通过强制几何一致性实现视觉纳米无人机赛道门3D姿态估计的自监督领域适应
Self-supervised Domain Adaptation for Visual 3D Pose Estimation of Nano-drone Racing Gates by Enforcing Geometric Consistency
AI总结：
本研究提出了一种通过强制几何一致性提升纳米无人机赛道门3D姿态估计的自监督领域适应方法，实验表明其在位置和方向估计上优于现有方法。
摘要：
我们考虑使用卷积神经网络在模拟数据上预训练，以回归无人机赛道门的相对姿态的任务。由于仿真到现实的差距，预训练模型在现实世界中表现不佳，必须适应目标领域。我们提出了一种仅使用无人机在门前任意轨迹飞行所收集的实拍图像序列的无监督领域适应（UDA）方法；序列通过无人机 onboard 传感器测量的里程计进行自监督标注。在该数据集上，状态一致性损失强制不同时间获取的两幅图像产生与无人机里程计一致的姿态预测。结果表明，我们的方法优于其他现有UDA方法，具有较低的平均绝对误差（位置x=26，y=28，z=10厘米，方向ψ=13°），在位置和方向上分别比基线提高了40%和37%。该方法的有效性在仅有10分钟的现实飞行数据下即可体现，并在部署在Crazyflie 2.1 Brushless纳米无人机上时，推断时间仅为30.4ms（33 fps）。\n
英文摘要：
We consider the task of visually estimating the relative pose of a drone racing gate in front of a nano-quadrotor, using a convolutional neural network pre-trained on simulated data to regress the gate's pose. Due to the sim-to-real gap, the pre-trained model underperforms in the real world and must be adapted to the target domain. We propose an unsupervised domain adaptation (UDA) approach using only real image sequences collected by the drone flying an arbitrary trajectory in front of a gate; sequences are annotated in a self-supervised fashion with the drone's odometry as measured by its onboard sensors. On this dataset, a state consistency loss enforces that two images acquired at different times yield pose predictions that are consistent with the drone's odometry. Results indicate that our approach outperforms other SoA UDA approaches, has a low mean absolute error in position (x=26, y=28, z=10 cm) and orientation ($ψ$=13${^{\circ}}$), an improvement of 40% in position and 37% in orientation over a baseline. The approach's effectiveness is appreciable with as few as 10 minutes of real-world flight data and yields models with an inference time of 30.4ms (33 fps) when deployed aboard the Crazyflie 2.1 Brushless nano-drone.
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。
