论文标题
基于视觉的自主无人机控制在模拟中使用监督学习
Vision-Based Autonomous Drone Control using Supervised Learning in Simulation
论文作者
论文摘要
有限的功率和计算资源，缺乏高端传感器设备和受GPS限制的环境是自动驾驶微区域（MAV）面临的挑战。我们在室内环境中自主导航和MAV降落的背景下解决了这些挑战，并使用监督学习提出了一种基于视觉的控制方法。为了实现这一目标，我们在模拟环境中收集了数据样本，该数据样本是根据由路径计划算法确定的最佳控制命令标记的。基于这些数据样本，我们训练了一个卷积神经网络（CNN），该网络（CNN）将低分辨率图像和传感器输入映射到高级控制命令。我们已经观察到在受阻和非启动的模拟环境中都有希望的结果，这表明我们的模型能够成功地将MAV导航到着陆平台。我们的方法需要较短的培训时间，而不是类似的强化学习方法，并且可能会克服可比较的监督学习方法所面临的手动数据收集的局限性。
Limited power and computational resources, absence of high-end sensor equipment and GPS-denied environments are challenges faced by autonomous micro areal vehicles (MAVs). We address these challenges in the context of autonomous navigation and landing of MAVs in indoor environments and propose a vision-based control approach using Supervised Learning. To achieve this, we collected data samples in a simulation environment which were labelled according to the optimal control command determined by a path planning algorithm. Based on these data samples, we trained a Convolutional Neural Network (CNN) that maps low resolution image and sensor input to high-level control commands. We have observed promising results in both obstructed and non-obstructed simulation environments, showing that our model is capable of successfully navigating a MAV towards a landing platform. Our approach requires shorter training times than similar Reinforcement Learning approaches and can potentially overcome the limitations of manual data collection faced by comparable Supervised Learning approaches.
