomous Drone Racing
复制标题
PencilNet：零样本模拟到真实迁移学习，实现自主无人机竞赛中稳健的门感知
DOI：
10.1109/lra.2022.3207545
复制
发表时间：
2022
影响因子：
5.2
通讯作者：
Erdal Kayacan
中科院分区：
文献类型：
--
作者：
H. Pham;Andriy Sarabakha;Mykola Odnoshyvkin;Erdal Kayacan
在自主和移动机器人技术中，主要挑战之一是对环境的强大的飞行感知，这种感知通常是未知的和动态的，就像自动无人机比赛一样。在这项工作中，我们提出了一种新的基于深度神经网络的感知方法-PencilNet1-它依赖于铅笔过滤器顶部的轻量级神经网络主干。这种方法将门的2D位置、距离和方向的预测统一在一个姿势元组中。实验结果表明，该方法对于不需要任何真实训练样本的零射击模拟-真实迁移学习是有效的。此外，与最先进的方法相比，我们的框架对快速飞行中常见的光照变化具有高度的健壮性。一套完整的实验证明了这种方法在多个具有挑战性的场景中的有效性，其中无人机在不同的照明条件下完成各种轨迹。
In autonomous and mobile robotics, one of the main challenges is the robust on-the-fly perception of the environment, which is often unknown and dynamic, like in autonomous drone racing. In this work, we propose a novel deep neural network-based perception method for racing gate detection – PencilNet1 – which relies on a lightweight neural network backbone on top of a pencil filter. This approach unifies predictions of the gates' 2D position, distance, and orientation in a single pose tuple. We show that our method is effective for zero-shot sim-to-real transfer learning that does not need any real-world training samples. Moreover, our framework is highly robust to illumination changes commonly seen under rapid flight compared to state-of-art methods. A thorough set of experiments demonstrates the effectiveness of this approach in multiple challenging scenarios, where the drone completes various tracks under different lighting conditions.